def parser_sub(self,response):
content = response.body # 乱码处理
# for i in range(100):
# try:
# new_content = unicode(content, 'gbk')
# break
# except Exception, e:
# if 'position' in str(e):
# error_str = crawlerTool.getRegex('position\s+(\d+-\d+)', str(e))
# start_index, end_index = int(error_str.split('-')[0]), int(error_str.split('-')[1]) + 1
# content = content[:start_index] + content[end_index:]
response_content = content
print response.url
url= response.url
cfemail = crawlerTool.getXpath('//a[@class="__cf_email__"]/@data-cfemail', content)
title = crawlerTool.getXpath('//title/text()', content)[0]
mail = ''
if cfemail:
mail = self.get_mail(cfemail[0])
data_obj = CmocroItem()
data_obj['url'] = url
data_obj['mail'] = mail
data_obj['name'] = title.replace('- CMOCRO','')
# print lxr,dz,yb,dh,sj
yield data_obj
def parse1(self, response):
base_url = get_base_url(response)
response_content = response.body # 乱码处理 #像https://www.chemicalbook.com/ShowSupplierProductsList6187/51100.htm有9万多
cat_name = response.meta.get('cat_name')
segs = crawlerTool.getXpath('//div[@class="product_list_left_in"]//li', response_content)
for seg in segs:
ChemicalName,CASNumber,MolFormula,SearchImg,Synonyms,url = ['' for i in range(6)]
SearchImg = crawlerTool.getXpath1('//div[@class="leftSearchImg"]/a/img/@src', seg)
SearchImg = 'https://www.trc-canada.com' + SearchImg
contents = crawlerTool.getXpath('//div[@class="ContentDesc"]', seg)
for content in contents:
content=content.replace('\r','').replace('\n','')
if 'Chemical Name:' in content:
ChemicalName = crawlerTool.getRegex('</label>(.*?)<',content).strip()
elif 'CAS number:' in content:
CASNumber = crawlerTool.getRegex('</label>(.*?)<', content).strip()
elif 'Mol. Formula:' in content:
MolFormula = crawlerTool.getRegex('</label>(.*?)<', content).strip()
elif 'Synonyms' in content:
Synonyms = crawlerTool.getRegex('</label>(.*?)<', content).strip()
# primaryVendorId = crawlerTool.getXpath1('//str[@name="primaryVendorId"]/text()', seg)
data_obj = Trc_Item()
data_obj['ChemicalName'] = ChemicalName
data_obj['CASNumber'] = CASNumber
data_obj['MolFormula'] = MolFormula
data_obj['SearchImg'] = SearchImg
data_obj['Synonyms'] = Synonyms
data_obj['api_name'] = cat_name
data_obj['url'] = SearchImg
yield data_obj
def parse(self, response):
base_url = get_base_url(response)
response_content = response.body # 乱码处理 #像https://www.chemicalbook.com/ShowSupplierProductsList6187/51100.htm有9万多
suburls = crawlerTool.getXpath(
"//table[@id='ContentPlaceHolder1_ProductClassDetail']//tr/td[1]/a/@href",
response_content)
for suburl in suburls:
suburl = urljoin(base_url, suburl)
yield scrapy.Request(url=suburl, callback=self.parser_sub)
next_page_url = crawlerTool.getXpath('//div[@align="center"]/a/@href',
response_content)
if next_page_url:
for page_url in next_page_url: # 重试
page_url = urljoin(base_url, page_url)
yield scrapy.Request(url=page_url, callback=self.parse)
def parse(self, response):
base_url = get_base_url(response)
response_content = response.body # 乱码处理 #像https://www.chemicalbook.com/ShowSupplierProductsList6187/51100.htm有9万多
cat_name = response.meta.get('cat_name')
segs = crawlerTool.getXpath('//doc', response_content, xml_type='XML')
for seg in segs:
name = crawlerTool.getXpath1('//str[@name="name"]/text()', seg)
cas = crawlerTool.getXpath1('//str[@name="casNumber"]/text()', seg)
function = crawlerTool.getXpath1('//str[@name="tagline"]/text()',
seg)
# primaryVendorId = crawlerTool.getXpath1('//str[@name="primaryVendorId"]/text()', seg)
data_obj = Caymanchem()
data_obj['name'] = name
data_obj['cas'] = cas
data_obj['function'] = function
data_obj['cat'] = cat_name
data_obj['url'] = name + cat_name + cas
yield data_obj
totalnum = int(
crawlerTool.getXpath1('//result[@name="response"]//@numFound',
response_content,
xml_type='XML'))
if not response.meta.get('depth'):
print totalnum
for i in range(1, totalnum, 1):
url = 'https://www.caymanchem.com/solr/cchProduct/select?facet=true&facet.field=raptas'+\
'&facet.field=newProduct&facet.limit=100000&fl=isEUSellable%2Cname%2CmarkupName%2CcatalogNum%2CproductImage%2Csynonyms%2CcasNumber%2Ctagline%2Cscore%2CitemGroupId%2CprimaryVendorId&spellcheck=true&spellcheck.collate=true&spellcheck.count=10&spellcheck.extendedResults=true&spellcheck.onlyMorePopular=false&facet.mincount=1&rows=10&version=2.2&json.nl=map&'+\
'q=*%3A*&start='+str(i)+'&fq=('+cats[cat_name]+')AND(!raptas%3ARAP000101%20AND%20websiteNotSearchable%3Afalse)'
yield scrapy.Request(url,
callback=self.parse,
meta={
'cat_name': cat_name,
'depth': 1
})
class HxChemSpider(scrapy.Spider):
name = "hxchem" # 唯一标识
# allowed_domains = ["csdn.net"]
start_urls = [
"http://www.hxchem.net/company.php?page=%s"%str(i) for i in range(200,3160,1) #
]
#def start_requests(self): #测试cookie
# # 带着cookie向网站服务器发请求，表明我们是一个已登录的用户
# yield scrapy.Request(self.start_urls[0], callback=self.parse, cookies={'meng':1})
def parse(self, response):
base_url = get_base_url(response)
content = response.body # 乱码处理
for i in range(100):
try:
new_content = unicode(content, 'gbk')
break
except Exception, e:
if 'position' in str(e):
error_str = crawlerTool.getRegex('position\s+(\d+-\d+)', str(e))
start_index, end_index = int(error_str.split('-')[0]), int(error_str.split('-')[1]) + 1
content = content[:start_index] + content[end_index:]
response_content = new_content
suburls = crawlerTool.getXpath("//div[@class='ad_content']//dl/dt/a/@href",response_content)
if len(suburls)<10:
print('num error',response.url)
for suburl in suburls:
suburl = urljoin(base_url,suburl)
yield scrapy.Request(url=suburl,callback = self.parser_sub)
def parse(self, response):
base_url = get_base_url(response)
content = response.body # 乱码处理
manufacturers = crawlerTool.getXpath("//h2/a/@href", content)
for manufacturer in manufacturers:
sub_url = 'https://www.parkers.co.uk' + manufacturer + 'specs/'
yield scrapy.Request(url=sub_url, callback=self.parser_sub)
def parser_spec_url(self, response):
content = response.body
url = response.url
FullSpecs_urls = crawlerTool.getXpath('//h3/a/@href', content)
for spec_url in FullSpecs_urls:
if not 'http' in spec_url:
spec_url = 'https://www.parkers.co.uk' + spec_url
yield scrapy.Request(url=spec_url, callback=self.parser_detail)
def keyword_search(keyword):
keywords = urllib.quote(keyword)
url = 'https://www.youtube.com/results?search_query=' + keywords
page = ct.get(url)
imgurl0 = ct.getXpath('//div[@id="img-preload"]/img/@src', page)[0]
vid = ct.getRegex('i.ytimg.com/vi/(.*?)/', imgurl0)
video_url = 'https://www.youtube.com/watch?v=' + vid
print video_url
return video_url, imgurl0
def parse(self, response):
base_url = get_base_url(response)
url_now = response.url
response_content = response.body # 乱码处理
segs = crawlerTool.getXpath('//div[@class="cas_default_list_star "]//ul', response_content)
for seg in segs[1:-1]:
data_obj = SeekchemItem()
lis=crawlerTool.getXpath('//li',seg)
data_obj['url'] = crawlerTool.getXpath1('//a/@href',lis[0])
data_obj['cas'] = crawlerTool.getXpath1('//b/text()',lis[0])
data_obj['name'] = crawlerTool.getXpath1('//text()',lis[1])
yield data_obj
# next_page = crawlerTool.getXpath1("//a[@class='next']/@href", response_content)
# next_page_url = urljoin(url_now,next_page)
# yield scrapy.Request(url=next_page_url, callback=self.parse)
page_urls = crawlerTool.getXpath( '//div[@class="pages"]/a/@href', response_content)
for page_url in page_urls:
yield scrapy.Request(urljoin(url_now,page_url), callback=self.parse)
def parse(self, response):
base_url = get_base_url(response)
response_content = response.body # 乱码处理 #像https://www.chemicalbook.com/ShowSupplierProductsList6187/51100.htm有9万多
# cat_name = response.meta.get('cat_name')
segs = crawlerTool.getXpath('//li[@class="list-group-item"]/text()',
response_content)
for seg in segs:
data_obj = angenechemical_item()
data_obj['url'] = seg
yield data_obj
def parser_sub(self, response):
base_url = get_base_url(response)
response_content = response.body # 乱码处理
url = response.url
#detail =crawlerTool.getXpath('//div[@id="ContentPlaceHolder1_SupplierContact"]',response_content)[0] # 关于我们
# response_content = unicode(response_content, 'gbk') # http://www.hxchem.net/companydetaildesenborn.html 这个就不行了！
# lxwm = HTMLParser().unescape(lxwm)
# lxwm=lxwm.encode('utf8')
data_obj = ChemicalBook()
data_obj['url'] = url
data_obj['name'] = crawlerTool.getXpath(
'//div[@id="ContentPlaceHolder1_SupplierContact"]/table[2]//tr[2]/td[2]/a/text()',
response_content)[0]
data_obj['lxdh'] = crawlerTool.getXpath1(
'//div[@id="ContentPlaceHolder1_SupplierContact"]/table[2]//tr[3]/td[2]//text()',
response_content)
data_obj['email'] = crawlerTool.getXpath1(
'//div[@id="ContentPlaceHolder1_SupplierContact"]/table[2]//tr[5]/td[2]//text()',
response_content)
data_obj['wz'] = crawlerTool.getXpath1(
'//div[@id="ContentPlaceHolder1_SupplierContact"]/table[2]//tr[6]/td[2]//text()',
response_content)
cplb_div = crawlerTool.getXpath(
'//div[@id="ContentPlaceHolder1_ProductSupplier"]//table',
response_content)[3:-1]
print data_obj['name'].encode('unicode-escape').decode('string_escape')
cplb = []
for cp in cplb_div:
chinese_name = crawlerTool.getXpath('//tr/td[2]/text()', cp)
chinese_name = chinese_name[0] if chinese_name else ''
cps = crawlerTool.getXpath('//tr/td[3]/text()', cp)
cps = cps[0] if cps else ''
cplb.append(' '.join([chinese_name, cps]))
data_obj['cplb'] = cplb
# print lxr,dz,yb,dh,sj
yield data_obj
page_urls = crawlerTool.getXpath(
'//div[@id="ContentPlaceHolder1_ProductSupplier"]//table[2]//tr[2]/td[2]//a/@href',
response_content)
for page_url in page_urls:
page_url = urljoin(base_url, page_url)
yield scrapy.Request(url=page_url, callback=self.parser_sub)
def parse(self, response):
base_url = get_base_url(response)
response_content = response.body # 乱码处理 #像https://www.chemicalbook.com/ShowSupplierProductsList6187/51100.htm有9万多
cat_name = response.meta.get('cat_name')
segs = crawlerTool.getXpath('//table[@id="product-list"]/tbody/tr',
response_content)
for seg in segs:
name, MolecularFormula, MolecularWeight, image, cas, url = [
'' for i in range(6)
]
SearchImg = crawlerTool.getXpath1(
'//img[@class="dg-picture-zoom acc_img_container acc_zoomer"]/@src',
seg)
contents = crawlerTool.getXpath('//table//tr', seg)
for content in contents:
content = content.replace('\r', '').replace('\n', '')
if 'Name' in content:
name = crawlerTool.getXpath1('//td[2]', content)
name = crawlerTool.getRegex('>(.*?)<', name).strip()
elif 'CAS No' in content:
cas = crawlerTool.getXpath1('//td[2]', content)
cas = crawlerTool.getRegex('>(.*?)<', cas).strip()
elif 'Molecular Formula' in content:
MolecularFormula = crawlerTool.getXpath1(
'//td[2]', content)
MolecularFormula = re.sub('<.*?>', '',
MolecularFormula).strip()
elif 'Molecular Weight' in content:
MolecularWeight = crawlerTool.getXpath1('//td[2]', content)
MolecularWeight = crawlerTool.getRegex(
'>(.*?)<', MolecularWeight).strip()
# primaryVendorId = crawlerTool.getXpath1('//str[@name="primaryVendorId"]/text()', seg)
data_obj = acccorporation_Item()
data_obj['url'] = name
data_obj['name'] = name
data_obj['MolecularFormula'] = MolecularFormula
data_obj['MolecularWeight'] = MolecularWeight
data_obj['image'] = SearchImg
data_obj['cas'] = cas
yield data_obj
def parse(self, response):
response_content = response.body
cats = crawlerTool.getXpath('//input[@type="checkbox"]/@value',response_content)
print len(cats)
# cats = ['Ether']
for cat in cats:
first_str = cat[0].lower()
# if first_str in ('a','b','c'):continue
yield scrapy.FormRequest(url='https://www.trc-canada.com/parentdrug-listing/',
formdata={"keyword" : " %s "%cat, "t" : "product","advanced":"yes"},
callback=self.parse1,meta = {'cat_name':cat})
def parser_detail(self, response):
content = response.body
url = response.url
data_obj = ParkersItem()
data_obj['title'] = crawlerTool.getXpath('//title/text()', content)[0]
data_obj['url'] = url # url 中提取名称和model
urlsplit = url.split('/')
if len(urlsplit) > 4:
data_obj['name'] = urlsplit[3]
data_obj['model'] = urlsplit[4]
data_obj['power'] = crawlerTool.getRegex('Power</th><td>(.*?)</td>',
content)
data_obj['TopSpeed'] = crawlerTool.getRegex(
'Top Speed</th><td>(.*?)</td>', content)
data_obj['zerotosixty'] = crawlerTool.getRegex(
'<th>0-60 mph</th><td>(.*?)</td>', content)
data_obj['Torque'] = crawlerTool.getRegex(
'<th>Torque</th><td>(.*?)</td>', content)
data_obj['co2Emissions'] = crawlerTool.getRegex(
'<th>CO<sub>2</sub> Emissions</th><td>(.*?)</td>', content)
data_obj['EuroEmissionsStandard'] = crawlerTool.getRegex(
'<th>Euro Emissions Standard</th><td>(.*?)</td>', content)
data_obj['Fuelconsumption'] = crawlerTool.getRegex(
'<tr><th>Fuel consumption</th><td>(.*?)</td>', content)
data_obj['Length'] = crawlerTool.getRegex(
'<tr><th>Length</th><td>(.*?)</td>', content)
data_obj['Width'] = crawlerTool.getRegex(
'<tr><th>Width</th><td>(.*?)</td>', content)
data_obj['Height'] = crawlerTool.getRegex(
'<tr><th>Height</th><td>(.*?)</td>', content)
data_obj['EngineSize'] = crawlerTool.getRegex(
'<tr><th>Engine Size</th><td>(.*?)</td>', content)
data_obj['Cylinders'] = crawlerTool.getRegex(
'<tr><th>Cylinders</th><td>(.*?)</td>', content)
data_obj['FuelType'] = crawlerTool.getRegex(
'<tr><th>Fuel Type</th><td>(.*?)</td>', content)
data_obj['Transmission'] = crawlerTool.getRegex(
'<tr><th>Transmission</th><td>(.*?)</td>', content)
data_obj['Doors'] = crawlerTool.getRegex(
'<tr><th>Doors</th><td>(.*?)</td>', content)
data_obj['Seats'] = crawlerTool.getRegex(
'<tr><th>Seats</th><td>(.*?)</td>', content)
data_obj['taxcostBasic'] = crawlerTool.getRegex(
'<tr><th>Monthly company car tax cost \(Basic Rate\)</th><td>(.*?)</td>',
content).replace('£', '£') # £ 是英镑
# print lxr,dz,yb,dh,sj
yield data_obj
def parse(self, response):
base_url = get_base_url(response)
content = response.body # 乱码处理
segs = crawlerTool.getXpath(
"//table//td[2]//td/table[2]//td//table//tr//td//tr", content)
for seg in segs[1:]:
tds = crawlerTool.getXpath("//td", seg)
if len(tds) < 4:
continue
cat_no = tds[0]
product_name = tds[1]
cas = tds[2]
assay = tds[3]
rovathin_item = RovathinItem()
rovathin_item['cat_no'] = re.sub('\s*<.*?>\s*', '', cat_no)
rovathin_item['product_name'] = re.sub('\s*<.*?>\s*', '',
product_name)
rovathin_item['cas'] = re.sub('\s*<.*?>\s*', '', cas)
rovathin_item['assay'] = re.sub('\s*<.*?>\s*', '', assay)
rovathin_item['url'] = crawlerTool.getXpath1(
"//a/@href", product_name)
yield rovathin_item
class CmocroSpider(scrapy.Spider):
name = "cmocro" # 唯一标识
# allowed_domains = ["csdn.net"]
start_urls = [
#
]
db_connect = MysqlPipeline3()
url_cache = [] # 这里用一下内存去重
for i in xrange(26):
c1 = chr(i + ord('a'))
for i in xrange(26):
c2 = chr(i + ord('a'))
start_urls .append("https://www.cmocro.com/company_search.php?company=%s%s" % (c1,c2))
# start_urls = start_urls[:1]
#def start_requests(self): #测试cookie
# # 带着cookie向网站服务器发请求，表明我们是一个已登录的用户
# yield scrapy.Request(self.start_urls[0], callback=self.parse, cookies={'meng':1})
def parse(self, response):
base_url = get_base_url(response)
content = response.body # 乱码处理
for i in range(100):
try:
new_content = unicode(content, 'utf8')
break
except Exception, e:
if 'position' in str(e):
print str(e)
error_str = crawlerTool.getRegex('position\s+(\d+-\d+)', str(e))
if '-' in str(e):
start_index, end_index = int(error_str.split('-')[0]), int(error_str.split('-')[1]) + 1
content = content[:start_index] + content[end_index:]
else:
start_index = int(crawlerTool.getRegex('position (\d+)',str(e)))
content = content[:start_index] + content[start_index+1:]
response_content = new_content
suburls = crawlerTool.getXpath('//div[@class="company_list"]/a/@href',response_content)
for suburl in suburls:
suburl = urljoin(base_url, suburl)
if not self.db_connect.get_by_unique_value(suburl):
yield scrapy.Request(url=suburl,callback = self.parser_sub)
def extractor_page2(page, code): # 解析详情页
# 买入前5名
content_table = crawlerTool.getXpath('//table', page, charset='gbk')[0]
trs = crawlerTool.getXpath('//tr', content_table, charset='gbk')
rows = [[], [u'股票代码', code]]
for tr in trs:
row = []
for td in crawlerTool.getXpath('//th', tr, charset='gbk'):
row.append(re.sub('(<.*?>)', "", td).strip())
for td in crawlerTool.getXpath('//td', tr, charset='gbk'):
row.append(re.sub('(<.*?>)', "", td).strip())
rows.append(row)
#卖出前5名
content_table = crawlerTool.getXpath('//table', page, charset='gbk')[1]
trs = crawlerTool.getXpath('//tr', content_table, charset='gbk')
for tr in trs:
row = []
for td in crawlerTool.getXpath('//th', tr, charset='gbk'):
row.append(re.sub('(<.*?>)', "", td).strip())
for td in crawlerTool.getXpath('//td', tr, charset='gbk'):
row.append(re.sub('(<.*?>)', "", td).strip())
rows.append(row)
return rows
def parser_sub(self,response):
content = response.body # 乱码处理
for i in range(100):
try:
new_content = unicode(content, 'gbk')
break
except Exception, e:
if 'position' in str(e):
error_str = crawlerTool.getRegex('position\s+(\d+-\d+)', str(e))
start_index, end_index = int(error_str.split('-')[0]), int(error_str.split('-')[1]) + 1
content = content[:start_index] + content[end_index:]
response_content = new_content
print response.url
url= response.url
gywm =crawlerTool.getXpath("//td[@class='goscill22']/table[2]//p/text()",response_content) # 关于我们
gywm = ''.join(gywm).replace('\n','').replace('\r','')
# response_content = unicode(response_content, 'gbk') # http://www.hxchem.net/companydetaildesenborn.html 这个就不行了！
lxwm = crawlerTool.getXpath("//td[@class='goscill22']/table[4]",response_content) # 联系我们
lxwm = lxwm[0]
# lxwm = HTMLParser().unescape(lxwm)
# lxwm=lxwm.encode('utf8')
data_obj = HxchemItem()
data_obj['url'] = url
data_obj['gywm'] = gywm
data_obj['name'] = crawlerTool.getXpath("//h1/text()",response_content)[0]
data_obj['lxr'] = crawlerTool.getRegex('联系人：(.*?)<',lxwm)
data_obj['dz'] = crawlerTool.getRegex('地 址：(.*?)<',lxwm)
data_obj['yb'] = crawlerTool.getRegex('邮 编：(.*?)<',lxwm)
data_obj['dh'] = crawlerTool.getRegex('电 话：(.*?)<',lxwm)
data_obj['sj'] = crawlerTool.getRegex('手 机：(.*?)<',lxwm)
