class OmvicScrapper:
isFinished = False
im_data = []
def __init__(self):
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.initScrapper()
def initScrapper(self):
try:
dupCsvReader = Csv()
dupCsvRows = dupCsvReader.readCsvRow('omvic.csv')
self.dbHelper = DbHelper('omvic.db')
self.dbHelper.createTable('omvic')
self.totaldata = self.dbHelper.getTotalProduct('omvic')
self.csvWriter = Csv('omvic.csv')
csvDataHeader = ['URL', 'Legal Name', 'Business Name', 'Status', 'Class of Registration', 'Subclass',
'Operating Status',
'Business Address', 'Email', 'Phone Number', 'Salesperson(s) Names']
if len(dupCsvRows) == 0:
self.csvWriter.writeCsvRow(csvDataHeader)
del dupCsvReader
del dupCsvRows
gc.collect()
del gc.garbage[:]
gc.collect()
except Exception, x:
print x
class AmazonScrapper(QThread):
notifyAmazon = pyqtSignal(object)
def __init__(self, urlList, category):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.urlList = urlList
self.category = category
dupCsvReader = Csv()
self.dupCsvRows = dupCsvReader.readCsvRow(category + '.csv')
self.csvWriter = Csv(category + '.csv')
csvDataHeader = ['SKU', 'Title', 'Sub Title', 'Price', 'Shipping Weight', 'Image URL']
if csvDataHeader not in self.dupCsvRows:
self.dupCsvRows.append(csvDataHeader)
self.csvWriter.writeCsvRow(csvDataHeader)
self.mainUrl = 'http://www.amazon.com'
self.scrapUrl = None
self.dbHelper = DbHelper('amazon.db')
self.dbHelper.createTable(category)
self.total = self.dbHelper.getTotalProduct(category)
def run(self, retry=0):
try:
# self.scrapProductDetail(
# 'http://www.amazon.com/Casio-MRW-S300H-8BVCF-Solar-Powered-Analog/dp/B00ELALKH2/ref=sr_1_544/184-7248556-2619812?s=watches&ie=UTF8&qid=1397580509&sr=1-544')
# return
if self.urlList is not None and len(self.urlList):
for url in self.urlList:
if len(url) > 0:
url = self.regex.replaceData('(?i)\r', '', url)
url = self.regex.replaceData('(?i)\n', '', url)
self.notifyAmazon.emit('<font color=green><b>Amazon Main URL: %s</b></font>' % url)
imUrl = None
retry = 0
while imUrl is None and retry < 4:
imUrl = self.reformatUrl(url)
retry += 1
if imUrl is None:
imUrl = url
self.total = 0
print 'URL: ' + str(imUrl)
sortList = ['relevance-fs-browse-rank', 'price', '-price', 'reviewrank_authority',
'date-desc-rank']
for sort in sortList:
self.scrapReformatData(imUrl, sort)
self.notifyAmazon.emit(
'<font color=red><b>Finish data for Amazon Main URL: %s</b></font><br /><br />' % url)
self.notifyAmazon.emit('<font color=red><b>Amazon Data Scraping finished.</b></font>')
except Exception, x:
print x.message
self.logger.error('Exception at run: ', x.message)
if retry < 5:
self.run(retry + 1)
class SaraivaScrapper(QThread):
notifySaraiva = pyqtSignal(object)
def __init__(self, urlList, category, htmlTag, replaceTag):
QThread.__init__(self)
self.logger = LogManager(__name__)
self.spider = Spider()
self.regex = Regex()
self.utils = Utils()
self.urlList = urlList
self.category = category
self.htmlTag = self.regex.replaceData('\r+', '', htmlTag)
self.htmlTag = self.regex.replaceData('\n+', ' ', self.htmlTag)
self.htmlTag = self.regex.replaceData('\s+', ' ', self.htmlTag)
self.htmlTag = self.regex.replaceData(r'\"+', '\"', self.htmlTag)
self.replaceTag = replaceTag
self.csvWriter = Csv(category + '.csv')
csvDataHeader = ['Link', 'Name', 'Subtitle', 'Price', 'Synopsis and Characteristics', 'Picture']
self.csvWriter.writeCsvRow(csvDataHeader)
self.mainUrl = 'http://busca.livrariasaraiva.com.br'
self.scrapUrl = None
self.dbHelper = DbHelper('saraiva.db')
self.dbHelper.createTable(category)
self.total = self.dbHelper.getTotalProduct(category)
def run(self, retry=0):
try:
if self.urlList is not None and len(self.urlList):
for url in self.urlList:
if len(url) > 0:
url = self.regex.replaceData('(?i)\r', '', url)
url = self.regex.replaceData('(?i)\n', '', url)
self.notifySaraiva.emit('<font color=green><b>Saraiva Main URL: %s</b></font>' % url)
paginationUrl, self.maxRecords = self.reformatUrl(url)
self.notifySaraiva.emit(
'<font color=black><b>Total Records: %s</b></font>' % str(self.maxRecords))
print 'Max records: ', self.maxRecords
print 'URL: ' + str(paginationUrl)
sortList = ['&isort=globalpop', '&isort=best', '&isort=title', '&isort=title+rev',
'&isort=price+rev',
'&isort=price', '&isort=date+rev']
for sort in sortList:
self.scrapResults(paginationUrl, sort)
self.notifySaraiva.emit('<font color=red><b>Saraiva Data Scraping finished.</b></font>')
except Exception, x:
print x.message
self.logger.error('Exception at run: ', x.message)
if retry < 5:
self.run(retry + 1)
