class TopsyScrapper:
isFinished = False
def __init__(self, filename):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.filename = filename
self.url = 'http://topsy.com/s?'
self.csvWriter = Csv('topsy.csv')
csvDataHeader = ['Keyword', 'Tweets in last 30 days', 'Topsy Sentiment Score', ' Date of scrape']
self.csvWriter.writeCsvRow(csvDataHeader)
def run(self):
self.scrapData()
self.csvWriter.closeWriter()
def scrapData(self):
try:
file = open(self.filename, 'rb')
for line in file.readlines():
if self.isFinished: return
line = self.regex.replaceData('\r+', '', line)
line = self.regex.reduceNewLine(line)
line = self.regex.reduceBlankSpace(line)
line = line.strip()
if len(line) > 0:
params = urllib.urlencode({'q': line, 'window': 'm', 'type': 'tweet'})
url = self.url + params
self.scrapBrowserData(url, line)
except Exception, x:
print x
class GoogleFinanceScrapper:
isFinished = False
def __init__(self, filename):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.filename = filename
self.url = 'https://www.google.com/finance?'
self.main_url = 'https://www.google.com'
self.csvWriter = Csv('google_finance.csv')
csvDataHeader = ['Ticker Symbol', 'Quarter End', 'Revenue', 'Total Revenue', 'Date of Scrape']
self.csvWriter.writeCsvRow(csvDataHeader)
def run(self):
self.scrapData()
self.csvWriter.closeWriter()
def scrapData(self):
try:
file = open(self.filename, 'rb')
for line in file.readlines():
if self.isFinished: return
line = self.regex.replaceData('\r+', '', line)
line = self.regex.reduceNewLine(line)
line = self.regex.reduceBlankSpace(line)
line = line.strip()
params = urllib.urlencode({'q': line})
url = self.url + params
self.scrapBykeyword(url, line)
except Exception, x:
print x
self.logger.error('Error: ' + x.message)
class AmazonScrapper():
def __init__(self, url):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.url = url
self.base_product_url = 'http://www.amazon.com/dp/'
self.base_image_url = 'http://ecx.images-amazon.com/images/I/'
self.csvWriter = Csv('amazon.csv')
csvDataHeader = ['URL', 'HTML Path', 'Image URLS']
self.csvWriter.writeCsvRow(csvDataHeader)
def scrapData(self):
try:
host = ('Host', 'www.amazon.com')
data = self.spider.fetchData(self.url, host=host)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
searchParams = self.regex.getSearchedData('(?i)var searchParams = {([^\}]*)}', data)
searchParams = searchParams.split(',')
seller = ''
marketPlaceId = ''
useMYI = ''
for searchParam in searchParams:
searchParam = self.regex.reduceBlankSpace(searchParam)
searchParam = self.regex.replaceData('\'', '', searchParam)
if searchParam.startswith('seller'):
seller = searchParam.split(':')[1].strip()
seller = seller.decode('string-escape')
if searchParam.startswith('marketplaceID'):
marketPlaceId = searchParam.split(':')[1].strip()
marketPlaceId = marketPlaceId.decode('string-escape')
if searchParam.startswith('useMYI'):
useMYI = searchParam.split(':')[1].strip()
useMYI = useMYI.decode('string-escape')
params = {'seller': seller,
'marketPlaceId': marketPlaceId,
'useMYI': useMYI}
ajax_url = 'http://www.amazon.com/gp/aag/ajax/productWidget.html'
self.scrapAjaxPage(ajax_url, params, host)
except Exception, x:
print x
class NisbetProduct(QtCore.QThread):
scrapProductData = QtCore.pyqtSignal(object)
stopThread = QtCore.pyqtSignal(int)
def __init__(self):
QtCore.QThread.__init__(self)
self.isExiting = False
self.totalProducts = 0
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('nisbets.csv', 0)
self.csvWriter = Csv('nisbets.csv')
self.mainUrl = 'http://www.nisbets.co.uk'
csvHeaderList = ['URL', 'Product Code', 'Product Technical Specifications', 'Product Name', 'Brand',
'Product Price', 'Product Short Description',
'Product Long Description', 'Image File Name', 'User Manual File Name',
'Exploded View File Name', 'Spares Code', 'Accessories', 'Product Status' 'Category1',
'Category2', 'Category3',
'Category4']
if 'URL' not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvHeaderList)
self.dupCsvRows.append(csvHeaderList[0])
self.utils = Utils()
def run(self):
self.scrapData()
def stop(self):
self.isExiting = True
def scrapData(self):
if self.isExiting: return
self.scrapProductData.emit('<font color=green><b>Main URL: </b>%s</font>' % self.mainUrl)
self.logger.debug('===== URL [' + self.mainUrl + '] =====')
data = self.spider.fetchData(self.mainUrl)
if data and len(str(data).strip()) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category1Chunk = self.regex.getAllSearchedData('(?i)<li id="li-id-\d+">(.*?)</ul> </li>', data)
if category1Chunk and len(str(category1Chunk).strip()) > 0:
i = 0
for category1Data in category1Chunk:
category1 = self.regex.getSearchedData('(?i)<a href="[^"]*">([^<]*)</a>', category1Data)
category2Chunk = self.regex.getAllSearchedData('(?i)<li><a href="([^"]*)">([^<]*)</a>',
category1Data)
if category2Chunk and len(str(category2Chunk).strip()) > 0:
for category2Data in category2Chunk:
try:
self.scrapCategory2Data(self.mainUrl + category2Data[0], category1, category2Data[1])
except Exception, x:
self.logger.error(x)
self.scrapProductData.emit('<font color=red><b>Finish Scraping Product data from %s</b></font>' % self.mainUrl)
class PentaTransaction():
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.loginUrl = 'http://www.v4.penta-transaction.com/telematica_v4/login_ing.jsp'
self.username = '******'
self.password = '******'
self.collectionUrl = 'http://www.trggroup.net/victorinox/index.php?p=124'
self.mainUrl = 'http://www.penta-transaction.com'
def scrapData(self):
self.onLogin()
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
print data
def onLogin(self):
'''
Credentials are:
action login_access
i
p
password sdfsdf
username sdfsdf
'''
try:
print self.loginUrl
loginCredentials = {'username': self.username,
'password': self.password}
loginData = self.spider.login(self.loginUrl, loginCredentials)
if loginData and len(loginData) > 0:
loginData = self.regex.reduceNewLine(loginData)
loginData = self.regex.reduceBlankSpace(loginData)
print 'Login: '******'There was an error when login'
return False
class PaodeacucarScrapper(QThread):
notifyPaode = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.mainUrl = 'http://www.paodeacucar.com.br/'
self.url = 'http://www.paodeacucar.com.br/'
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('paodeacucar.csv', 4)
self.csvWriter = Csv('paodeacucar.csv')
csvDataHeader = ['SKU', 'Category', 'Subcategory', 'Name', 'URL', 'URL Image', 'Details',
'Nutrients Table html code', 'Price from, 28/abr/14', '28/abr/14']
if 'URL' not in self.dupCsvRows:
self.dupCsvRows.append(csvDataHeader)
self.csvWriter.writeCsvRow(csvDataHeader)
def run(self):
self.scrapData()
def scrapData(self):
try:
print 'Main URL: ', self.url
self.notifyPaode.emit(('<font color=green><b>Main URL: %s</b></font>' % self.url))
data = self.spider.fetchData(self.url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
soup = BeautifulSoup(data)
categories = soup.find('nav', class_='items-wrapper').find_all('li', class_=re.compile('\s*item\s*'))
print 'Total Categories: ', len(categories)
self.notifyPaode.emit(('<font color=black><b>Total Categories: %s</b></font>' % str(len(categories))))
for category in categories:
if category.a is not None:
submenu_target = self.regex.replaceData('#', '', category.a.get('data-target'))
sub_categories = soup.find('ul', id=submenu_target).find_all('li', class_='item')
print 'Total Sub Categories: ', len(sub_categories)
self.notifyPaode.emit(('<font color=black><b>Total Subcategories: %s</b></font>' % str(len(sub_categories))))
for sub_category in sub_categories:
sub_category_label = sub_category.find('span', class_='label').text
sub_category_url = sub_category.a.get('href') if sub_category.a is not None else 'N/A'
self.scrapItems(sub_category_url, category.text, sub_category_label)
except Exception, x:
self.logger.error(x.message)
print x
class CsBrands(QThread):
notifyBrand = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow("cs_Brands.csv")
self.csvWriter = Csv("cs_Brands.csv")
self.mainUrl = "http://www.cs-catering-equipment.co.uk/brands"
self.isExiting = False
headerData = [
"URL",
"Parent Category",
"Brand Category",
"Brand Description",
"Image File",
"Product Codes in this category",
]
if headerData not in self.dupCsvRows:
self.csvWriter.writeCsvRow(headerData)
def run(self):
self.scrapBrands()
self.notifyBrand.emit("<font color=red><b>Finished Scraping All Brands.</b></font>")
def scrapBrands(self):
self.notifyBrand.emit("<font color=green><b>Main URL: %s<b></font>" % self.mainUrl)
self.notifyBrand.emit("<b>Try To scrap All Brands.<b>")
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
brandChunks = self.regex.getAllSearchedData('(?i)<div class="man-group man-group-[a-z]">(.*?)</div>', data)
if brandChunks and len(brandChunks) > 0:
for brandChunk in brandChunks:
brands = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', brandChunk)
self.notifyBrand.emit("<b>Total Brands Found: %s<b>" % str(len(brands)))
if brands and len(brands) > 0:
for brand in brands:
try:
self.scrapBrandInfo(brand[0], "Shop By Brand", brand[1])
except Exception, x:
self.logger.error(x)
class CsTest(QThread):
notifyProduct = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows0 = dupCsvReader.readCsvRow('cs_product.csv', 0)
self.dupCsvRows = dupCsvReader.readCsvRow('cs_product.csv', 1)
self.csvWriter = Csv('cs_product.csv')
# self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
self.mainUrl = 'http://www.cs-catering-equipment.co.uk/brands'
self.utils = Utils()
if 'Product Code' not in self.dupCsvRows:
self.csvWriter.writeCsvRow(
['URL', 'Product Code', 'Product Name', 'Manufacturer', 'List Price', 'Product Price', 'Discount',
'Product Short Description', 'Product Long Description', 'Product Technical Specifications', 'Warranty'
,
'Delivery',
'Product Image',
'Category 1', 'Category 2', 'Category 3', 'Category 4', 'Brand Image'])
self.totalProducts = len(self.dupCsvRows)
def run(self):
self.scrapBrands()
self.notifyProduct.emit('<font color=red><b>Finished Scraping All Brands.</b></font>')
def scrapBrands(self):
self.notifyProduct.emit('<font color=green><b>Main URL: %s<b></font>' % self.mainUrl)
self.notifyProduct.emit('<b>Try To scrap All Brands.<b>')
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
brandChunks = self.regex.getAllSearchedData('(?i)<div class="man-group man-group-[a-z]">(.*?)</div>', data)
if brandChunks and len(brandChunks) > 0:
for brandChunk in brandChunks:
brands = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', brandChunk)
self.notifyProduct.emit('<b>Total Brands Found: %s<b>' % str(len(brands)))
if brands and len(brands) > 0:
for brand in brands:
try:
self.scrapBrandInfo(brand[0], 'Shop By Brand', brand[1])
except Exception, x:
self.logger.error(x)
class TopsyScrapper:
isFinished = False
def __init__(self, filename):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.filename = filename
self.url = 'http://topsy.com/s?'
self.csvWriter = Csv('topsy.csv')
csvDataHeader = [
'Keyword', 'Tweets in last 30 days', 'Topsy Sentiment Score',
' Date of scrape'
]
self.csvWriter.writeCsvRow(csvDataHeader)
def run(self):
self.scrapData()
self.csvWriter.closeWriter()
def scrapData(self):
try:
file = open(self.filename, 'rb')
for line in file.readlines():
if self.isFinished: return
line = self.regex.replaceData('\r+', '', line)
line = self.regex.reduceNewLine(line)
line = self.regex.reduceBlankSpace(line)
line = line.strip()
if len(line) > 0:
params = urllib.urlencode({
'q': line,
'window': 'm',
'type': 'tweet'
})
url = self.url + params
self.scrapBrowserData(url, line)
except Exception, x:
print x
class GoogleFinanceScrapper:
isFinished = False
def __init__(self, filename):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.filename = filename
self.url = 'https://www.google.com/finance?'
self.main_url = 'https://www.google.com'
self.csvWriter = Csv('google_finance.csv')
csvDataHeader = [
'Ticker Symbol', 'Quarter End', 'Revenue', 'Total Revenue',
'Date of Scrape'
]
self.csvWriter.writeCsvRow(csvDataHeader)
def run(self):
self.scrapData()
self.csvWriter.closeWriter()
def scrapData(self):
try:
file = open(self.filename, 'rb')
for line in file.readlines():
if self.isFinished: return
line = self.regex.replaceData('\r+', '', line)
line = self.regex.reduceNewLine(line)
line = self.regex.reduceBlankSpace(line)
line = line.strip()
params = urllib.urlencode({'q': line})
url = self.url + params
self.scrapBykeyword(url, line)
except Exception, x:
print x
self.logger.error('Error: ' + x.message)
class WalgreensScrapper():
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.main_url = 'http://www.walgreens.com'
self.url = 'http://www.walgreens.com/store/catalog/shopLanding'
self.sitemap_xml = 'http://www.walgreens.com/sitemap.xml'
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('walgreens.csv')
self.csvWriter = Csv('walgreens.csv')
csvDataHeader = ['Product Name', 'Price', 'Description', 'Shipping', 'Ingredients', 'Image']
if csvDataHeader not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvDataHeader)
def scrapData(self):
try:
print 'First scrapping sitemap...'
self.scrapSiteMap()
print 'Main URL: ' + self.url
data = self.spider.fetchData(self.url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
soup = BeautifulSoup(data)
categoryBar = soup.find('div', class_='wid150 padrt5px padlt5px float-left')
if categoryBar:
categories = categoryBar.find_all('li')
for category in categories:
category_url = self.main_url + category.a.get('href')
self.scrapCategory(category_url)
except Exception, x:
print x
class EbagsScrapper():
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.mainUrl = 'http://www.ebags.com'
self.url = 'http://www.ebags.com/brands'
def scrapData(self):
data = self.spider.fetchData(self.url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
allBrandLinks = []
soup = BeautifulSoup(data)
brandChunks = soup.find_all('div', class_='brandList4Col')
if brandChunks and len(brandChunks) > 0:
for brandChunk in brandChunks:
brandLinks = brandChunk.find_all('a')
if brandLinks and len(brandLinks) > 0:
for brandLink in brandLinks:
brandUrl = brandLink.get('href')
allBrandLinks.append(self.mainUrl + brandUrl)
print 'Total brands found: ', str(len(allBrandLinks))
for brandUrl in allBrandLinks:
self.scrapBrandData(brandUrl)
def scrapBrandData(self, url, page=1):
brandUrl = url if page is 1 else url + '?page=' + str(page)
print 'Brand URL: ', brandUrl
data = self.spider.fetchData(brandUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
soup = BeautifulSoup(data)
productLinks = soup.find_all('div', class_='itemProductName')
if productLinks and len(productLinks) > 0:
for productLink in productLinks:
productUrl = productLink.find('a').get('href')
productDetailUrl = self.mainUrl + productUrl
print 'Product detail url: ', productDetailUrl
fileName = self.regex.getSearchedData('(?i)^.*?(\d+)$', productUrl) + '.html'
print 'File Name: ', fileName
self.scrapProductDetail(self.mainUrl + productUrl, fileName)
## Check if any next page
if soup.find('a', class_='pagingNext') is not None:
nextLink = soup.find('a', class_='pagingNext').get('href')
print nextLink
if nextLink is not None and len(nextLink) > 0:
print 'Pagination found...'
return self.scrapBrandData(url, page + 1)
def scrapProductDetail(self, url, filename):
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
directory = os.path.dirname('./products/' + filename)
if not os.path.exists(directory):
os.makedirs(directory)
print 'File saving path: ', os.path.abspath('./products/' + filename)
dl_file = open('./products/' + filename, 'wb')
dl_file.write(data)
dl_file.close()
class CsProduct(QThread):
notifyProduct = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows0 = dupCsvReader.readCsvRow('cs_product.csv', 0)
self.dupCsvRows = dupCsvReader.readCsvRow('cs_product.csv', 1)
self.csvWriter = Csv('cs_product.csv')
self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
self.utils = Utils()
if 'Product Code' not in self.dupCsvRows:
self.csvWriter.writeCsvRow(
['URL', 'Product Code', 'Product Name', 'Manufacturer', 'List Price', 'Product Price', 'Discount',
'Product Short Description', 'Product Long Description', 'Product Technical Specifications', 'Warranty'
,
'Delivery',
'Product Image',
'Category 1', 'Category 2', 'Category 3', 'Category 4', 'Brand Image'])
self.totalProducts = len(self.dupCsvRows)
def run(self):
self.scrapProduct()
self.notifyProduct.emit('<font color=red><b>Finished Scraping All products.</b></font>')
def scrapProduct(self):
# self.logger.debug('Main URL: ' + self.mainUrl)
self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % self.mainUrl)
data = self.spider.fetchData(self.mainUrl)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)" class="level-top" title="([^"]*)"', data)
if categories and len(categories) > 0:
self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
for category in categories:
category1Name = unicode(category[1]).strip()
self.scrapCategory1Data(str(category[0]).strip(), category1Name)
def scrapCategory1Data(self, url, category1Name):
# self.logger.debug('Category 1 URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category1Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if categories and len(categories) > 0:
self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
for category in categories:
self.scrapCategory2Data(category[0], category1Name, category[1])
def scrapCategory2Data(self, url, category1Name, category2Name):
# self.logger.debug('Category 2 URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category2Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if categories and len(categories) > 0:
for category in categories:
print 'category2: ' + category[0]
self.scrapCategory3Data(category[0], category1Name, category2Name, category[1])
def scrapCategory3Data(self, url, category1Name, category2Name, category3Name):
# self.logger.debug('Category 3 URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category3Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if categories and len(categories) > 0:
for category in categories:
print [category1Name, category2Name, category3Name, category[1]]
self.scrapProductsDetails(category[0], category1Name, category2Name, category3Name, category[1])
def scrapProductsDetails(self, url, category1Name, category2Name, category3Name, category4Name):
self.logger.debug('Product Details URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all products under Category[%s]</b>' % category4Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
maxLimit = 25
maxLimitChunk = self.spider.fetchData(url + '?mode=list')
if maxLimitChunk and len(maxLimitChunk):
maxLimitChunk = self.regex.reduceNewLine(maxLimitChunk)
maxLimitChunk = self.regex.reduceBlankSpace(maxLimitChunk)
maxLimits = self.regex.getAllSearchedData('<option value="[^"]*limit=(\d+)[^"]*"', maxLimitChunk)
# print maxLimits
if maxLimits and len(maxLimits) > 0:
maxLimit = max(map(int, maxLimits))
# print maxLimit
# self.notifyProduct.emit('<font color=blue><b>Max Limit: %s</b></font>' % str(maxLimit))
data = self.spider.fetchData(url + '?limit=' + str(maxLimit) + '&mode=list')
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
products = self.regex.getAllSearchedData('(?i)<div class="listing-item[^"]*?">(.*?)</div>', data)
if products and len(products) > 0:
print len(products)
# self.totalProducts += len(products)
# self.logger.debug('Total Products for %s is [%s]' % (str(len(products)), self.totalProducts))
self.notifyProduct.emit('<font color=green><b>Total Products Found [%s] for category[%s]</b></font>' % (
str(len(products)), category4Name))
for product in products:
productDetailUrl = self.regex.getSearchedData('(?i)<a href="([^"]*)"', product)
if productDetailUrl not in self.dupCsvRows0:
# self.totalProducts += 1
self.dupCsvRows0.append(productDetailUrl)
self.scrapProductDetails(productDetailUrl, category1Name, category2Name, category3Name,
category4Name)
else:
self.notifyProduct.emit(
'<font color=green><b>Already Exists This Product Under Category[%s]. Skip It.</b></font>' % category4Name)
self.notifyProduct.emit(
'<font color=green><b>Total Products Scraped [%s].</b></font>' % str(self.totalProducts))
def scrapProductDetails(self, url, category1Name, category2Name, category3Name, category4Name):
self.logger.debug('Product Detail URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap product details under Category[%s]</b>' % category4Name)
self.notifyProduct.emit('<font color=green><b>Product Detail URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
manufacturer = self.regex.getSearchedData(
'(?i)<span class="manufacturer-box-label">Manufacturer:</span>([^<]*)</p>', data)
productCode = self.regex.getSearchedData(
'(?i)<span class="manufacturer-box-label">Model No:</span>([^<]*)</p>',
data)
if productCode not in self.dupCsvRows:
self.totalProducts += 1
self.dupCsvRows.append(productCode)
else:
self.notifyProduct.emit(
'<font color=green><b>Already Exists This Product Under Category[%s]. Skip It.</b></font>' % category4Name)
return
productName = self.regex.getSearchedData('(?i)<div class="product-name"> <h1>([^<]*)</h1>', data)
productTechnicalDesc = self.regex.getSearchedData('(?i)<div class="product-short-description">([^<]*)</div>'
, data)
productDescriptions = self.regex.getSearchedData('(?i)<div class="product-specs">(.*?)</div>', data)
productShortDesc = ''
productFullDesc = ''
if productDescriptions and len(productDescriptions) > 0:
print 'desc: ' + productDescriptions
productShortDesc = self.regex.getSearchedData('(?i)<p>(.*?)</p>', productDescriptions)
productFullDesc = '\n'.join(
self.regex.getAllSearchedData('(?i)<li>([^<]*)</li>', productDescriptions))
listPriceChunk = self.regex.getSearchedData('(?i)<div class="rrp-price regular-price">(.*?)</div>', data)
listPrice = ''
if listPriceChunk and len(listPriceChunk) > 0:
listPrice = self.regex.getSearchedData('(?i)([0-9,.]+)', listPriceChunk)
savePriceChunk = self.regex.getSearchedData('(?i)<div class="regular-price saving-price">(.*?)</div>', data)
savePrice = ''
if savePriceChunk and len(savePriceChunk) > 0:
savePrice = self.regex.getSearchedData('(?i)([0-9%]+)', savePriceChunk)
priceChunk = self.regex.getSearchedData('(?i)<div class="[^"]*" id="product-price-\d+">(.*?)</div>', data)
price = ''
if priceChunk and len(priceChunk) > 0:
price = self.regex.getSearchedData('(?i)([0-9,.]+)', priceChunk)
deliveryChunk = self.regex.getSearchedData('(?i)<div class="delivery">(.*?)</div>', data)
delivery = ''
if deliveryChunk and len(deliveryChunk) > 0:
delivery = self.regex.getSearchedData('(?i)<p>([^<]*)</p>', deliveryChunk)
warrantyChunk = self.regex.getSearchedData('(?i)<div class="warranty">(.*?)</div>', data)
warranty = ''
if warrantyChunk and len(warrantyChunk) > 0:
warranty = self.regex.getSearchedData('(?i)<p>([^<]*)</p>', warrantyChunk)
## Download and save product images
productImageUrl = self.regex.getSearchedData(
'(?i)src="(http://assets.cs-catering-equipment.co.uk/media/catalog/product/cache/1/image/256x/[^"]*)"',
data)
print productImageUrl
productImage = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_.]*)$', productImageUrl)
if productImage and len(productImage) > 0:
print productImage
self.notifyProduct.emit(
'<font color=green><b>Downloading Product Image [%s]. Please wait...</b></font>' % productImage)
self.downloadFile(productImageUrl, 'product_image/' + productImage)
self.notifyProduct.emit('<font color=green><b>Downloaded Product Image [%s].</b></font>' % productImage)
# self.utils.downloadFile(productImageUrl, 'product_image/' + productImage)
## Download and save brand images
brandImageUrl = self.regex.getSearchedData(
'(?i)<div class="manufacturer-box-left"><a href="[^"]*"[^>]*?><img src="([^"]*)"', data)
brandImage = ''
if brandImageUrl and len(brandImageUrl) > 0:
brandImageUrl = self.regex.replaceData('(?i)logo/', '', brandImageUrl)
brandImage = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_.]*)$', brandImageUrl)
if brandImage and len(brandImage) > 0:
self.notifyProduct.emit(
'<font color=green><b>Downloading Brand Image [%s]. Please wait...</b></font>' % brandImage)
# self.utils.downloadFile(brandImageUrl, 'brand_image/' + brandImage)
self.downloadFile(brandImageUrl, 'brand_image/' + brandImage)
self.notifyProduct.emit('<font color=green><b>Downloaded Brand Image [%s].</b></font>' % brandImage)
csvData = [url, productCode, productName, manufacturer, listPrice, price, savePrice,
productShortDesc, productFullDesc, productTechnicalDesc, warranty, delivery,
productImage,
category1Name, category2Name, category3Name, category4Name, brandImage]
self.csvWriter.writeCsvRow(csvData)
self.logger.debug(unicode(csvData))
self.notifyProduct.emit('<b>Product Details: %s</b>' % unicode(csvData))
def downloadFile(self, url, downloadPath, retry=0):
print url
self.notifyProduct.emit('<b>File URL: %s.</b>' % url)
try:
socket.setdefaulttimeout(10)
opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0))
opener.addheaders = [
('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1')]
urllib2.install_opener(opener)
# resp = opener.open(url, timeout=30)
# resp = urllib2.urlopen(url, timeout=30)
resp = None
try:
# resp = urllib.urlopen(url)
resp = opener.open(url, timeout=30)
except Exception, x:
print x
if resp is None: return False
print resp.info()
print 'info.......'
contentLength = resp.info()['Content-Length']
contentLength = self.regex.getSearchedData('(?i)^(\d+)', contentLength)
totalSize = float(contentLength)
directory = os.path.dirname(downloadPath)
if not os.path.exists(directory):
try:
os.makedirs(directory)
except Exception, x:
print x
dl_file = open(downloadPath, 'wb')
currentSize = 0
CHUNK_SIZE = 32768
totalSizeKB = totalSize / 1024 if totalSize > 0 else totalSize
print 'everything ok............'
while True:
data = None
try:
data = resp.read(CHUNK_SIZE)
except Exception, x:
print x
if not data:
break
currentSize += len(data)
dl_file.write(data)
print('============> ' +\
str(round(float(currentSize * 100) / totalSize, 2)) +\
'% of ' + str(totalSize) + ' bytes')
notifyDl = '===> Downloaded ' + str(round(float(currentSize * 100) / totalSize, 2)) + '% of ' + str(
totalSizeKB) + ' KB.'
self.notifyProduct.emit('<b>%s</b>' % notifyDl)
if currentSize >= totalSize:
dl_file.close()
return True
class MyLinkedIn(QThread):
notifyLinkedIn = pyqtSignal(object)
notifyMember = pyqtSignal(object)
cookieL = pyqtSignal(object)
def __init__(self, username, password):
QThread.__init__(self)
self.spider = Spider()
self.regex = Regex()
self.username = username
self.password = password
def run(self):
if self.login():
self.getAllGroups()
def login(self):
print 'login start'
self.notifyLinkedIn.emit('<b>Trying to login. Please wait...</b>')
loginPageData = self.spider.fetchData(
'https://www.linkedin.com/uas/login?goback=&trk=hb_signin')
loginPageData = self.regex.reduceNewLine(loginPageData)
loginPageData = self.regex.reduceBlankSpace(loginPageData)
## <input type="hidden" name="session_redirect" value="" id="session_redirect-login"><input type="hidden" name="csrfToken" value="ajax:9073845200579364133" id="csrfToken-login"><input type="hidden" name="sourceAlias" value="0_7r5yezRXCiA_H0CRD8sf6DhOjTKUNps5xGTqeX8EEoi" id="sourceAlias-login">
self.sessionRedirect = self.regex.getSearchedData(
'(?i)<input type="hidden" name="session_redirect" value="([^"]*)"',
loginPageData)
self.token = self.regex.getSearchedData(
'(?i)<input type="hidden" name="csrfToken" value="([^"]*)"',
loginPageData)
self.alias = self.regex.getSearchedData(
'(?i)<input type="hidden" name="sourceAlias" value="([^"]*)"',
loginPageData)
loginParam = {
'csrfToken': self.token,
'isJsEnabled': 'true',
'session_key': self.username,
'session_password': self.password,
# 'session_key': '*****@*****.**',
# 'session_password': '******',
'session_redirect': self.sessionRedirect,
'signin': 'Sign In',
'sourceAlias': self.alias,
'source_app': ''
}
print loginParam
print 'start login'
time.sleep(5)
loginData = self.spider.login(
'https://www.linkedin.com/uas/login-submit', loginParam)
loginData = self.regex.reduceNewLine(loginData)
loginData = self.regex.reduceBlankSpace(loginData)
# print loginData
isLoggedIn = self.regex.isFoundPattern('(?i)<li class="signout">',
loginData)
if isLoggedIn:
self.notifyLinkedIn.emit(
'<font color=green><b>Successfully Logged In.</b></font>')
print 'login success'
self.cookieL.emit(self.spider)
return True
else:
self.notifyLinkedIn.emit(
'<font color=red><b>Something wrong with logging in. Please try again or check manually with this username/password</b></font>'
)
return False
def getAllGroups(self):
print 'start groups'
self.notifyLinkedIn.emit(
'<font color=green><b>Start Scraping All Groups.</b></font>')
self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
time.sleep(15)
self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
self.notifyLinkedIn.emit(
'<font color=green><b>Fetching data for scraping your groups.</b></font>'
)
groupsUrl = 'http://www.linkedin.com/myGroups?trk=hb_side_grps_top'
groupsData = self.spider.fetchData(groupsUrl)
self.notifyLinkedIn.emit(
'<font color=green><b>Data fetching complete for scraping your groups.</b></font>'
)
if groupsData is not None and len(groupsData) > 0:
print 'starting groups'
groupsData = self.regex.reduceNewLine(groupsData)
groupsData = self.regex.reduceBlankSpace(groupsData)
print groupsData
## <a href="/groups?gid=72881&trk=myg_ugrp_ovr" class="private" title="This group is members only">MySQL Professionals</a>
groupInfo = self.regex.getAllSearchedData(
'(?i)<a href="(/groups\?gid=[^"]*)"[^>]*>([^<]*)</a>',
groupsData)
if groupInfo is not None and len(groupInfo) > 0:
members = []
for group in groupInfo:
groupUrl = 'http://www.linkedin.com' + str(group[0])
groupName = str(group[1])
self.notifyLinkedIn.emit(
'<b>Group Name: </b>%s <b>URL: </b>%s' %
(groupName, groupUrl))
# http://www.linkedin.com/groups?members=&gid=65688&trk=anet_ug_memb
gid = self.regex.getSearchedData('(?i)gid=(\d+)', group[0])
print gid
groupUrl = 'http://www.linkedin.com/groups?members=&gid=' + gid + '&trk=anet_ug_memb'
members.append((groupName, groupUrl))
self.notifyMember.emit(members)
self.notifyLinkedIn.emit(
'<font color=red><b>Finish Scraping All Groups.</b></font>')
class MyLinkedInMessage(QThread):
notifyLinkedIn = pyqtSignal(object)
def __init__(self, spider, memberList, subject, message):
QThread.__init__(self)
# self.spider = Spider()
self.spider = spider
self.regex = Regex()
self.memberList = memberList
self.subject = unicode(subject)
self.message = unicode(message)
def run(self):
self.sendMessage()
self.notifyLinkedIn.emit('<font color=red><b>Finish Sending All Messages.</b></font>')
def sendMessage(self):
print self.memberList
for member in self.memberList:
messageUrl = 'http://www.linkedin.com/inbox/compose/dialog?insider=true&connId=' + str(member[1])
print messageUrl
# messageUrl = 'http://www.linkedin.com/inbox/compose/dialog?insider=true&connId=' + '65471931'
# data = self.spider.fetchData('http://www.linkedin.com/inbox/compose/dialog?insider=true&connId=65471931')
data = self.spider.fetchData(messageUrl)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
fromName = self.regex.getSearchedData('(?i)<input type="hidden" name="fromName" value="([^"]*)"', data)
fromEmail = self.regex.getSearchedData('(?i)<input type="hidden" name="fromEmail" value="([^"]*)"', data)
# connectionIds = self.regex.getSearchedData('(?i)<input type="hidden" name="connectionIds" value="([^"]*)"', data)
csrfToken = self.regex.getSearchedData('(?i)<input type="hidden" name="csrfToken" value="([^"]*)"', data)
sourceAlias = self.regex.getSearchedData('(?i)<input type="hidden" name="sourceAlias" value="([^"]*)"', data)
linkedInSubject = u'Hi ' + unicode(member[0]).split(' ')[0] + self.subject
linkedInMessage = u'Hi ' + unicode(member[0]).split(' ')[0] + u',\n' + self.message
print linkedInMessage
params = {'addMoreRcpts': 'false',
'ajaxSubmit': 'Send Message',
'allowEditRcpts': 'true',
'body': linkedInMessage,
'connectionIds': str(member[1]),
'connectionNames': '',
'csrfToken': csrfToken,
'fromEmail': fromEmail,
'fromName': fromName,
'itemID': '',
'openSocialAppBodySuffix': '',
'showRecipeints': 'showRecipeints',
'sourceAlias': sourceAlias,
'st': '',
'subject': linkedInSubject,
'submit': 'Send Message',
'viewerDestinationUrl': ''}
print params
msgUrl = 'http://www.linkedin.com/msgToConns?displayCreate='
data = self.spider.fetchData(msgUrl, params)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
if self.regex.isFoundPattern('(?i)<div class="alert success">', data):
print 'Message Sent.'
self.notifyLinkedIn.emit('<font color=green><b>Successfully Sent Message To: %s</b></font>' % member[0])
else:
self.notifyLinkedIn.emit('<font color=red><b>Something Wrong during Send Message To</b></font>' % member[0])
# params = {'addMoreRcpts': 'false',
# 'ajaxSubmit': 'Send Message',
# 'allowEditRcpts': 'true',
# 'body': 'Script Test',
# 'connectionIds': '65471931',
# 'connectionNames': '',
# 'csrfToken': 'ajax: 6539671039643459056',
# 'fromEmail': '467728216',
# 'fromName': 'Mehedi Hasan',
# 'itemID': '',
# 'openSocialAppBodySuffix': '',
# 'showRecipeints': 'showRecipeints',
# 'sourceAlias': '0_6k2algZhQ6vbvlhlVSByxRKi0OB9NXjxrnJYWBFvfhn',
# 'st': '',
# 'subject': 'Script Test',
# 'submit': 'Send Message',
# 'viewerDestinationUrl': ''}
#<input type="hidden" name="fromName" value="Mehedi Hasan" id="fromName-msgForm">
# <input type="hidden" name="showRecipeints" value="showRecipeints" id="showRecipeints-msgForm">
# <input type="hidden" name="fromEmail" value="467728216" id="fromEmail-msgForm">
# <input type="hidden" name="connectionIds" value="65471931" id="connectionIds-msgForm">
# <input type="hidden" name="connectionNames" value="" id="connectionNames-msgForm">
# <input type="hidden" name="allowEditRcpts" value="true" id="allowEditRcpts-msgForm">
# <input type="hidden" name="addMoreRcpts" value="false" id="addMoreRcpts-msgForm">
# <input type="hidden" name="itemID" value="" id="itemID-msgForm">
# <input type="hidden" name="openSocialAppBodySuffix" value="" id="openSocialAppBodySuffix-msgForm">
# <input type="hidden" name="st" value="" id="st-msgForm">
# <input type="hidden" name="viewerDestinationUrl" value="" id="viewerDestinationUrl-msgForm">
# <input type="hidden" name="csrfToken" value="ajax:6539671039643459056" id="csrfToken-msgForm">
# <input type="hidden" name="sourceAlias" value="0_6k2algZhQ6vbvlhlVSByxRKi0OB9NXjxrnJYWBFvfhn" id="sourceAlias-msgForm">
"""
msgUrl1 = 'http://www.linkedin.com/msgToConns?displayCreate='
msgParams = {}
addMoreRcpts false
ajaxSubmit Send Message
allowEditRcpts true
body fdgdfgdfgdfg dg d
connectionIds 57414219
connectionNames
csrfToken ajax:3480949306085123249
fromEmail 467728216
fromName Mehedi Hasan
goback .con.npv_57414219_*1_*1_name_r5tN_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1
itemID
openSocialAppBodySuffix
showRecipeints showRecipeints
sourceAlias 0_6k2algZhQ6vbvlhlVSByxRKi0OB9NXjxrnJYWBFvfhn
st
subject
viewerDestinationUrl
"""
"""addMoreRcpts false
class WebTable():
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.browser = BrowserUtil()
self.regex = Regex()
self.utils = Utils()
self.csvHeader = ['Category', 'Sub Category 1', 'Sub Category 2', 'Product Code', 'Product Name',
'Product ShortName', 'Product Description', 'List Price', 'Vendor Price', 'Availability',
'Power', 'Size', 'KW', 'Weight(kg)', 'Other Tech', 'Pdf File', 'Image File']
self.totalProducts = 0
def scrapData(self):
postParams = {'__ASYNCPOST': 'true',
'__EVENTVALIDATION': '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',
'__VIEWSTATE': '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',
'btn': 'Search',
'ddlcategory': 'MIN',
'ddlstate': 'Gujarat',
'ddlstatus': 'UPEC',
'ddlyear': '2011',
'textbox2': '',
'ww': 'UpdatePanel3'}
data = self.spider.fetchData('http://environmentclearance.nic.in/Search.aspx', postParams)
print data
data = self.spider.fetchData1('http://environmentclearance.nic.in/Search.aspx')
print data
# soup = BeautifulSoup(data)
def scrapSubCat1(self, url):
print 'url: ', url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
for cat in soup.find_all('td', {"class": re.compile("item_level")}):
c = cat.find("a", {"href": re.compile('rayons\.aspx\?value_path=.*?$'),
"id": re.compile('ctl00_cph_center_dl_level_ctl\d+_a_level.*?$')})
if c:
print c.string.strip()
self.scrapSubCat2('http://www.diamond-europe.com/' + c.get("href"))
def scrapSubCat2(self, url):
print 'url1: ' + url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
for cat in soup.find_all('div', {'class': re.compile('bg_ombre')}):
self.scrapProducts('http://www.diamond-europe.com/' + cat.find('a').get('href'))
def scrapProducts(self, url):
print 'url2', url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
results = soup.find('table', {'id': 'results'})
if results:
for row in results.find_all('tr'):
colRef = row.find('td', {'class': 'reference'})
if colRef:
prCode = colRef.find('span', {'class': 'imp'})
price1 = colRef.find('span',
{'id': re.compile('ctl\d+_cph_center_r_articles_ctl\d+_l_prix_barre$')})
price2 = colRef.find('span', {'class', 'promo'})
print prCode.string.strip()
print price1.string.strip()
print price2.string.strip()
coldesc = row.find('td', {'class': re.compile('description.*?$')})
if coldesc:
pr = coldesc.find('a')
print pr.string.strip()
self.scrapProductDetails('http://www.diamond-europe.com/' + pr.get('href'))
def scrapProductDetails(self, url):
print 'Detail url: ' + url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
productDescS = soup.find('span', 'h1_nom_article')
print productDescS.string.strip()
productDesc = soup.find('div', {'id': 'article_right'})
print productDesc.text.strip()
specs = soup.find('ul', {'id': 'spec_tech'})
if specs:
print specs.contents
"""
__ASYNCPOST true
__EVENTARGUMENT
__EVENTTARGET ctl00$cph_center$menu_left1$lb_login
__EVENTVALIDATION /wEWEwKOk7qrBAKG4eyLBALGw+PfBwK7jI7eDQL/2fqXBwLH9rmjDwLG2KLDCAKCvreACALPgYP1DQKqvLeACAKKtP7+DAL07MD3CwLksZZaAuSxmloCicn43Q8Cisn43Q8C/Iag2AMClcHvlQgCyNGw1Ax/PwzywfL/ooD/FU51memYxQ1U+Q==
__LASTFOCUS
__SCROLLPOSITIONX 0
__SCROLLPOSITIONY 0
__VIEWSTATE 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
ctl00$ToolkitScriptManage... ctl00$cph_center$menu_left1$up_login|ctl00$cph_center$menu_left1$lb_login
ctl00$cph_center$hf_value...
ctl00$cph_center$menu_lef...
ctl00$cph_center$menu_lef... C913327
ctl00$cph_center$menu_lef... sdfsdfsdf
ctl00$cph_center$n_vei$cp...
ctl00$cph_center$n_vei$hf...
ctl00$ddl_search_type Reference
ctl00$tb_search
ctl00_ToolkitScriptManage... ;;AjaxControlToolkit, Version=3.5.40412.0, Culture=neutral, PublicKeyToken=28f01b0e84b6d53e:en-GB:1547e793-5b7e-48fe-8490-03a375b13a33:de1feab2:f2c8e708:720a52bf:f9cec9bc:589eaa30:698129cf:7a92f56c:4a2c8239;
hiddenInputToUpdateATBuff... 1
"""
def loginDiamondEurope(self):
params = {'__ASYNCPOST': 'true',
'__EVENTARGUMENT': '',
'__EVENTTARGET': 'ctl00$cph_center$menu_left1$lb_login',
'__EVENTVALIDATION': '/wEWEwKOk7qrBAKG4eyLBALGw+PfBwK7jI7eDQL/2fqXBwLH9rmjDwLG2KLDCAKCvreACALPgYP1DQKqvLeACAKKtP7+DAL07MD3CwLksZZaAuSxmloCicn43Q8Cisn43Q8C/Iag2AMClcHvlQgCyNGw1Ax/PwzywfL/ooD/FU51memYxQ1U+Q==',
'__LASTFOCUS': '',
'__SCROLLPOSITIONX': '0',
'__SCROLLPOSITIONY': '0',
'__VIEWSTATE': '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',
'ctl00$ToolkitScriptManager1': 'ctl00$cph_center$menu_left1$up_login|ctl00$cph_center$menu_left1$lb_login',
'ctl00$cph_center$menu_left1$tb_login': '******',
'ctl00$cph_center$menu_left1$tb_password': '******',
'ctl00$ddl_search_type': 'Reference',
'ctl00_ToolkitScriptManager1HiddenField': ';;AjaxControlToolkit, Version=3.5.40412.0, Culture=neutral, PublicKeyToken=28f01b0e84b6d53e:en-GB:1547e793-5b7e-48fe-8490-03a375b13a33:de1feab2:f2c8e708:720a52bf:f9cec9bc:589eaa30:698129cf:7a92f56c:4a2c8239;',
'hiddenInputToUpdateATBuffer_CommonToolkitScripts':
'1'}
if self.spider.login('http://www.diamond-europe.com/rayons.aspx', params) is not None:
return True
return False
def scrapBertos(self, retry=0):
# self.downloadFile('http://s900.bertos.it/download.php?file=editorcms/documentazione/schede/scheda_13722600.pdf', 'a.pdf')
# self.scrapSubCategory('http://s900.bertos.it/en/', '', None, None)
# self.scrapProducts('http://s900.bertos.it/en/pasta_cookers/', '', '', None, None)
# return
self.notifyProduct.emit('<font color=green><b>Try to get all language links.</b></font>')
self.logger.debug(self.mainUrl)
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
languages = self.regex.getAllSearchedData(
'(?i)<div class="[^"]*"><a href="([^"]*)"\s*?class="boxalingua">([^<]*)</a>', data)
if languages and len(languages) > 0:
self.logger.debug('Total languages: %s' % str(len(languages)))
self.notifyProduct.emit('<b>Total languages found[%s]</b>' % str(len(languages)))
for language in languages:
self.totalProducts = 0
url = language[0]
# if str(language[1]).lower() != 'en':
# continue
urlChunk = self.spider.fetchData(url)
if urlChunk and len(urlChunk) > 0:
urlChunk = self.regex.reduceNewLine(urlChunk)
urlChunk = self.regex.reduceBlankSpace(urlChunk)
url = self.regex.getSearchedData('(?i)<a href="([^"]*)" onmouseover="vedi_po_cat\(2\)\s*?"',
urlChunk)
csvFile = str(language[1].strip()).lower() + '_' + 'bertos.csv'
dupCsvReader = Csv()
dupCsvRows = dupCsvReader.readCsvRow(csvFile)
csvWriter = Csv(csvFile)
if self.csvHeader not in dupCsvRows:
dupCsvRows.append(self.csvHeader)
csvWriter.writeCsvRow(self.csvHeader)
self.notifyProduct.emit(
'<font color=green><b>Try to get data for language [%s].</b></font>' % language[1])
self.scrapCategory(url, dupCsvRows, csvWriter)
self.notifyProduct.emit(
'<font color=red><b>===== Finish scraping data for [%s] =====</b></font><br /><br />' %
language[1])
else:
if retry < 5:
return self.scrapBertos(retry + 1)
def scrapCategory(self, mainUrl, dupCsvRows, csvWriter):
url = mainUrl
self.logger.debug('Main URL: ' + url)
self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
data = self.regex.reduceNbsp(data)
self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
categoryChunk = self.regex.getSearchedData('(?i)<div id="contenuto1">(.*?)</div>\s*?</div>', data)
if categoryChunk and len(categoryChunk) > 0:
categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', categoryChunk)
if categories and len(categories) > 0:
self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
for category in categories:
categoryName = category[1].strip()
self.scrapSubCategory(str(category[0]).strip(), categoryName, dupCsvRows, csvWriter)
def scrapSubCategory(self, url, categoryName, dupCsvRows, csvWriter):
self.logger.debug('Category URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap subcategories for: %s</b>' % categoryName)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
subCategories = self.regex.getAllSearchedData('(?i)<li\s*?><a href="([^"]*)" title="([^"]*)"', data)
if subCategories and len(subCategories) > 0:
self.notifyProduct.emit(
'<font color=green><b>Total subcategories found %s.</b></font>' % str(len(subCategories)))
for subCategory in subCategories:
subCategoryName = subCategory[1].strip()
self.scrapProducts(subCategory[0].strip(), categoryName, subCategoryName, dupCsvRows, csvWriter)
def downloadFile(self, url, downloadPath, retry=0):
print url
self.notifyProduct.emit('<b>File URL: %s.</b>' % url)
try:
socket.setdefaulttimeout(10)
opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0))
opener.addheaders = [
('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1')]
urllib2.install_opener(opener)
# resp = opener.open(url, timeout=30)
# resp = urllib2.urlopen(url, timeout=30)
resp = None
try:
# resp = urllib.urlopen(url)
resp = opener.open(url, timeout=30)
except Exception, x:
print x
if resp is None: return False
# if resp.info()['Connection'] == 'close' or resp.getcode() != 200:
# if retry < 3:
# self.notifyProduct.emit('<font color=red><b>Failed to download file. Retrying...</b></font>')
# return self.downloadFile(url, downloadPath, retry + 1)
# else:
# self.notifyProduct.emit('<font color=red><b>Failed to download file after 3 retry.</b></font>')
# return
print resp.info()
print 'info.......'
contentLength = resp.info()['Content-Length']
contentLength = self.regex.getSearchedData('(?i)^(\d+)', contentLength)
totalSize = float(contentLength)
directory = os.path.dirname(downloadPath)
if not os.path.exists(directory):
try:
os.makedirs(directory)
except Exception, x:
print x
dl_file = open(downloadPath, 'wb')
currentSize = 0
CHUNK_SIZE = 32768
totalSizeKB = totalSize / 1024 if totalSize > 0 else totalSize
print 'everything ok............'
while True:
data = None
try:
data = resp.read(CHUNK_SIZE)
except Exception, x:
print x
if not data:
break
currentSize += len(data)
dl_file.write(data)
print('============> ' + \
str(round(float(currentSize * 100) / totalSize, 2)) + \
'% of ' + str(totalSize) + ' bytes')
notifyDl = '===> Downloaded ' + str(round(float(currentSize * 100) / totalSize, 2)) + '% of ' + str(
totalSizeKB) + ' KB.'
self.notifyProduct.emit('<b>%s</b>' % notifyDl)
if currentSize >= totalSize:
dl_file.close()
return True
class WpScrapper():
def __init__(self, input_file, output_file):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.input_file = input_file
self.output_file = output_file
def scrapData(self):
csv_writer = csv.writer(open(self.output_file, 'wb'), delimiter=';')
with open(self.input_file, 'rb') as csvfile:
csv_rows = csv.reader(csvfile, delimiter=';')
rows = list(csv_rows)
total = len(rows)
counter = 0
for row in rows:
counter += 1
print '---------------- Checking [%d] of [%d] records. ----------------------' % (counter, total)
self.logger.debug('Checking %d of %d records.' % (counter, total))
domain = 'http://' + row[0] + '/wp-login.php'
https_domain = 'https://' + row[0] + '/wp-login.php'
wp_admin = 'http://' + row[0] + '/wp-admin/'
https_wp_admin = 'https://' + row[0] + '/wp-admin/'
username = row[1]
password = row[2]
status = 0
print 'Login Credential => Domain: ' + domain + ' User: '******' Password: '******'Login Credential => Domain: ' + domain + ' User: '******' Password: '******'Successfully logged in.'
self.logger.debug('Successfully logged in.')
status = 1
else:
print 'Login failed!'
self.logger.debug('Login failed!')
csv_writer.writerow([row[0], username, password, status])
print '---------------- End of checking [%d] of [%d] records. ----------------------' % (counter, total)
print '\n\n'
def onLogin(self, url, https_url, wp_url, https_wp_url, username, password):
'''
Credentials are:
action login_access
i
p
password sdfsdf
username sdfsdf
'''
try:
loginCredentials = {'log': username,
'pwd': password,
'redirect_to': wp_url}
print 'Credentials', loginCredentials
print 'Please wait...Try to login with your credentials.'
redirected_url, loginData = self.spider.login(url, loginCredentials)
print 'redirected url: ', redirected_url
if loginData and len(loginData) > 0:
loginData = self.regex.reduceNewLine(loginData)
loginData = self.regex.reduceBlankSpace(loginData)
print 'After login data: ', loginData
if redirected_url is not None and redirected_url.strip() == wp_url.strip(): return True
# if loginData and len(loginData) > 0:
# loginData = self.regex.reduceNewLine(loginData)
# loginData = self.regex.reduceBlankSpace(loginData)
# soup = BeautifulSoup(loginData)
# if soup.find('div', {'id': 'login_error'}):
# return False
# else:
# return True
except Exception, x:
print x
print 'There was an error when login with http'
try:
https_loginCredentials = {'log': username,
'pwd': password,
'redirect_to': https_wp_url}
print 'Credentials', https_loginCredentials
print 'Please wait...Try to login with your credentials.'
https_redirected_url, https_login_data = self.spider.login(https_url, https_loginCredentials)
if https_redirected_url is not None and https_redirected_url.strip() == https_wp_url.strip(): return True
except Exception, x:
print x
print 'There was an error when login with https'
class MyLinkedInMembers(QThread):
notifyLinkedIn = pyqtSignal(object)
notifyMembers = pyqtSignal(object)
cookieL = pyqtSignal(object)
def __init__(self, spider, url, pageRange=None):
QThread.__init__(self)
# self.spider = Spider()
self.spider = spider
self.regex = Regex()
self.url = url
self.startPage = None
self.endPage = None
if self.regex.isFoundPattern('(?i)(\d+)-(\d+)', str(pageRange).strip()):
pageRangeFormat = self.regex.getSearchedDataGroups('(?i)(\d+)-(\d+)', str(pageRange).strip())
self.startPage = int(pageRangeFormat.group(1))
self.endPage = int(pageRangeFormat.group(2))
elif self.regex.isFoundPattern('(?i)(\d+)', str(pageRange).strip()):
pageRangeFormat = self.regex.getSearchedDataGroups('(?i)(\d+)', str(pageRange).strip())
self.startPage = int(pageRangeFormat.group(1))
self.endPage = self.startPage
def run(self):
self.getMembers(self.url)
self.notifyLinkedIn.emit('<font color=red><b>Finish scraping members.<b></font>')
def getMembers(self, url, pageNumber=0):
print 'Members URL: ' + url
self.notifyLinkedIn.emit('<font color=green><b>Start Scraping All Members.<b></font>')
self.notifyLinkedIn.emit('<b>Wait For 15 seconds Break...<b>')
time.sleep(15)
self.notifyLinkedIn.emit('<b>15 seconds Break Finish.<b>')
groupData = self.spider.fetchData(str(url).replace('&', '&'))
groupData = self.regex.reduceNewLine(groupData)
groupData = self.regex.reduceBlankSpace(groupData)
print groupData
print 'page number: ' + str(pageNumber)
if pageNumber > 0:
harvestedMembers = []
allMembers = self.regex.getAllSearchedData('(?i)<li class="member" id="member-[^"]*"[^>]*?>(.*?)</div>',
groupData)
for members in allMembers:
memberId = self.regex.getSearchedData('(?i)data-li-memberId="([^"]*)"', members)
memberName = self.regex.getSearchedData('(?i)data-li-fullName="([^"]*)"', members)
memberTitle = self.regex.getSearchedData('(?i)<p class="headline">([^<]*?)</p>', members)
memberTitle = self.regex.replaceData('(?i)&', '&', memberTitle)
harvestedMembers.append((memberId, memberName, memberTitle))
self.notifyLinkedIn.emit('<b>Member ID: </b>%s <b>Member Name: </b>%s' % (memberId, memberName + ' (' + memberTitle + ')'))
# members = self.regex.getAllSearchedData(
# '(?i)class="send-message" data-li-memberId="([^"]*)" data-li-fullName="([^"]*)"', groupData)
# print members
self.notifyMembers.emit(harvestedMembers)
# for member in members:
# print member
# self.notifyLinkedIn.emit('<b>Member Name: </b>%s <b>Member ID: </b>%s' % (member[1], member[0]))
urlNext = self.regex.getSearchedData('(?i)<a href="([^"]*)"[^>]*?>\s*?<strong>\s*?next', groupData)
if urlNext and len(urlNext) > 0:
# nextP = int(self.regex.getSearchedData('(?i).*?(\d+)$', urlNext.strip()))
urlNext = self.regex.replaceData('(?i)&', '&', urlNext)
urlNext = self.regex.replaceData('(?i)split_page=\d+', 'split_page=', urlNext)
pageNumber += 1
if self.startPage <= pageNumber <= self.endPage:
self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
time.sleep(15)
print 'sleep 15 s'
self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
self.getMembers('http://www.linkedin.com' + urlNext + str(pageNumber), pageNumber)
elif pageNumber < self.startPage:
pageNumber = self.startPage
self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
time.sleep(15)
print 'page number less 0 sleep'
self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
self.getMembers('http://www.linkedin.com' + urlNext + str(pageNumber), pageNumber)
if self.startPage is None and self.endPage is None:
pageNumber += 1
self.notifyLinkedIn.emit('<b>Wait for 15 second break...</b>')
time.sleep(15)
print 'page number less 0 sleep'
self.notifyLinkedIn.emit('<b>15 second break finish!!!</b>')
self.getMembers('http://www.linkedin.com' + urlNext + str(pageNumber), pageNumber)
class Scrapper(QThread):
notifyScrapper = pyqtSignal(object)
isFinished = False
def __init__(self, urllist):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
print urllist
self.urllist = urllist
self.csv = Csv('scrapper.csv')
def run(self):
self.scrapData()
self.notifyScrapper.emit(
'<font color=green><b>------------------ Finish! ------------------------- </b></font>')
def scrapData(self):
try:
total = 0
csvHeader = ['URL', 'Title', 'Price', 'Brand', 'Features', 'Material', 'Measurements', 'Category',
'Size', 'Color', 'Design']
self.csv.writeCsvRow(csvHeader)
if self.isFinished: return
for url in self.urllist:
if len(url) > 0:
url = self.regex.replaceData('(?i)\r', '', url)
url = self.regex.replaceData('(?i)\n', '', url)
url = self.regex.getSearchedData('(?i)(http.*?)$', url)
print 'URL: ', url
self.notifyScrapper.emit(('<font color=green><b>URL: %s</b></font>' % url))
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
soup = BeautifulSoup(data)
soup.prettify()
title = ''
price = ''
size = ''
brand = ''
features = ''
material = ''
measurements = ''
category = ''
color = ''
design = ''
if soup.find('span', id='vi-lkhdr-itmTitl') is not None:
title = soup.find('span', id='vi-lkhdr-itmTitl').text
if soup.find('span', id='prcIsum'):
price = soup.find('span', id='prcIsum').text
if soup.find('div', class_='itemAttr'):
specchunk = soup.find('div', class_='itemAttr')
rows = specchunk.find_all('tr')
for row in rows:
cols = row.find_all('td')
for i in range(0, len(cols), 2):
# if self.regex.isFoundPattern('(?i)Condition:', cols[i].text.strip()):
# conditionChunk = cols[i + 1]
# conditionChunk = self.regex.replaceData(u'(?i)<span class="infoLink u-nowrap" id="readFull">.*?</span>', '', unicode(conditionChunk))
# conditionChunk = self.regex.replaceData(u'(?i)<b class="g-hdn">.*?</b>', '', conditionChunk)
# condition = BeautifulSoup(conditionChunk).text
# print condition
if self.regex.isFoundPattern('(?i)Brand:', cols[i].text.strip()):
brand = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Features:', cols[i].text.strip()):
features = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Material:', cols[i].text.strip()):
material = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Measurements:', cols[i].text.strip()):
measurements = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Category:', cols[i].text.strip()):
category = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Color:', cols[i].text.strip()):
color = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Design:', cols[i].text.strip()):
design = cols[i + 1].text
if self.regex.isFoundPattern('(?i)Size:', cols[i].text.strip()):
size = cols[i + 1].text
self.notifyScrapper.emit('<font color=black><b>Writting data to csv file.</b></font>')
csvData = [url, title, price, brand, features, material, measurements, category, size, color, design]
self.notifyScrapper.emit('<font color=black><b>Data: %s</b></font>' % unicode(csvData))
self.csv.writeCsvRow(csvData)
self.notifyScrapper.emit('<font color=black><b>Successfully Written data to csv file.</b></font>')
total += 1
self.notifyScrapper.emit('<font color=green><b>Total Data scrapped: [%s]</b></font>' % str(total))
except Exception, x:
self.notifyScrapper.emit('<font color=red><b>Error scrapping category: %s</b></font>' % x.message)
self.logger.error(x.message)
print x
class NisbetCat(QtCore.QThread):
scrapCategoryData = QtCore.pyqtSignal(object)
stopThread = QtCore.pyqtSignal(int)
def __init__(self):
QtCore.QThread.__init__(self)
self.isExiting = False
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('nisbetCat.csv')
self.csvWriter = Csv('nisbetCat.csv')
self.mainUrl = 'http://www.nisbets.co.uk'
csvHeaderList = ['Parent Category', 'Category Name', 'Category Description']
if csvHeaderList not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvHeaderList)
self.dupCsvRows.append(csvHeaderList)
def run(self):
self.scrapData()
def stop(self):
self.isExiting = True
def scrapData(self):
if self.isExiting: return
self.scrapCategoryData.emit('<font color=green><b>Main URL: </b>%s</font>' % self.mainUrl)
self.logger.debug('===== URL [' + self.mainUrl + '] =====')
data = self.spider.fetchData(self.mainUrl)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
links = self.regex.getAllSearchedData('(?i)<li id="li-id-\d+"> <a href="([^"]*)">([^<]*)</a>', data)
if links:
for link in links:
self.scrapCategoryData.emit('<b>Link URL: </b>%s' % (self.mainUrl + link[0]))
self.logger.debug('===Link URL [' + self.mainUrl + link[0] + '] ===')
csvData = ['Home']
category = link[1]
csvData.append(category)
linkInfo = self.spider.fetchData(self.mainUrl + link[0])
if linkInfo:
linkInfo = self.regex.reduceNewLine(linkInfo)
linkInfo = self.regex.reduceBlankSpace(linkInfo)
csvData.append(
self.regex.getSearchedData('(?i)<p class="br5px padding10 mb0 mt10">([^<]*)</p>', linkInfo))
self.logger.debug('Category ' + str(csvData))
if csvData not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvData)
self.dupCsvRows.append(csvData)
self.scrapCategoryData.emit('<b>Scraped Data: </b>%s<br />' % str(csvData))
else:
self.scrapCategoryData.emit(
'<font color=green><b>Already Scrapped Skip This Category</b></font>')
## After write first cat data
subUrlsChunk = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>',
linkInfo)
if subUrlsChunk:
subUrls = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<span', subUrlsChunk)
if subUrls:
for subUrl in subUrls:
self.scrapSubCat(self.mainUrl + subUrl[0], category, subUrl[1])
self.scrapCategoryData.emit(
'<font color=red><b>Finish Scraping Category data from %s</b></font>' % self.mainUrl)
def scrapSubCat(self, url, parentCat, category):
if self.isExiting: return
self.scrapCategoryData.emit('<b>Link URL: </b>%s' % url)
self.logger.debug('== Sub URL [' + url + '] ==')
data = self.spider.fetchData(url)
if data:
csvData = [parentCat, category]
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
csvData.append(self.regex.getSearchedData('(?i)<p class="br5px padding10 mb0 mt10">([^<]*)</p>', data))
self.logger.debug('Sub Category ' + str(csvData))
if csvData not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvData)
self.dupCsvRows.append(csvData)
self.scrapCategoryData.emit('<b>Scraped Data: </b>%s<br />' % str(csvData))
else:
self.scrapCategoryData.emit('<font color=green><b>Already Scrapped Skip This Category</b></font>')
## After write first cat data
subUrlsChunk = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
if subUrlsChunk:
subUrls = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<span', subUrlsChunk)
if subUrls:
for subUrl in subUrls:
self.scrapSubSubCat(self.mainUrl + subUrl[0], category, subUrl[1])
def scrapSubSubCat(self, url, parentCat, category):
if self.isExiting: return
self.scrapCategoryData.emit('<b>Link URL: </b>%s' % url)
self.logger.debug('== SUb SUb URL [' + url + '] ==')
data = self.spider.fetchData(url)
if data:
csvData = [parentCat, category]
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
csvData.append(self.regex.getSearchedData('(?i)<p class="br5px padding10 mb0 mt10">([^<]*)</p>', data))
self.logger.debug('Sub SUb Category ' + str(csvData))
if csvData not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvData)
self.dupCsvRows.append(csvData)
self.scrapCategoryData.emit('<b>Scraped Data: </b>%s<br />' % str(csvData))
else:
self.scrapCategoryData.emit('<font color=green><b>Already Scrapped Skip This Category</b></font>')
class WpScrapper():
def __init__(self, input_file, output_file):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.input_file = input_file
self.output_file = output_file
def scrapData(self):
csv_writer = csv.writer(open(self.output_file, 'wb'), delimiter=';')
with open(self.input_file, 'rb') as csvfile:
csv_rows = csv.reader(csvfile, delimiter=';')
rows = list(csv_rows)
total = len(rows)
counter = 0
for row in rows:
counter += 1
print '---------------- Checking [%d] of [%d] records. ----------------------' % (
counter, total)
self.logger.debug('Checking %d of %d records.' %
(counter, total))
domain = 'http://' + row[0] + '/wp-login.php'
https_domain = 'https://' + row[0] + '/wp-login.php'
wp_admin = 'http://' + row[0] + '/wp-admin/'
https_wp_admin = 'https://' + row[0] + '/wp-admin/'
username = row[1]
password = row[2]
status = 0
print 'Login Credential => Domain: ' + domain + ' User: '******' Password: '******'Login Credential => Domain: ' + domain +
' User: '******' Password: '******'Successfully logged in.'
self.logger.debug('Successfully logged in.')
status = 1
else:
print 'Login failed!'
self.logger.debug('Login failed!')
csv_writer.writerow([row[0], username, password, status])
print '---------------- End of checking [%d] of [%d] records. ----------------------' % (
counter, total)
print '\n\n'
def onLogin(self, url, https_url, wp_url, https_wp_url, username,
password):
'''
Credentials are:
action login_access
i
p
password sdfsdf
username sdfsdf
'''
try:
loginCredentials = {
'log': username,
'pwd': password,
'redirect_to': wp_url
}
print 'Credentials', loginCredentials
print 'Please wait...Try to login with your credentials.'
redirected_url, loginData = self.spider.login(
url, loginCredentials)
print 'redirected url: ', redirected_url
if loginData and len(loginData) > 0:
loginData = self.regex.reduceNewLine(loginData)
loginData = self.regex.reduceBlankSpace(loginData)
print 'After login data: ', loginData
if redirected_url is not None and redirected_url.strip(
) == wp_url.strip():
return True
# if loginData and len(loginData) > 0:
# loginData = self.regex.reduceNewLine(loginData)
# loginData = self.regex.reduceBlankSpace(loginData)
# soup = BeautifulSoup(loginData)
# if soup.find('div', {'id': 'login_error'}):
# return False
# else:
# return True
except Exception, x:
print x
print 'There was an error when login with http'
try:
https_loginCredentials = {
'log': username,
'pwd': password,
'redirect_to': https_wp_url
}
print 'Credentials', https_loginCredentials
print 'Please wait...Try to login with your credentials.'
https_redirected_url, https_login_data = self.spider.login(
https_url, https_loginCredentials)
if https_redirected_url is not None and https_redirected_url.strip(
) == https_wp_url.strip():
return True
except Exception, x:
print x
print 'There was an error when login with https'
class YtDownloadManager(object):
def __init__(self):
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
def scrapVideoDownloadUrl(self, url):
data = self.spider.fetchData(url)
print data
soup = BeautifulSoup(data)
exit(1)
if data and len(data) > 0:
title = self.scrapTitle(url)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
dlUrlChunk = self.regex.getSearchedData('(?i)"url_encoded_fmt_stream_map": "([^"]*)"', data)
dlUrlChunk = self.regex.replaceData('(?i)\\\\u0026', ' ', dlUrlChunk)
dlUrlParts = dlUrlChunk.split(',')
sig = ''
video = ''
videoUrl = ''
print dlUrlParts
for dlUrlPart in dlUrlParts:
dlUrlPart = urllib2.unquote(dlUrlPart)
print dlUrlPart
# if self.regex.isFoundPattern('(?i)itag=5', dlUrlPart):
urlPart = dlUrlPart.split(' ')
for part in urlPart:
print part
if self.regex.isFoundPattern('(?i)sig=.*?', part):
sig = self.regex.getSearchedData('(?i)sig=(.*?)$', part)
if self.regex.isFoundPattern('(?i)url=.*?', part):
video = self.regex.getSearchedData('(?i)url=(.*?)$', part)
print video
videoUrl = video + '&signature=' + sig
self.downloadDir = './test.flv'
# print 'Video URL= ' + videoUrl
# print self.downloadDir
# dlPath = './test.flv'
# print dlPath
print '\n\n'
# if self.downloadFile(videoUrl, dlPath) is True:
# break
def scrapTitle(self, url):
# https://www.youtube.com/oembed?url=http://www.youtube.com/watch?v=9bZkp7q19f0&format=xml
xmlUrl = 'https://www.youtube.com/oembed?url=' + str(url) + '&format=xml'
data = self.spider.fetchData(xmlUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
return self.regex.getSearchedData('(?i)<title>([^<]*)</title>', data)
def downloadFile(self, url, downloadPath, retry=0):
try:
opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0))
opener.addheaders = [
('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1'),
('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'),
('Connection', 'keep-alive')]
# resp = opener.open(url, timeout=10)
resp = urllib2.urlopen(url, timeout=30)
print resp.info()
contentLength = resp.info()['Content-Length']
contentLength = self.regex.getSearchedData('(?i)^(\d+)', contentLength)
totalSize = float(contentLength)
directory = os.path.dirname(downloadPath)
if not os.path.exists(directory):
os.makedirs(directory)
dl_file = open(downloadPath, 'wb')
currentSize = 0
CHUNK_SIZE = 32768
while True:
data = resp.read(CHUNK_SIZE)
if not data:
break
currentSize += len(data)
dl_file.write(data)
print('============> ' + \
str(round(float(currentSize * 100) / totalSize, 2)) + \
'% of ' + str(totalSize) + ' bytes')
notifyDl = '===> Downloaded ' + str(round(float(currentSize * 100) / totalSize, 2)) + '% of ' + str(
totalSize) + ' KB.'
if currentSize >= totalSize:
dl_file.close()
return True
except Exception, x:
error = 'Error downloading: ' + x
return False
class YoutubeScrapper(object):
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
def scrapVideoDownloadUrl(self, url, filename=None):
data = self.spider.fetchData(url)
if data and len(data) > 0:
title = self.scrapTitle(url)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
dlUrlChunk = self.regex.getSearchedData('(?i)"url_encoded_fmt_stream_map": "([^"]*)"', data)
dlUrlChunk = self.regex.replaceData('(?i)\\\\u0026', ' ', dlUrlChunk)
dlUrlParts = dlUrlChunk.split(',')
sig = ''
video = ''
videoUrl = ''
print dlUrlParts
for dlUrlPart in dlUrlParts:
dlUrlPart = urllib2.unquote(dlUrlPart)
print dlUrlPart
## TODO
if self.regex.isFoundPattern('(?i)itag=22', dlUrlPart) or self.regex.isFoundPattern('(?i)itag=18',
dlUrlPart):
urlPart = dlUrlPart.split(' ')
for part in urlPart:
print part
if self.regex.isFoundPattern('(?i)sig=.*?', part):
sig = self.regex.getSearchedData('(?i)sig=(.*?)$', part)
if self.regex.isFoundPattern('(?i)url=.*?', part):
video = self.regex.getSearchedData('(?i)url=(.*?)$', part)
print video
videoUrl = video + '&signature=' + sig
self.downloadDir = './natok.mp4'
print 'Video URL= ' + videoUrl
print self.downloadDir
break
# dlPath = './natok.mp4' if filename is None else filename
fname = self.regex.replaceData('\s+', '_', title)
dlPath = './' + fname + '.mp4' if filename is None else filename
print dlPath
print '\n\n'
if self.downloadFile(videoUrl, dlPath) is True:
print 'Download complete'
else:
print 'No data found.'
def scrapTitle(self, url):
# https://www.youtube.com/oembed?url=http://www.youtube.com/watch?v=9bZkp7q19f0&format=xml
xmlUrl = 'https://www.youtube.com/oembed?url=' + str(url) + '&format=xml'
data = self.spider.fetchData(xmlUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
print data
return self.regex.getSearchedData('(?i)<title>([^<]*)</title>', data)
def downloadFile(self, url, downloadPath, retry=0):
try:
opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0))
opener.addheaders = [
('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1'),
('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'),
('Connection', 'keep-alive')]
# resp = opener.open(url, timeout=10)
resp = urllib2.urlopen(url, timeout=60)
print 'ok'
print resp.info()
contentLength = resp.info()['Content-Length']
contentLength = self.regex.getSearchedData('(?i)^(\d+)', contentLength)
totalSize = float(contentLength)
directory = os.path.dirname(downloadPath)
if not os.path.exists(directory):
os.makedirs(directory)
currentSize = 0
dl_file = open(downloadPath, 'ab')
try:
if os.path.getsize(downloadPath):
start = os.path.getsize(downloadPath)
currentSize = start
opener.addheaders.append(('Range', 'bytes=%s-' % (start)))
except Exception, x:
print x
res = opener.open(url, timeout=60)
CHUNK_SIZE = 256 * 1024
while True:
data = res.read(CHUNK_SIZE)
# data = resp.read(CHUNK_SIZE)
if not data:
break
currentSize += len(data)
dl_file.write(data)
print('============> ' + \
str(round(float(currentSize * 100) / totalSize, 2)) + \
'% of ' + str(totalSize / (1024 * 1024)) + ' Mega Bytes')
notifyDl = '===> Downloaded ' + str(round(float(currentSize * 100) / totalSize, 2)) + '% of ' + str(
totalSize) + ' KB.'
if currentSize >= totalSize:
dl_file.close()
return True
except Exception, x:
error = 'Error downloading: '
print x
if retry < 20:
time.sleep(30)
return self.downloadFile(url, downloadPath, retry + 1)
class MyLinkedIn(QThread):
notifyLinkedIn = pyqtSignal(object)
notifyMember = pyqtSignal(object)
cookieL = pyqtSignal(object)
def __init__(self, username, password):
QThread.__init__(self)
self.spider = Spider()
self.regex = Regex()
self.username = username
self.password = password
def run(self):
if self.login():
self.getAllGroups()
def login(self):
print "login start"
self.notifyLinkedIn.emit("<b>Trying to login. Please wait...</b>")
loginPageData = self.spider.fetchData("https://www.linkedin.com/uas/login?goback=&trk=hb_signin")
loginPageData = self.regex.reduceNewLine(loginPageData)
loginPageData = self.regex.reduceBlankSpace(loginPageData)
## <input type="hidden" name="session_redirect" value="" id="session_redirect-login"><input type="hidden" name="csrfToken" value="ajax:9073845200579364133" id="csrfToken-login"><input type="hidden" name="sourceAlias" value="0_7r5yezRXCiA_H0CRD8sf6DhOjTKUNps5xGTqeX8EEoi" id="sourceAlias-login">
self.sessionRedirect = self.regex.getSearchedData(
'(?i)<input type="hidden" name="session_redirect" value="([^"]*)"', loginPageData
)
self.token = self.regex.getSearchedData(
'(?i)<input type="hidden" name="csrfToken" value="([^"]*)"', loginPageData
)
self.alias = self.regex.getSearchedData(
'(?i)<input type="hidden" name="sourceAlias" value="([^"]*)"', loginPageData
)
loginParam = {
"csrfToken": self.token,
"isJsEnabled": "true",
"session_key": self.username,
"session_password": self.password,
# 'session_key': '*****@*****.**',
# 'session_password': '******',
"session_redirect": self.sessionRedirect,
"signin": "Sign In",
"sourceAlias": self.alias,
"source_app": "",
}
print loginParam
print "start login"
time.sleep(5)
loginData = self.spider.login("https://www.linkedin.com/uas/login-submit", loginParam)
loginData = self.regex.reduceNewLine(loginData)
loginData = self.regex.reduceBlankSpace(loginData)
# print loginData
isLoggedIn = self.regex.isFoundPattern('(?i)<li class="signout">', loginData)
if isLoggedIn:
self.notifyLinkedIn.emit("<font color=green><b>Successfully Logged In.</b></font>")
print "login success"
self.cookieL.emit(self.spider)
return True
else:
self.notifyLinkedIn.emit(
"<font color=red><b>Something wrong with logging in. Please try again or check manually with this username/password</b></font>"
)
return False
def getAllGroups(self):
print "start groups"
self.notifyLinkedIn.emit("<font color=green><b>Start Scraping All Groups.</b></font>")
self.notifyLinkedIn.emit("<b>Wait for 15 second break...</b>")
time.sleep(15)
self.notifyLinkedIn.emit("<b>15 second break finish!!!</b>")
self.notifyLinkedIn.emit("<font color=green><b>Fetching data for scraping your groups.</b></font>")
groupsUrl = "http://www.linkedin.com/myGroups?trk=hb_side_grps_top"
groupsData = self.spider.fetchData(groupsUrl)
self.notifyLinkedIn.emit("<font color=green><b>Data fetching complete for scraping your groups.</b></font>")
if groupsData is not None and len(groupsData) > 0:
print "starting groups"
groupsData = self.regex.reduceNewLine(groupsData)
groupsData = self.regex.reduceBlankSpace(groupsData)
print groupsData
## <a href="/groups?gid=72881&trk=myg_ugrp_ovr" class="private" title="This group is members only">MySQL Professionals</a>
groupInfo = self.regex.getAllSearchedData('(?i)<a href="(/groups\?gid=[^"]*)"[^>]*>([^<]*)</a>', groupsData)
if groupInfo is not None and len(groupInfo) > 0:
members = []
for group in groupInfo:
groupUrl = "http://www.linkedin.com" + str(group[0])
groupName = str(group[1])
self.notifyLinkedIn.emit("<b>Group Name: </b>%s <b>URL: </b>%s" % (groupName, groupUrl))
# http://www.linkedin.com/groups?members=&gid=65688&trk=anet_ug_memb
gid = self.regex.getSearchedData("(?i)gid=(\d+)", group[0])
print gid
groupUrl = "http://www.linkedin.com/groups?members=&gid=" + gid + "&trk=anet_ug_memb"
members.append((groupName, groupUrl))
self.notifyMember.emit(members)
self.notifyLinkedIn.emit("<font color=red><b>Finish Scraping All Groups.</b></font>")
class Nisbets:
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.csvWriter = Csv('nisbets.csv')
self.mainUrl = 'http://www.nisbets.co.uk'
csvHeaderList = ['Category', 'Product Image Url', 'Product Code', 'Product Name', 'Price']
self.csvWriter.writeCsvRow(csvHeaderList)
def scrapData(self):
self.logger.debug('===== URL [' + self.mainUrl + '] =====')
data = self.spider.fetchData(self.mainUrl)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
data = self.regex.getSearchedData('(?i)<div class="cms-left-nav-category">(.*?)</ul>', data)
if data:
links = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"', data)
if links:
for link in links:
self.scrapLinkData(self.mainUrl + link)
def scrapLinkData(self, link):
self.logger.debug('== Link URL [' + link + '] ==')
data = self.spider.fetchData(link)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
data = self.regex.getSearchedData('(?i)<h3>Brand</h3> <ul class="subCat02 clear-fix">(.*?)</ul>', data)
if data:
links = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"', data)
if links:
for link in links:
self.scrapInfo(self.mainUrl + link)
def scrapInfo(self, link):
self.logger.debug('= Info URL [' + link + '] =')
data = self.spider.fetchData(link)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category = self.regex.getSearchedData('(?i)<li><h3>Category</h3></li> <li class="remCont"> <span class="block">([^<]*)</span>', data)
allInfo = self.regex.getAllSearchedData('(?i)<div class="product-list-row clear-after">(.*?)</fieldset>', data)
if allInfo:
for info in allInfo:
csvData = []
csvData.append(category)
grpData = self.regex.getSearchedDataGroups('(?i)<img class="primaryImage" src="([^"]*)" alt="([^"]*)" />', info)
if grpData.group(1):
imageUrl = grpData.group(1)
imageUrl = self.regex.replaceData('(?i)medium', 'xlarge', imageUrl)
csvData.append(self.mainUrl + imageUrl)
else:
csvData.append('')
csvData.append(grpData.group(2))
name = self.regex.getSearchedData('(?i)<h3 class="product-name"> <a href="[^"]*">([^<]*)</a>', info)
csvData.append(name)
price = self.regex.getSearchedData(u'(?i)<div class="reduced-price"> <span class="bold">([^<]*)</span>', info)
csvData.append(price.strip()[1:])
self.logger.debug('Scraped Data ' + str(csvData))
self.csvWriter.writeCsvRow(csvData)
class WebTable():
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.browser = BrowserUtil()
self.regex = Regex()
self.utils = Utils()
self.csvHeader = [
'Category', 'Sub Category 1', 'Sub Category 2', 'Product Code',
'Product Name', 'Product ShortName', 'Product Description',
'List Price', 'Vendor Price', 'Availability', 'Power', 'Size',
'KW', 'Weight(kg)', 'Other Tech', 'Pdf File', 'Image File'
]
self.totalProducts = 0
def scrapData(self):
postParams = {
'__ASYNCPOST': 'true',
'__EVENTVALIDATION':
'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',
'__VIEWSTATE':
'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',
'btn': 'Search',
'ddlcategory': 'MIN',
'ddlstate': 'Gujarat',
'ddlstatus': 'UPEC',
'ddlyear': '2011',
'textbox2': '',
'ww': 'UpdatePanel3'
}
data = self.spider.fetchData(
'http://environmentclearance.nic.in/Search.aspx', postParams)
print data
data = self.spider.fetchData1(
'http://environmentclearance.nic.in/Search.aspx')
print data
# soup = BeautifulSoup(data)
def scrapSubCat1(self, url):
print 'url: ', url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
for cat in soup.find_all('td', {"class": re.compile("item_level")}):
c = cat.find(
"a", {
"href":
re.compile('rayons\.aspx\?value_path=.*?$'),
"id":
re.compile('ctl00_cph_center_dl_level_ctl\d+_a_level.*?$')
})
if c:
print c.string.strip()
self.scrapSubCat2('http://www.diamond-europe.com/' +
c.get("href"))
def scrapSubCat2(self, url):
print 'url1: ' + url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
for cat in soup.find_all('div', {'class': re.compile('bg_ombre')}):
self.scrapProducts('http://www.diamond-europe.com/' +
cat.find('a').get('href'))
def scrapProducts(self, url):
print 'url2', url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
results = soup.find('table', {'id': 'results'})
if results:
for row in results.find_all('tr'):
colRef = row.find('td', {'class': 'reference'})
if colRef:
prCode = colRef.find('span', {'class': 'imp'})
price1 = colRef.find(
'span', {
'id':
re.compile(
'ctl\d+_cph_center_r_articles_ctl\d+_l_prix_barre$'
)
})
price2 = colRef.find('span', {'class', 'promo'})
print prCode.string.strip()
print price1.string.strip()
print price2.string.strip()
coldesc = row.find('td',
{'class': re.compile('description.*?$')})
if coldesc:
pr = coldesc.find('a')
print pr.string.strip()
self.scrapProductDetails('http://www.diamond-europe.com/' +
pr.get('href'))
def scrapProductDetails(self, url):
print 'Detail url: ' + url
data = self.spider.fetchData(url)
soup = BeautifulSoup(data)
productDescS = soup.find('span', 'h1_nom_article')
print productDescS.string.strip()
productDesc = soup.find('div', {'id': 'article_right'})
print productDesc.text.strip()
specs = soup.find('ul', {'id': 'spec_tech'})
if specs:
print specs.contents
"""
__ASYNCPOST true
__EVENTARGUMENT
__EVENTTARGET ctl00$cph_center$menu_left1$lb_login
__EVENTVALIDATION /wEWEwKOk7qrBAKG4eyLBALGw+PfBwK7jI7eDQL/2fqXBwLH9rmjDwLG2KLDCAKCvreACALPgYP1DQKqvLeACAKKtP7+DAL07MD3CwLksZZaAuSxmloCicn43Q8Cisn43Q8C/Iag2AMClcHvlQgCyNGw1Ax/PwzywfL/ooD/FU51memYxQ1U+Q==
__LASTFOCUS
__SCROLLPOSITIONX 0
__SCROLLPOSITIONY 0
__VIEWSTATE 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
ctl00$ToolkitScriptManage... ctl00$cph_center$menu_left1$up_login|ctl00$cph_center$menu_left1$lb_login
ctl00$cph_center$hf_value...
ctl00$cph_center$menu_lef...
ctl00$cph_center$menu_lef... C913327
ctl00$cph_center$menu_lef... sdfsdfsdf
ctl00$cph_center$n_vei$cp...
ctl00$cph_center$n_vei$hf...
ctl00$ddl_search_type Reference
ctl00$tb_search
ctl00_ToolkitScriptManage... ;;AjaxControlToolkit, Version=3.5.40412.0, Culture=neutral, PublicKeyToken=28f01b0e84b6d53e:en-GB:1547e793-5b7e-48fe-8490-03a375b13a33:de1feab2:f2c8e708:720a52bf:f9cec9bc:589eaa30:698129cf:7a92f56c:4a2c8239;
hiddenInputToUpdateATBuff... 1
"""
def loginDiamondEurope(self):
params = {
'__ASYNCPOST': 'true',
'__EVENTARGUMENT': '',
'__EVENTTARGET': 'ctl00$cph_center$menu_left1$lb_login',
'__EVENTVALIDATION':
'/wEWEwKOk7qrBAKG4eyLBALGw+PfBwK7jI7eDQL/2fqXBwLH9rmjDwLG2KLDCAKCvreACALPgYP1DQKqvLeACAKKtP7+DAL07MD3CwLksZZaAuSxmloCicn43Q8Cisn43Q8C/Iag2AMClcHvlQgCyNGw1Ax/PwzywfL/ooD/FU51memYxQ1U+Q==',
'__LASTFOCUS': '',
'__SCROLLPOSITIONX': '0',
'__SCROLLPOSITIONY': '0',
'__VIEWSTATE':
'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',
'ctl00$ToolkitScriptManager1':
'ctl00$cph_center$menu_left1$up_login|ctl00$cph_center$menu_left1$lb_login',
'ctl00$cph_center$menu_left1$tb_login': '******',
'ctl00$cph_center$menu_left1$tb_password': '******',
'ctl00$ddl_search_type': 'Reference',
'ctl00_ToolkitScriptManager1HiddenField':
';;AjaxControlToolkit, Version=3.5.40412.0, Culture=neutral, PublicKeyToken=28f01b0e84b6d53e:en-GB:1547e793-5b7e-48fe-8490-03a375b13a33:de1feab2:f2c8e708:720a52bf:f9cec9bc:589eaa30:698129cf:7a92f56c:4a2c8239;',
'hiddenInputToUpdateATBuffer_CommonToolkitScripts': '1'
}
if self.spider.login('http://www.diamond-europe.com/rayons.aspx',
params) is not None:
return True
return False
def scrapBertos(self, retry=0):
# self.downloadFile('http://s900.bertos.it/download.php?file=editorcms/documentazione/schede/scheda_13722600.pdf', 'a.pdf')
# self.scrapSubCategory('http://s900.bertos.it/en/', '', None, None)
# self.scrapProducts('http://s900.bertos.it/en/pasta_cookers/', '', '', None, None)
# return
self.notifyProduct.emit(
'<font color=green><b>Try to get all language links.</b></font>')
self.logger.debug(self.mainUrl)
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
languages = self.regex.getAllSearchedData(
'(?i)<div class="[^"]*"><a href="([^"]*)"\s*?class="boxalingua">([^<]*)</a>',
data)
if languages and len(languages) > 0:
self.logger.debug('Total languages: %s' % str(len(languages)))
self.notifyProduct.emit('<b>Total languages found[%s]</b>' %
str(len(languages)))
for language in languages:
self.totalProducts = 0
url = language[0]
# if str(language[1]).lower() != 'en':
# continue
urlChunk = self.spider.fetchData(url)
if urlChunk and len(urlChunk) > 0:
urlChunk = self.regex.reduceNewLine(urlChunk)
urlChunk = self.regex.reduceBlankSpace(urlChunk)
url = self.regex.getSearchedData(
'(?i)<a href="([^"]*)" onmouseover="vedi_po_cat\(2\)\s*?"',
urlChunk)
csvFile = str(
language[1].strip()).lower() + '_' + 'bertos.csv'
dupCsvReader = Csv()
dupCsvRows = dupCsvReader.readCsvRow(csvFile)
csvWriter = Csv(csvFile)
if self.csvHeader not in dupCsvRows:
dupCsvRows.append(self.csvHeader)
csvWriter.writeCsvRow(self.csvHeader)
self.notifyProduct.emit(
'<font color=green><b>Try to get data for language [%s].</b></font>'
% language[1])
self.scrapCategory(url, dupCsvRows, csvWriter)
self.notifyProduct.emit(
'<font color=red><b>===== Finish scraping data for [%s] =====</b></font><br /><br />'
% language[1])
else:
if retry < 5:
return self.scrapBertos(retry + 1)
def scrapCategory(self, mainUrl, dupCsvRows, csvWriter):
url = mainUrl
self.logger.debug('Main URL: ' + url)
self.notifyProduct.emit(
'<font color=green><b>Main URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
data = self.regex.reduceNbsp(data)
self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
categoryChunk = self.regex.getSearchedData(
'(?i)<div id="contenuto1">(.*?)</div>\s*?</div>', data)
if categoryChunk and len(categoryChunk) > 0:
categories = self.regex.getAllSearchedData(
'(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', categoryChunk)
if categories and len(categories) > 0:
self.notifyProduct.emit(
'<b>Total Categories Found: %s</b>' %
str(len(categories)))
for category in categories:
categoryName = category[1].strip()
self.scrapSubCategory(
str(category[0]).strip(), categoryName, dupCsvRows,
csvWriter)
def scrapSubCategory(self, url, categoryName, dupCsvRows, csvWriter):
self.logger.debug('Category URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap subcategories for: %s</b>' %
categoryName)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
subCategories = self.regex.getAllSearchedData(
'(?i)<li\s*?><a href="([^"]*)" title="([^"]*)"', data)
if subCategories and len(subCategories) > 0:
self.notifyProduct.emit(
'<font color=green><b>Total subcategories found %s.</b></font>'
% str(len(subCategories)))
for subCategory in subCategories:
subCategoryName = subCategory[1].strip()
self.scrapProducts(subCategory[0].strip(), categoryName,
subCategoryName, dupCsvRows, csvWriter)
def downloadFile(self, url, downloadPath, retry=0):
print url
self.notifyProduct.emit('<b>File URL: %s.</b>' % url)
try:
socket.setdefaulttimeout(10)
opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0))
opener.addheaders = [(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1'
)]
urllib2.install_opener(opener)
# resp = opener.open(url, timeout=30)
# resp = urllib2.urlopen(url, timeout=30)
resp = None
try:
# resp = urllib.urlopen(url)
resp = opener.open(url, timeout=30)
except Exception, x:
print x
if resp is None: return False
# if resp.info()['Connection'] == 'close' or resp.getcode() != 200:
# if retry < 3:
# self.notifyProduct.emit('<font color=red><b>Failed to download file. Retrying...</b></font>')
# return self.downloadFile(url, downloadPath, retry + 1)
# else:
# self.notifyProduct.emit('<font color=red><b>Failed to download file after 3 retry.</b></font>')
# return
print resp.info()
print 'info.......'
contentLength = resp.info()['Content-Length']
contentLength = self.regex.getSearchedData('(?i)^(\d+)',
contentLength)
totalSize = float(contentLength)
directory = os.path.dirname(downloadPath)
if not os.path.exists(directory):
try:
os.makedirs(directory)
except Exception, x:
print x
dl_file = open(downloadPath, 'wb')
currentSize = 0
CHUNK_SIZE = 32768
totalSizeKB = totalSize / 1024 if totalSize > 0 else totalSize
print 'everything ok............'
while True:
data = None
try:
data = resp.read(CHUNK_SIZE)
except Exception, x:
print x
if not data:
break
currentSize += len(data)
dl_file.write(data)
print('============> ' + \
str(round(float(currentSize * 100) / totalSize, 2)) + \
'% of ' + str(totalSize) + ' bytes')
notifyDl = '===> Downloaded ' + str(
round(float(currentSize * 100) / totalSize,
2)) + '% of ' + str(totalSizeKB) + ' KB.'
self.notifyProduct.emit('<b>%s</b>' % notifyDl)
if currentSize >= totalSize:
dl_file.close()
return True
class CsProduct(QThread):
notifyProduct = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('cs_product.csv', 0)
self.csvWriter = Csv('cs_product.csv')
self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
self.utils = Utils()
self.csvWriter.writeCsvRow(
['URL', 'Product Code', 'Product Name', 'Manufacturer', 'List Price', 'Product Price', 'Discount',
'Product Short Description', 'Product Long Description', 'Product Technical Specifications', 'Warranty',
'Delivery',
'Product Image',
'Category 1', 'Category 2', 'Category 3', 'Category 4', 'Brand Image'])
self.totalProducts = 0
def run(self):
self.scrapProduct()
self.notifyProduct.emit('<font color=red><b>Finished Scraping All products.</b></font>')
def scrapProduct(self):
self.logger.debug('Main URL: ' + self.mainUrl)
self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % self.mainUrl)
data = self.spider.fetchData(self.mainUrl)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)" class="level-top" title="([^"]*)"', data)
if categories and len(categories) > 0:
self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
for category in categories:
category1Name = unicode(category[1]).strip()
self.scrapCategory1Data(str(category[0]).strip(), category1Name)
def scrapCategory1Data(self, url, category1Name):
self.logger.debug('Category 1 URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category1Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if categories and len(categories) > 0:
self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
for category in categories:
self.scrapCategory2Data(category[0], category1Name, category[1])
def scrapCategory2Data(self, url, category1Name, category2Name):
self.logger.debug('Category 2 URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category2Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if categories and len(categories) > 0:
for category in categories:
print 'category2: ' + category[0]
self.scrapCategory3Data(category[0], category1Name, category2Name, category[1])
def scrapCategory3Data(self, url, category1Name, category2Name, category3Name):
self.logger.debug('Category 3 URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all categories under Category[%s]</b>' % category3Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if categories and len(categories) > 0:
for category in categories:
print [category1Name, category2Name, category3Name, category[1]]
self.scrapProductsDetails(category[0], category1Name, category2Name, category3Name, category[1])
def scrapProductsDetails(self, url, category1Name, category2Name, category3Name, category4Name):
self.logger.debug('Product Details URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap all products under Category[%s]</b>' % category4Name)
self.notifyProduct.emit('<font color=green><b>Category URL: %s</b></font>' % url)
data = self.spider.fetchData(url + '?limit=10000&mode=list')
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
products = self.regex.getAllSearchedData('(?i)<div class="listing-item[^"]*?">(.*?)</div>', data)
if products and len(products) > 0:
self.totalProducts += len(products)
self.notifyProduct.emit('<font color=green><b>Total Products Found [%s]</b></font>' % unicode(self.totalProducts))
for product in products:
productDetailUrl = self.regex.getSearchedData('(?i)<a href="([^"]*)"', product)
if productDetailUrl not in self.dupCsvRows:
self.scrapProductDetails(productDetailUrl, category1Name, category2Name, category3Name,
category4Name)
else:
self.notifyProduct.emit(
'<font color=green><b>Already Exists This Product Under Category[%s]. Skip It.</b></font>' % category4Name)
def scrapProductDetails(self, url, category1Name, category2Name, category3Name, category4Name):
self.logger.debug('Product Detail URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap product details under Category[%s]</b>' % category4Name)
self.notifyProduct.emit('<font color=green><b>Product Detail URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
manufacturer = self.regex.getSearchedData(
'(?i)<span class="manufacturer-box-label">Manufacturer:</span>([^<]*)</p>', data)
productCode = self.regex.getSearchedData(
'(?i)<span class="manufacturer-box-label">Model No:</span>([^<]*)</p>',
data)
productName = self.regex.getSearchedData('(?i)<div class="product-name"> <h1>([^<]*)</h1>', data)
productTechnicalDesc = self.regex.getSearchedData('(?i)<div class="product-short-description">([^<]*)</div>'
, data)
productDescriptions = self.regex.getSearchedData('(?i)<div class="product-specs">(.*?)</div>', data)
productShortDesc = ''
productFullDesc = ''
if productDescriptions and len(productDescriptions) > 0:
print 'desc: ' + productDescriptions
productShortDesc = self.regex.getSearchedData('(?i)<p>(.*?)</p>', productDescriptions)
productFullDesc = '\n'.join(
self.regex.getAllSearchedData('(?i)<li>([^<]*)</li>', productDescriptions))
listPriceChunk = self.regex.getSearchedData('(?i)<div class="rrp-price regular-price">(.*?)</div>', data)
listPrice = ''
if listPriceChunk and len(listPriceChunk) > 0:
listPrice = self.regex.getSearchedData('(?i)([0-9,.]+)', listPriceChunk)
savePriceChunk = self.regex.getSearchedData('(?i)<div class="regular-price saving-price">(.*?)</div>', data)
savePrice = ''
if savePriceChunk and len(savePriceChunk) > 0:
savePrice = self.regex.getSearchedData('(?i)([0-9%]+)', savePriceChunk)
priceChunk = self.regex.getSearchedData('(?i)<div class="[^"]*" id="product-price-\d+">(.*?)</div>', data)
price = ''
if priceChunk and len(priceChunk) > 0:
price = self.regex.getSearchedData('(?i)([0-9,.]+)', priceChunk)
deliveryChunk = self.regex.getSearchedData('(?i)<div class="delivery">(.*?)</div>', data)
delivery = ''
if deliveryChunk and len(deliveryChunk) > 0:
delivery = self.regex.getSearchedData('(?i)<p>([^<]*)</p>', deliveryChunk)
warrantyChunk = self.regex.getSearchedData('(?i)<div class="warranty">(.*?)</div>', data)
warranty = ''
if warrantyChunk and len(warrantyChunk) > 0:
warranty = self.regex.getSearchedData('(?i)<p>([^<]*)</p>', warrantyChunk)
## Download and save product images
productImageUrl = self.regex.getSearchedData(
'(?i)src="(http://assets.cs-catering-equipment.co.uk/media/catalog/product/cache/1/image/256x/[^"]*)"',
data)
print productImageUrl
productImage = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_.]*)$', productImageUrl)
if productImage and len(productImage) > 0:
print productImage
self.notifyProduct.emit('<b>Downloading Product Image [%s]. Please wait...</b>' % productImage)
self.utils.downloadFile(productImageUrl, 'product_image/' + productImage)
## Download and save brand images
brandImageUrl = self.regex.getSearchedData(
'(?i)<div class="manufacturer-box-left"><a href="[^"]*"[^>]*?><img src="([^"]*)"', data)
brandImage = ''
if brandImageUrl and len(brandImageUrl) > 0:
brandImageUrl = self.regex.replaceData('(?i)logo/', '', brandImageUrl)
brandImage = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_.]*)$', brandImageUrl)
if brandImage and len(brandImage) > 0:
self.notifyProduct.emit('<b>Downloading Brand Image [%s]. Please wait...</b>' % brandImage)
self.utils.downloadFile(brandImageUrl, 'brand_image/' + brandImage)
csvData = [url, productCode, productName, manufacturer, listPrice, price, savePrice,
productShortDesc, productFullDesc, productTechnicalDesc, warranty, delivery,
productImage,
category1Name, category2Name, category3Name, category4Name, brandImage]
self.csvWriter.writeCsvRow(csvData)
self.logger.debug(unicode(csvData))
self.notifyProduct.emit('<b>Product Details: %s</b>' % unicode(csvData))
class CsCat(QThread):
notifyCategory = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('cs_cat.csv')
self.csvWriter = Csv('cs_cat.csv')
dupFilterCsvReader = Csv()
self.dupFilterCsvRows = dupFilterCsvReader.readCsvRow('filter_cat' + '.csv')
self.csvW = Csv('filter_cat' + '.csv')
self.mainUrl = 'http://www.cs-catering-equipment.co.uk/'
self.totalCategory = 0
def run(self):
self.scrapCategories()
self.notifyCategory.emit('<font color=red><b>Finished Scraping All Categories.</b></font>')
def scrapCategories(self):
# self.scrapFinalCategory('http://www.cs-catering-equipment.co.uk/kitchen-equipment/food-prep-machines/chocolate-fountains', '', '')
# return
self.notifyCategory.emit('<b>Start scraping Category.</b>')
self.notifyCategory.emit('<font color=green><b>Main URL: %s</b></font>' % self.mainUrl)
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
# <a href="http://www.cs-catering-equipment.co.uk/kitchen-equipment" class="level-top" title="Kitchen Equipment"
categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)" class="level-top" title="([^"]*)"', data)
if categories and len(categories) > 0:
self.totalCategory += len(categories)
self.notifyCategory.emit(
'<font color=green><b>Total Category Found [%s]</b></font>' % unicode(self.totalCategory))
for category in categories:
homeCategoryName = 'Home'
categoryName = unicode(category[1]).strip()
self.scrapCategory(str(category[0]).strip(), homeCategoryName, categoryName)
def scrapCategory(self, url, rootCategoryName, categoryName):
self.notifyCategory.emit('<font color=green><b>Start scraping URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
print 'category 1'
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
self.filterCategory(data, categoryName)
categoryDesc = self.regex.getSearchedData('(?i)<div class="category-description std">([^<]*)</div>', data)
if categoryDesc and len(categoryDesc) > 0:
categoryDesc = unicode(categoryDesc).strip()
csvData = [rootCategoryName, categoryName, categoryDesc]
if csvData not in self.dupCsvRows:
self.notifyCategory.emit('<b>Scraped Data: %s</b>' % unicode(csvData))
self.csvWriter.writeCsvRow(csvData)
self.dupCsvRows.append(csvData)
else:
self.notifyCategory.emit('<font color=green><b>Already Exits Category [%s] in csv file. Skip it.</b></font>' % categoryName)
subCategories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if subCategories and len(subCategories) > 0:
self.totalCategory += len(subCategories)
self.notifyCategory.emit(
'<font color=green><b>Total Category Found [%s]</b></font>' % unicode(self.totalCategory))
for subCategory in subCategories:
print subCategory
self.scrapSubCategory(subCategory[0], categoryName, subCategory[1])
def scrapSubCategory(self, url, rootCategoryName, categoryName):
self.notifyCategory.emit('<font color=green><b>Start scraping URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
self.filterCategory(data, categoryName)
categoryDesc = self.regex.getSearchedData('(?i)<div class="category-description std">([^<]*)</div>', data)
categoryDesc = unicode(categoryDesc).strip()
csvData = [rootCategoryName, categoryName, categoryDesc]
if csvData not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvData)
self.dupCsvRows.append(csvData)
self.notifyCategory.emit('<b>Scraped Data: %s</b>' % unicode(csvData))
else:
self.notifyCategory.emit('<font color=green><b>Already Exits Category [%s] in csv file. Skip it.</b></font>' % categoryName)
subCategories = self.regex.getAllSearchedData(
'(?i)<li> <a href="([^"]*)" title="([^"]*)"[^>]*?>[^<]*?</a> </li>', data)
if subCategories and len(subCategories) > 0:
self.totalCategory += len(subCategories)
self.notifyCategory.emit(
'<font color=green><b>Total Category Found [%s]</b></font>' % unicode(self.totalCategory))
for subCategory in subCategories:
self.scrapFinalCategory(subCategory[0], categoryName, subCategory[1])
def scrapFinalCategory(self, url, rootCategoryName, categoryName):
self.notifyCategory.emit('<font color=green><b>Start scraping URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
self.filterCategory(data, categoryName)
categoryDesc = self.regex.getSearchedData(u'(?i)<div class="category-description std">([^<]*)</div>', data)
if len(categoryDesc) > 0:
categoryDesc = categoryDesc.strip()
csvData = [rootCategoryName, categoryName, categoryDesc]
if csvData not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvData)
self.dupCsvRows.append(csvData)
self.notifyCategory.emit('<b>Scraped Data: %s</b>' % unicode(csvData))
else:
self.notifyCategory.emit('<font color=green><b>Already Exits Category [%s] in csv file. Skip it.</b></font>' % categoryName)
def filterCategory(self, data, categoryName):
# self.csvW = Csv(category + '.csv')
filterData = self.regex.getSearchedData('(?i)<h4>Filter your results</h4> <dl id="narrow-by-list">(.*?)</dl>',
data)
if filterData and len(filterData) > 0:
self.notifyCategory.emit('<b>Filter Data found writing to csv</b>')
allFilters = self.regex.getAllSearchedData('(?i)<dt>([^<]*)</dt> <dd>(.*?)</dd>', filterData)
topData = [categoryName]
childData = []
maxLen = 0
for allFilter in allFilters:
topData.append(allFilter[0])
print 'Filter: ' + allFilter[0]
filterName = self.regex.replaceData('(?i)<span class="price">', '', allFilter[1])
filterName = self.regex.replaceData('(?i)</span>', '', filterName)
filters = self.regex.getAllSearchedData('(?i)<a href=[^>]*>([^<]*)</a>', filterName)
if filters is not None and len(filters) > 0:
childData.append(filters)
if len(filters) > maxLen:
maxLen = len(filters)
if topData not in self.dupFilterCsvRows:
self.csvW.writeCsvRow(topData)
self.notifyCategory.emit(
'<font color=green><b>Filters Found For Category [%s].</b></font> <br /><b>Filters are: %s</b>' % (
unicode(categoryName), unicode(topData[1:])))
else:
self.notifyCategory.emit('<font color=green><b>Already scraped Filter For Category [%s]. Skip it.</b></font>' % categoryName)
return
for row in range(maxLen):
rowData = ['']
for columnData in childData:
if len(columnData) > row:
rowData.append(columnData[row])
else:
rowData.append('')
print rowData
self.csvW.writeCsvRow(rowData)
else:
self.notifyCategory.emit(
'<font color=green><b>No Filter Found For Category[%s].</b></font>' % categoryName)
class TrggroupScrapper():
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.loginUrl = 'http://www.trggroup.net/victorinox/index.php'
self.username = '******'
self.password = '******'
self.collectionUrl = 'http://www.trggroup.net/victorinox/index.php?p=124'
self.mainUrl = 'http://www.trggroup.net/victorinox/'
self.url = 'http://www.ebags.com/brands'
self.csvWriter = Csv('trggroup.csv')
csvDataHeader = ['Name1', 'Name2', 'Dimension1', 'Dimension2', 'Spec1', 'Spec2', 'Spec3', 'Product Details',
'Image']
self.csvWriter.writeCsvRow(csvDataHeader)
self.proxy = urllib2.ProxyHandler({'http': '184.168.55.226:80'})
def scrapData(self):
if self.onLogin() is True:
print 'Successfully logged in.'
data = self.spider.fetchData(self.collectionUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
soup = BeautifulSoup(data)
allCollections = soup.find('table', class_='sidebar').find_all('td', class_='sidebara')
if allCollections and len(allCollections) > 0:
print 'Total collection found: ' + str(len(allCollections))
for collection in allCollections:
collectionUrl = collection.get('onclick')
collectionUrl = self.regex.getSearchedData('(?i)location.href=\'([^\']*)\'', collectionUrl)
collectionUrl = self.mainUrl + collectionUrl
print collectionUrl
self.scrapCollectionData(collectionUrl)
def onLogin(self):
'''
Credentials are:
action login_access
i
p
password sdfsdf
username sdfsdf
'''
try:
loginCredentials = {'action': 'login_access',
'i': '',
'p': '',
'username': self.username,
'password': self.password}
loginData = self.spider.login(self.loginUrl, loginCredentials, proxy=self.proxy)
if loginData and len(loginData) > 0:
loginData = self.regex.reduceNewLine(loginData)
loginData = self.regex.reduceBlankSpace(loginData)
soup = BeautifulSoup(loginData)
if soup.find('input', {'value': 'Search'}):
return True
except Exception, x:
print 'There was an error when login'
return False
class NisbetProduct(QtCore.QThread):
scrapProductData = QtCore.pyqtSignal(object)
stopThread = QtCore.pyqtSignal(int)
def __init__(self):
QtCore.QThread.__init__(self)
self.isExiting = False
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow("nisbets.csv", 0)
self.csvWriter = Csv("nisbets.csv")
self.mainUrl = "http://www.nisbets.co.uk"
csvHeaderList = [
"URL",
"Product Code",
"Product Technical Specifications",
"Product Name",
"Brand",
"Product Price",
"Product Short Description",
"Product Long Description",
"Image File Name",
"User Manual File Name",
"Exploded View File Name",
"Spares Code",
"Accessories",
"Product Status" "Category1",
"Category2",
"Category3",
"Category4",
]
if "URL" not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvHeaderList)
self.dupCsvRows.append(csvHeaderList[0])
self.utils = Utils()
def run(self):
self.scrapData()
def stop(self):
self.isExiting = True
def scrapData(self):
if self.isExiting:
return
self.scrapProductData.emit("<font color=green><b>Main URL: </b>%s</font>" % self.mainUrl)
self.logger.debug("===== URL [" + self.mainUrl + "] =====")
data = self.spider.fetchData(self.mainUrl)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category1Chunk = self.regex.getAllSearchedData('(?i)<li id="li-id-\d+">(.*?)</ul> </li>', data)
if category1Chunk:
for category1Data in category1Chunk:
category1 = self.regex.getSearchedData('(?i)<a href="[^"]*">([^<]*)</a>', category1Data)
category2Chunk = self.regex.getAllSearchedData(
'(?i)<li><a href="([^"]*)">([^<]*)</a>', category1Data
)
if category2Chunk:
for category2Data in category2Chunk:
self.scrapCategory2Data(self.mainUrl + category2Data[0], category1, category2Data[1])
self.scrapProductData.emit("<font color=red><b>Finish Scraping Product data from %s</b></font>" % self.mainUrl)
def scrapCategory2Data(self, url, category1, category2):
if self.isExiting:
return
self.scrapProductData.emit("<b>Category 2 URL: </b>%s" % url)
self.logger.debug("== Category 2 URL [" + url + "] ==")
data = self.spider.fetchData(url)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category3Chunks = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
if category3Chunks:
category3Chunk = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<', category3Chunks)
if category3Chunk:
for category3Data in category3Chunk:
self.scrapCategory3Data(self.mainUrl + category3Data[0], category1, category2, category3Data[1])
def scrapCategory3Data(self, url, category1, category2, category3):
if self.isExiting:
return
self.scrapProductData.emit("<b>Category 3 URL: </b>%s" % url)
self.logger.debug("== Category 3 URL [" + url + "] ==")
data = self.spider.fetchData(url)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category4Chunks = self.regex.getSearchedData('(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
if category4Chunks:
category4Chunk = self.regex.getAllSearchedData('(?i)<a href="([^"]*)">([^<]*)<', category4Chunks)
if category4Chunk:
for category4Data in category4Chunk:
category4Url = self.mainUrl + category4Data[0]
self.scrapCategory4Data(category4Url, category1, category2, category3, category4Data[1])
def scrapCategory4Data(self, url, category1, category2, category3, category4):
if self.isExiting:
return
self.scrapProductData.emit("<b>Category 4 URL: </b>%s" % url)
self.logger.debug("== Category 4 URL [" + url + "] ==")
data = self.spider.fetchData(url)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categoryChunk = self.regex.getAllSearchedData(
'(?i)<div class="product-list-row clear-after">(.*?)</fieldset>', data
)
if categoryChunk:
for categoryData in categoryChunk:
if self.isExiting:
return
productInfo = self.regex.getSearchedDataGroups(
'(?i)<h3 class="product-name"> <a href="([^"]*)"[^>]*?>([^<]*)</a>', categoryData
)
productUrl = self.mainUrl + productInfo.group(1)
productName = productInfo.group(2)
if productUrl not in self.dupCsvRows:
self.dupCsvRows.append(productUrl)
else:
self.scrapProductData.emit(
"<font color=green><b>Already exists this item in csv Skip it</b></font>"
)
self.logger.debug("========= Already exists this item Skip it ===========")
return
productImageInfo = self.regex.getSearchedDataGroups(
'(?i)<img class="primaryImage" src="([^"]*)" alt="([^"]*)"', categoryData
)
image = self.regex.replaceData("(?i)medium", "xlarge", str(productImageInfo.group(1)))
productImageUrl = self.mainUrl + image
productImage = self.regex.getSearchedData("(?i)/([a-zA-Z0-9-_.]*)$", image)
self.utils.downloadFile(productImageUrl, "images/" + productImage)
productCode = productImageInfo.group(2)
productTechSpecs = self.regex.getSearchedData(
'(?i)<p class="description">([^<]*)</p>', categoryData
)
brandName = self.regex.getSearchedData(
'(?i)<img class="brand-image" src="[^"]*" alt="([^"]*)"', categoryData
)
price = self.regex.getSearchedData(
'(?i)<div class="reduced-price"> <span class="[^"]*">([^<]*)</span>', categoryData
)
if price:
price = price.strip()[1:]
productStatus = self.regex.getSearchedData(
'(?i)<div class="availibility"> <img alt="([^"]*)"', categoryData
)
productDesc = ""
productLongDesc = ""
spareCodes = ""
accessoryCode = ""
userManual = ""
explodedView = ""
self.scrapProductData.emit(
"<br /><font color=green><b>Product Details URL: </b>%s</font>" % productUrl
)
productChunk = self.spider.fetchData(productUrl)
if productChunk:
productChunk = self.regex.reduceNewLine(productChunk)
productChunk = self.regex.reduceBlankSpace(productChunk)
productDesc = self.regex.getSearchedData(
'(?i)<div class="productDesc"> <h1 class="[^"]*"[^>]*?>[^<]*?</h1>.*?<p>([^<]*)</p>',
productChunk,
)
productLongDesc = self.regex.getSearchedData(
'(?i)<div class="info-product[^>]*?>(.*?)</div>', productChunk
)
otherUrl = self.regex.getSearchedData("(?i)(^.*?/)[a-zA-Z0-9._-]*?$", productUrl)
self.logger.debug("== Common Product URL [" + otherUrl + "] ==")
sparesUrl = otherUrl + "AjaxProductSpares.raction"
self.logger.debug("== Spares URL [" + sparesUrl + "] ==")
spares = self.spider.fetchData(sparesUrl)
if spares:
spares = self.regex.getAllSearchedData(
'(?i)<p class="code"><span class="bold">Code:</span>([^<]*)</p>', spares
)
if spares:
spareCodes = ", ".join(spares)
accessoriesUrl = otherUrl + "AjaxProductAccessories.raction"
self.logger.debug("== Accessories URL [" + accessoriesUrl + "] ==")
accessories = self.spider.fetchData(accessoriesUrl)
if accessories:
accessories = self.regex.getAllSearchedData(
'(?i)<p class="code"><span class="bold">Code:</span>([^<]*)</p>', accessories
)
if accessories:
accessoryCode = ", ".join(accessories)
docUrl = otherUrl + "AjaxProductDocuments.raction"
self.logger.debug("== Document URL[" + docUrl + "] ==")
userManuals = self.spider.fetchData(docUrl)
if userManuals:
userManual = self.regex.getSearchedData(
'(?i)<a class="document-icon" href="([^"]*)"[^>]*?>Download User Manual</a>',
userManuals,
)
self.logger.debug("Manual URL: " + userManual)
if userManual:
userManualUrl = self.mainUrl + self.regex.replaceData(" ", "%20", userManual)
self.logger.debug("User Manual URL: " + userManualUrl)
self.scrapProductData.emit("<b>User Manual PDF URL: </b>%s" % userManualUrl)
userManual = self.regex.getSearchedData("(?i)/([a-zA-Z0-9-_. ]*)$", userManual)
userManual = self.regex.replaceData("\s+", "_", userManual.strip())
self.scrapProductData.emit(
"<font color=green><b>Downloading User Manual: </b>%s <b>Please Wait...</b>"
% userManual
)
self.utils.downloadFile(userManualUrl, "user_manual/" + userManual)
explodedView = self.regex.getSearchedData(
'(?i)<a class="document-icon" href="([^"]*)"[^>]*?>Download Exploded Diagram</a>',
userManuals,
)
if explodedView:
explodedViewUrl = self.mainUrl + self.regex.replaceData(" ", "%20", explodedView)
self.scrapProductData.emit("<b>Exploded Diagram PDF URL: </b>%s" % explodedViewUrl)
explodedView = self.regex.getSearchedData("(?i)/([a-zA-Z0-9-_. ]*)$", explodedView)
explodedView = self.regex.replaceData("\s+", "_", explodedView.strip())
self.scrapProductData.emit(
"<font color=green><b>Downloading Exploded Diagram: </b>%s <b>Please Wait...</b>"
% explodedView
)
self.utils.downloadFile(explodedViewUrl, "exploded_view/" + explodedView)
csvData = [
productUrl,
productCode,
productTechSpecs,
productName,
brandName,
price.strip(),
productDesc,
productLongDesc,
productImage,
userManual,
explodedView,
spareCodes,
accessoryCode,
productStatus,
category1,
category2,
category3,
category4,
]
self.csvWriter.writeCsvRow(csvData)
self.logger.debug("Scraped data " + str(csvData))
self.scrapProductData.emit("<div><b>Scraped Data: </b>%s<br /></div>" % str(csvData))
class BetrosProduct(QThread):
notifyProduct = pyqtSignal(object)
def __init__(self):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.mainUrl = 'http://www.bertos.com'
self.utils = Utils()
self.csvHeader = ['Home Category', 'Sub Category', 'Category Description', 'Category Image', 'Code',
'Product Code',
'Product Name',
'Product Description', 'Product Image File', 'Technical Sheet File', 'Exploded View File']
self.totalProducts = 0
def run(self):
self.scrapBertos()
self.notifyProduct.emit('<font color=red><b>Finished Scraping All products.</b></font>')
def scrapBertos(self, retry=0):
# self.downloadFile('http://s900.bertos.it/download.php?file=editorcms/documentazione/schede/scheda_13722600.pdf', 'a.pdf')
# self.scrapSubCategory('http://s900.bertos.it/en/', '', None, None)
# self.scrapProducts('http://s900.bertos.it/en/pasta_cookers/', '', '', None, None)
# return
self.notifyProduct.emit('<font color=green><b>Try to get all language links.</b></font>')
self.logger.debug(self.mainUrl)
data = self.spider.fetchData(self.mainUrl)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
languages = self.regex.getAllSearchedData(
'(?i)<div class="[^"]*"><a href="([^"]*)"\s*?class="boxalingua">([^<]*)</a>', data)
if languages and len(languages) > 0:
self.logger.debug('Total languages: %s' % str(len(languages)))
self.notifyProduct.emit('<b>Total languages found[%s]</b>' % str(len(languages)))
for language in languages:
self.totalProducts = 0
url = language[0]
# if str(language[1]).lower() != 'en':
# continue
urlChunk = self.spider.fetchData(url)
if urlChunk and len(urlChunk) > 0:
urlChunk = self.regex.reduceNewLine(urlChunk)
urlChunk = self.regex.reduceBlankSpace(urlChunk)
url = self.regex.getSearchedData('(?i)<a href="([^"]*)" onmouseover="vedi_po_cat\(2\)\s*?"',
urlChunk)
csvFile = str(language[1].strip()).lower() + '_' + 'bertos.csv'
dupCsvReader = Csv()
dupCsvRows = dupCsvReader.readCsvRow(csvFile)
csvWriter = Csv(csvFile)
if self.csvHeader not in dupCsvRows:
dupCsvRows.append(self.csvHeader)
csvWriter.writeCsvRow(self.csvHeader)
self.notifyProduct.emit(
'<font color=green><b>Try to get data for language [%s].</b></font>' % language[1])
self.scrapCategory(url, dupCsvRows, csvWriter)
self.notifyProduct.emit(
'<font color=red><b>===== Finish scraping data for [%s] =====</b></font><br /><br />' %
language[1])
else:
if retry < 5:
return self.scrapBertos(retry + 1)
def scrapCategory(self, mainUrl, dupCsvRows, csvWriter):
url = mainUrl
self.logger.debug('Main URL: ' + url)
self.notifyProduct.emit('<font color=green><b>Main URL: %s</b></font>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
data = self.regex.reduceNbsp(data)
self.notifyProduct.emit('<b>Try to scrap all categories.</b>')
categoryChunk = self.regex.getSearchedData('(?i)<div id="contenuto1">(.*?)</div>\s*?</div>', data)
if categoryChunk and len(categoryChunk) > 0:
categories = self.regex.getAllSearchedData('(?i)<a href="([^"]*)"[^>]*?>([^<]*)</a>', categoryChunk)
if categories and len(categories) > 0:
self.notifyProduct.emit('<b>Total Categories Found: %s</b>' % str(len(categories)))
for category in categories:
categoryName = category[1].strip()
self.scrapSubCategory(str(category[0]).strip(), categoryName, dupCsvRows, csvWriter)
def scrapSubCategory(self, url, categoryName, dupCsvRows, csvWriter):
self.logger.debug('Category URL: ' + url)
self.notifyProduct.emit('<b>Try to scrap subcategories for: %s</b>' % categoryName)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
subCategories = self.regex.getAllSearchedData('(?i)<li\s*?><a href="([^"]*)" title="([^"]*)"', data)
if subCategories and len(subCategories) > 0:
self.notifyProduct.emit(
'<font color=green><b>Total subcategories found %s.</b></font>' % str(len(subCategories)))
for subCategory in subCategories:
subCategoryName = subCategory[1].strip()
self.scrapProducts(subCategory[0].strip(), categoryName, subCategoryName, dupCsvRows, csvWriter)
def scrapProducts(self, url, categoryName, subCategoryName, dupCsvRows, csvWriter):
self.logger.debug('Product URL: ' + url)
self.notifyProduct.emit('<b>Product URL: %s.</b>' % url)
data = self.spider.fetchData(url)
if data and len(data) > 0:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categoryDescription = self.regex.getSearchedData(
'(?i)<td class="prodottidescrizione1">\s*?<h1>[^<]*?</h1>(.*?)</td>', data)
categoryDescription = self.regex.replaceData('(?i)<!--.*?-->', '', categoryDescription)
categoryDescription = self.regex.replaceData('(?i)<[^>]*>', '', categoryDescription)
productUrl = self.regex.getSearchedData('(?i)^(http://.*?)/', url)
categoryImage = self.regex.getSearchedData(
'(?i)<div class="boximgcat" id="boximgcatid">\s*?<a rel="shadowbox" href="([^"]*)"', data)
categoryImageName = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_. ]*)$', categoryImage)
categoryImageName = self.regex.replaceData('\s+', '_', categoryImageName.strip())
if categoryImageName is not None and len(categoryImageName) > 0 and not os.path.exists(
'category_image/' + categoryImageName):
self.notifyProduct.emit(
'<font color=green><b>Downloading Category Image: </b>%s <b>Please Wait...</b></font>' % categoryImageName)
self.downloadFile(productUrl + categoryImage, 'category_image/' + categoryImageName)
# self.utils.downloadFile(categoryImage, 'category_image/' + categoryImageName)
self.notifyProduct.emit(
'<font color=green><b>Downloaded Category Image: %s.</b></font>' % categoryImageName)
productChunks = self.regex.getSearchedData('(?i)<table.*?class="prodottiriga"[^>]*?>(.*?)</table>', data)
if productChunks and len(productChunks) > 0:
productChunk = self.regex.getAllSearchedData('(?i)<tr>(.*?</div>\s*?</td>)\s*?</tr>', productChunks)
for products in productChunk:
print 'url: ' + url
code = self.regex.getSearchedData('(?i)Cod\. ([a-zA-Z0-9 /]+)', products).strip()
for dup in dupCsvRows:
if code == dup[4]:
return
model = self.regex.getSearchedData('(?i)Mod\. ([^<]*)<', products).strip()
productName = self.regex.getSearchedData('(?i)<h1>([^<]*)</h1>', products).strip()
self.notifyProduct.emit(
'<font color=green><b>Product Name: %s.</b></font>' % productName)
desc = self.regex.getSearchedData(
'(?i)<div id="prtdescrizione\d+" style="display:none">(.*?)<div class="prodotticomando">',
products).strip()
productImage = productUrl + self.regex.getSearchedData('(?i)<img src="/tpl/\.\.([^"]*)"',
products).strip()
productImage = self.regex.replaceData('(?i)k_\d+_\d+', 'k_800_557', productImage)
productImageName = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_. ]*)$', productImage)
productImageName = self.regex.replaceData('\s+', '_', productImageName.strip())
if productImageName is not None and len(productImageName) > 0 and not os.path.exists(
'product_image/' + productImageName):
self.notifyProduct.emit(
'<font color=green><b>Downloading Product Image: </b>%s <b>Please Wait...</b></font>' % productImageName)
self.downloadFile(productImage, 'product_image/' + productImageName)
# self.utils.downloadFile(productImage, 'product_image/' + productImageName)
self.notifyProduct.emit(
'<font color=green><b>Downloaded Product Image: %s.</b></font>' % productImageName)
techPdf = self.regex.getSearchedData(
'(?i)<td class="prodottiriga\d+">\s*?<div class="scarica">\s*?<a href="([^"]*)"'
, products).strip()
techPdfName = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_. ]*)$', techPdf)
techPdfName = self.regex.replaceData('\s+', '_', techPdfName.strip())
if techPdfName is not None and len(techPdfName) > 0 and not os.path.exists(
'tech_pdf/' + techPdfName):
self.notifyProduct.emit(
'<font color=green><b>Downloading Tech Pdf: </b>%s <b>Please Wait...</b></font>' % techPdfName)
self.downloadFile(techPdf, 'tech_pdf/' + techPdfName)
# self.utils.downloadFile(techPdf, 'tech_pdf/' + techPdfName)
self.notifyProduct.emit(
'<font color=green><b>Downloaded Tech Pdf: %s.</b></font>' % techPdfName)
explodedViewPdf = self.regex.getSearchedData(
'(?i)</a>\s*?</div>\s*?<div class="scarica">\s*?<a href="([^"]*\.pdf)">[^<]*?</a>'
, products).strip()
explodedViewPdfName = self.regex.getSearchedData('(?i)/([a-zA-Z0-9-_. ]*)$', explodedViewPdf)
explodedViewPdfName = self.regex.replaceData('\s+', '_', explodedViewPdfName.strip())
if explodedViewPdfName is not None and len(explodedViewPdfName) > 0 and not os.path.exists(
'exploded_pdf/' + explodedViewPdfName):
self.notifyProduct.emit(
'<font color=green><b>Downloading Exploded View Pdf: </b>%s <b>Please Wait...</b></font>' % explodedViewPdfName)
# self.utils.downloadFile(explodedViewPdf, 'exploded_pdf/' + explodedViewPdfName)
self.downloadFile(explodedViewPdf, 'exploded_pdf/' + explodedViewPdfName)
self.notifyProduct.emit(
'<font color=green><b>Downloading Exploded View Pdf: %s.</b></font>' % explodedViewPdfName)
csvData = [categoryName, subCategoryName, categoryDescription, categoryImageName, code, model,
productName, desc, productImageName, techPdfName, explodedViewPdfName]
print csvData
if csvData not in dupCsvRows:
csvWriter.writeCsvRow(csvData)
dupCsvRows.append(csvData)
self.notifyProduct.emit('<font color=green><b>Successfully write data to csv file.</b></font>')
else:
self.notifyProduct.emit('<font color=green><b>Already exists. Skip it.</b></font>')
def downloadFile(self, url, downloadPath, retry=0):
print url
self.notifyProduct.emit('<b>File URL: %s.</b>' % url)
try:
socket.setdefaulttimeout(10)
opener = urllib2.build_opener(urllib2.HTTPRedirectHandler(),
urllib2.HTTPHandler(debuglevel=0),
urllib2.HTTPSHandler(debuglevel=0))
opener.addheaders = [
('User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1')]
urllib2.install_opener(opener)
# resp = opener.open(url, timeout=30)
# resp = urllib2.urlopen(url, timeout=30)
resp = None
try:
# resp = urllib.urlopen(url)
resp = opener.open(url, timeout=30)
except Exception, x:
print x
if resp is None: return False
# if resp.info()['Connection'] == 'close' or resp.getcode() != 200:
# if retry < 3:
# self.notifyProduct.emit('<font color=red><b>Failed to download file. Retrying...</b></font>')
# return self.downloadFile(url, downloadPath, retry + 1)
# else:
# self.notifyProduct.emit('<font color=red><b>Failed to download file after 3 retry.</b></font>')
# return
print resp.info()
print 'info.......'
contentLength = resp.info()['Content-Length']
contentLength = self.regex.getSearchedData('(?i)^(\d+)', contentLength)
totalSize = float(contentLength)
directory = os.path.dirname(downloadPath)
if not os.path.exists(directory):
try:
os.makedirs(directory)
except Exception, x:
print x
dl_file = open(downloadPath, 'wb')
currentSize = 0
CHUNK_SIZE = 32768
totalSizeKB = totalSize / 1024 if totalSize > 0 else totalSize
print 'everything ok............'
while True:
data = None
try:
data = resp.read(CHUNK_SIZE)
except Exception, x:
print x
if not data:
break
currentSize += len(data)
dl_file.write(data)
print('============> ' +\
str(round(float(currentSize * 100) / totalSize, 2)) +\
'% of ' + str(totalSize) + ' bytes')
notifyDl = '===> Downloaded ' + str(round(float(currentSize * 100) / totalSize, 2)) + '% of ' + str(
totalSizeKB) + ' KB.'
self.notifyProduct.emit('<b>%s</b>' % notifyDl)
if currentSize >= totalSize:
dl_file.close()
return True
class MyLinkedInMessage(QThread):
notifyLinkedIn = pyqtSignal(object)
def __init__(self, spider, memberList, subject, message):
QThread.__init__(self)
# self.spider = Spider()
self.spider = spider
self.regex = Regex()
self.memberList = memberList
self.subject = unicode(subject)
self.message = unicode(message)
def run(self):
self.sendMessage()
self.notifyLinkedIn.emit(
'<font color=red><b>Finish Sending All Messages.</b></font>')
def sendMessage(self):
print self.memberList
for member in self.memberList:
messageUrl = 'http://www.linkedin.com/inbox/compose/dialog?insider=true&connId=' + str(
member[1])
print messageUrl
# messageUrl = 'http://www.linkedin.com/inbox/compose/dialog?insider=true&connId=' + '65471931'
# data = self.spider.fetchData('http://www.linkedin.com/inbox/compose/dialog?insider=true&connId=65471931')
data = self.spider.fetchData(messageUrl)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
fromName = self.regex.getSearchedData(
'(?i)<input type="hidden" name="fromName" value="([^"]*)"',
data)
fromEmail = self.regex.getSearchedData(
'(?i)<input type="hidden" name="fromEmail" value="([^"]*)"',
data)
# connectionIds = self.regex.getSearchedData('(?i)<input type="hidden" name="connectionIds" value="([^"]*)"', data)
csrfToken = self.regex.getSearchedData(
'(?i)<input type="hidden" name="csrfToken" value="([^"]*)"',
data)
sourceAlias = self.regex.getSearchedData(
'(?i)<input type="hidden" name="sourceAlias" value="([^"]*)"',
data)
linkedInSubject = u'Hi ' + unicode(
member[0]).split(' ')[0] + self.subject
linkedInMessage = u'Hi ' + unicode(
member[0]).split(' ')[0] + u',\n' + self.message
print linkedInMessage
params = {
'addMoreRcpts': 'false',
'ajaxSubmit': 'Send Message',
'allowEditRcpts': 'true',
'body': linkedInMessage,
'connectionIds': str(member[1]),
'connectionNames': '',
'csrfToken': csrfToken,
'fromEmail': fromEmail,
'fromName': fromName,
'itemID': '',
'openSocialAppBodySuffix': '',
'showRecipeints': 'showRecipeints',
'sourceAlias': sourceAlias,
'st': '',
'subject': linkedInSubject,
'submit': 'Send Message',
'viewerDestinationUrl': ''
}
print params
msgUrl = 'http://www.linkedin.com/msgToConns?displayCreate='
data = self.spider.fetchData(msgUrl, params)
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
if self.regex.isFoundPattern('(?i)<div class="alert success">',
data):
print 'Message Sent.'
self.notifyLinkedIn.emit(
'<font color=green><b>Successfully Sent Message To: %s</b></font>'
% member[0])
else:
self.notifyLinkedIn.emit(
'<font color=red><b>Something Wrong during Send Message To</b></font>'
% member[0])
# params = {'addMoreRcpts': 'false',
# 'ajaxSubmit': 'Send Message',
# 'allowEditRcpts': 'true',
# 'body': 'Script Test',
# 'connectionIds': '65471931',
# 'connectionNames': '',
# 'csrfToken': 'ajax: 6539671039643459056',
# 'fromEmail': '467728216',
# 'fromName': 'Mehedi Hasan',
# 'itemID': '',
# 'openSocialAppBodySuffix': '',
# 'showRecipeints': 'showRecipeints',
# 'sourceAlias': '0_6k2algZhQ6vbvlhlVSByxRKi0OB9NXjxrnJYWBFvfhn',
# 'st': '',
# 'subject': 'Script Test',
# 'submit': 'Send Message',
# 'viewerDestinationUrl': ''}
#<input type="hidden" name="fromName" value="Mehedi Hasan" id="fromName-msgForm">
# <input type="hidden" name="showRecipeints" value="showRecipeints" id="showRecipeints-msgForm">
# <input type="hidden" name="fromEmail" value="467728216" id="fromEmail-msgForm">
# <input type="hidden" name="connectionIds" value="65471931" id="connectionIds-msgForm">
# <input type="hidden" name="connectionNames" value="" id="connectionNames-msgForm">
# <input type="hidden" name="allowEditRcpts" value="true" id="allowEditRcpts-msgForm">
# <input type="hidden" name="addMoreRcpts" value="false" id="addMoreRcpts-msgForm">
# <input type="hidden" name="itemID" value="" id="itemID-msgForm">
# <input type="hidden" name="openSocialAppBodySuffix" value="" id="openSocialAppBodySuffix-msgForm">
# <input type="hidden" name="st" value="" id="st-msgForm">
# <input type="hidden" name="viewerDestinationUrl" value="" id="viewerDestinationUrl-msgForm">
# <input type="hidden" name="csrfToken" value="ajax:6539671039643459056" id="csrfToken-msgForm">
# <input type="hidden" name="sourceAlias" value="0_6k2algZhQ6vbvlhlVSByxRKi0OB9NXjxrnJYWBFvfhn" id="sourceAlias-msgForm">
"""
msgUrl1 = 'http://www.linkedin.com/msgToConns?displayCreate='
msgParams = {}
addMoreRcpts false
ajaxSubmit Send Message
allowEditRcpts true
body fdgdfgdfgdfg dg d
connectionIds 57414219
connectionNames
csrfToken ajax:3480949306085123249
fromEmail 467728216
fromName Mehedi Hasan
goback .con.npv_57414219_*1_*1_name_r5tN_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1_*1
itemID
openSocialAppBodySuffix
showRecipeints showRecipeints
sourceAlias 0_6k2algZhQ6vbvlhlVSByxRKi0OB9NXjxrnJYWBFvfhn
st
subject
viewerDestinationUrl
"""
"""addMoreRcpts false
class NisbetProduct(QtCore.QThread):
scrapProductData = QtCore.pyqtSignal(object)
stopThread = QtCore.pyqtSignal(int)
def __init__(self):
QtCore.QThread.__init__(self)
self.isExiting = False
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow('nisbets.csv', 0)
self.csvWriter = Csv('nisbets.csv')
self.mainUrl = 'http://www.nisbets.co.uk'
csvHeaderList = [
'URL', 'Product Code', 'Product Technical Specifications',
'Product Name', 'Brand', 'Product Price',
'Product Short Description', 'Product Long Description',
'Image File Name', 'User Manual File Name',
'Exploded View File Name', 'Spares Code', 'Accessories',
'Product Status'
'Category1', 'Category2', 'Category3', 'Category4'
]
if 'URL' not in self.dupCsvRows:
self.csvWriter.writeCsvRow(csvHeaderList)
self.dupCsvRows.append(csvHeaderList[0])
self.utils = Utils()
def run(self):
self.scrapData()
def stop(self):
self.isExiting = True
def scrapData(self):
if self.isExiting: return
self.scrapProductData.emit(
'<font color=green><b>Main URL: </b>%s</font>' % self.mainUrl)
self.logger.debug('===== URL [' + self.mainUrl + '] =====')
data = self.spider.fetchData(self.mainUrl)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category1Chunk = self.regex.getAllSearchedData(
'(?i)<li id="li-id-\d+">(.*?)</ul> </li>', data)
if category1Chunk:
for category1Data in category1Chunk:
category1 = self.regex.getSearchedData(
'(?i)<a href="[^"]*">([^<]*)</a>', category1Data)
category2Chunk = self.regex.getAllSearchedData(
'(?i)<li><a href="([^"]*)">([^<]*)</a>', category1Data)
if category2Chunk:
for category2Data in category2Chunk:
self.scrapCategory2Data(
self.mainUrl + category2Data[0], category1,
category2Data[1])
self.scrapProductData.emit(
'<font color=red><b>Finish Scraping Product data from %s</b></font>'
% self.mainUrl)
def scrapCategory2Data(self, url, category1, category2):
if self.isExiting: return
self.scrapProductData.emit('<b>Category 2 URL: </b>%s' % url)
self.logger.debug('== Category 2 URL [' + url + '] ==')
data = self.spider.fetchData(url)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category3Chunks = self.regex.getSearchedData(
'(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
if category3Chunks:
category3Chunk = self.regex.getAllSearchedData(
'(?i)<a href="([^"]*)">([^<]*)<', category3Chunks)
if category3Chunk:
for category3Data in category3Chunk:
self.scrapCategory3Data(
self.mainUrl + category3Data[0], category1,
category2, category3Data[1])
def scrapCategory3Data(self, url, category1, category2, category3):
if self.isExiting: return
self.scrapProductData.emit('<b>Category 3 URL: </b>%s' % url)
self.logger.debug('== Category 3 URL [' + url + '] ==')
data = self.spider.fetchData(url)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
category4Chunks = self.regex.getSearchedData(
'(?i)<ul class="topCat clear-fix">(.*?)</ul>', data)
if category4Chunks:
category4Chunk = self.regex.getAllSearchedData(
'(?i)<a href="([^"]*)">([^<]*)<', category4Chunks)
if category4Chunk:
for category4Data in category4Chunk:
category4Url = self.mainUrl + category4Data[0]
self.scrapCategory4Data(category4Url, category1,
category2, category3,
category4Data[1])
def scrapCategory4Data(self, url, category1, category2, category3,
category4):
if self.isExiting: return
self.scrapProductData.emit('<b>Category 4 URL: </b>%s' % url)
self.logger.debug('== Category 4 URL [' + url + '] ==')
data = self.spider.fetchData(url)
if data:
data = self.regex.reduceNewLine(data)
data = self.regex.reduceBlankSpace(data)
categoryChunk = self.regex.getAllSearchedData(
'(?i)<div class="product-list-row clear-after">(.*?)</fieldset>',
data)
if categoryChunk:
for categoryData in categoryChunk:
if self.isExiting: return
productInfo = self.regex.getSearchedDataGroups(
'(?i)<h3 class="product-name"> <a href="([^"]*)"[^>]*?>([^<]*)</a>',
categoryData)
productUrl = self.mainUrl + productInfo.group(1)
productName = productInfo.group(2)
if productUrl not in self.dupCsvRows:
self.dupCsvRows.append(productUrl)
else:
self.scrapProductData.emit(
'<font color=green><b>Already exists this item in csv Skip it</b></font>'
)
self.logger.debug(
'========= Already exists this item Skip it ==========='
)
return
productImageInfo = self.regex.getSearchedDataGroups(
'(?i)<img class="primaryImage" src="([^"]*)" alt="([^"]*)"',
categoryData)
image = self.regex.replaceData(
'(?i)medium', 'xlarge', str(productImageInfo.group(1)))
productImageUrl = self.mainUrl + image
productImage = self.regex.getSearchedData(
'(?i)/([a-zA-Z0-9-_.]*)$', image)
self.utils.downloadFile(productImageUrl,
'images/' + productImage)
productCode = productImageInfo.group(2)
productTechSpecs = self.regex.getSearchedData(
'(?i)<p class="description">([^<]*)</p>', categoryData)
brandName = self.regex.getSearchedData(
'(?i)<img class="brand-image" src="[^"]*" alt="([^"]*)"',
categoryData)
price = self.regex.getSearchedData(
'(?i)<div class="reduced-price"> <span class="[^"]*">([^<]*)</span>',
categoryData)
if price:
price = price.strip()[1:]
productStatus = self.regex.getSearchedData(
'(?i)<div class="availibility"> <img alt="([^"]*)"',
categoryData)
productDesc = ''
productLongDesc = ''
spareCodes = ''
accessoryCode = ''
userManual = ''
explodedView = ''
self.scrapProductData.emit(
'<br /><font color=green><b>Product Details URL: </b>%s</font>'
% productUrl)
productChunk = self.spider.fetchData(productUrl)
if productChunk:
productChunk = self.regex.reduceNewLine(productChunk)
productChunk = self.regex.reduceBlankSpace(
productChunk)
productDesc = self.regex.getSearchedData(
'(?i)<div class="productDesc"> <h1 class="[^"]*"[^>]*?>[^<]*?</h1>.*?<p>([^<]*)</p>',
productChunk)
productLongDesc = self.regex.getSearchedData(
'(?i)<div class="info-product[^>]*?>(.*?)</div>',
productChunk)
otherUrl = self.regex.getSearchedData(
'(?i)(^.*?/)[a-zA-Z0-9._-]*?$', productUrl)
self.logger.debug('== Common Product URL [' +
otherUrl + '] ==')
sparesUrl = otherUrl + "AjaxProductSpares.raction"
self.logger.debug('== Spares URL [' + sparesUrl +
'] ==')
spares = self.spider.fetchData(sparesUrl)
if spares:
spares = self.regex.getAllSearchedData(
'(?i)<p class="code"><span class="bold">Code:</span>([^<]*)</p>',
spares)
if spares:
spareCodes = ', '.join(spares)
accessoriesUrl = otherUrl + "AjaxProductAccessories.raction"
self.logger.debug('== Accessories URL [' +
accessoriesUrl + '] ==')
accessories = self.spider.fetchData(accessoriesUrl)
if accessories:
accessories = self.regex.getAllSearchedData(
'(?i)<p class="code"><span class="bold">Code:</span>([^<]*)</p>',
accessories)
if accessories:
accessoryCode = ', '.join(accessories)
docUrl = otherUrl + "AjaxProductDocuments.raction"
self.logger.debug('== Document URL[' + docUrl + '] ==')
userManuals = self.spider.fetchData(docUrl)
if userManuals:
userManual = self.regex.getSearchedData(
'(?i)<a class="document-icon" href="([^"]*)"[^>]*?>Download User Manual</a>',
userManuals)
self.logger.debug('Manual URL: ' + userManual)
if userManual:
userManualUrl = self.mainUrl + self.regex.replaceData(
' ', '%20', userManual)
self.logger.debug('User Manual URL: ' +
userManualUrl)
self.scrapProductData.emit(
'<b>User Manual PDF URL: </b>%s' %
userManualUrl)
userManual = self.regex.getSearchedData(
'(?i)/([a-zA-Z0-9-_. ]*)$', userManual)
userManual = self.regex.replaceData(
'\s+', '_', userManual.strip())
self.scrapProductData.emit(
'<font color=green><b>Downloading User Manual: </b>%s <b>Please Wait...</b>'
% userManual)
self.utils.downloadFile(
userManualUrl, 'user_manual/' + userManual)
explodedView = self.regex.getSearchedData(
'(?i)<a class="document-icon" href="([^"]*)"[^>]*?>Download Exploded Diagram</a>',
userManuals)
if explodedView:
explodedViewUrl = self.mainUrl + self.regex.replaceData(
' ', '%20', explodedView)
self.scrapProductData.emit(
'<b>Exploded Diagram PDF URL: </b>%s' %
explodedViewUrl)
explodedView = self.regex.getSearchedData(
'(?i)/([a-zA-Z0-9-_. ]*)$', explodedView)
explodedView = self.regex.replaceData(
'\s+', '_', explodedView.strip())
self.scrapProductData.emit(
'<font color=green><b>Downloading Exploded Diagram: </b>%s <b>Please Wait...</b>'
% explodedView)
self.utils.downloadFile(
explodedViewUrl,
'exploded_view/' + explodedView)
csvData = [
productUrl, productCode, productTechSpecs, productName,
brandName,
price.strip(), productDesc, productLongDesc,
productImage, userManual, explodedView, spareCodes,
accessoryCode, productStatus, category1, category2,
category3, category4
]
self.csvWriter.writeCsvRow(csvData)
self.logger.debug('Scraped data ' + str(csvData))
self.scrapProductData.emit(
'<div><b>Scraped Data: </b>%s<br /></div>' %
str(csvData))