def parse(self, response):
if "job.liepin.com" in response.url:
soup=BeautifulSoup(response.body,'lxml')
if not soup.find('div','title-info over'):
liepinItem = LiepinJobItem()
liepinItem['name'] = soup.find('div',class_='title-info').find('h1').get_text().strip()
liepinItem['salary'] = soup.find('p',class_='job-main-title').get_text().strip().split()[0].strip()
liepinItem['jobid'] = Util.pathnumber_job(response.url)
liepinItem['companyid'] = Util.pathnumber_company(soup.find('div',class_='right-post-top').find('a')['href'])
liepinItem['location'] = soup.find('p',class_='basic-infor').find('span').get_text().strip()
spantext = ''
resumespan = soup.find('div',class_='resume clearfix')
if resumespan :
spans = resumespan.find_all('span')
for span in spans:
spantext = spantext+span.get_text()+" "
liepinItem['require'] = spantext
divtags = soup.find('div',class_='tag-list clearfix')
tags = []
if divtags:
tags = divtags.find_all('span')
tagtext = ''
for tag in tags:
tagtext = tagtext + tag.get_text().strip() + ','
liepinItem['tag']=tagtext
liepinItem['jobdes'] = soup.find('div',class_='content content-word')
lis = []
jobmaindiv = soup.find_all('div',class_='job-main main-message ')
if jobmaindiv.__len__() > 1:
lis = jobmaindiv[1].find_all('li')
liepinItem['partment'] = ''
liepinItem['major'] = ''
liepinItem['report']=''
liepinItem['sub']=''
liepinItem['sex'] =''
for li in lis:
if u'所' in li.find('span').get_text().strip():
liepinItem['partment']=li.get_text().split()[0].strip()[5::].strip()
if u'专' in li.find('span').get_text().strip():
liepinItem['major']=li.get_text().split()[0].strip()[5::].strip()
if u'汇' in li.find('span').get_text().strip():
liepinItem['report']=li.get_text().split()[0].strip()[5::].strip()
if u'下' in li.find('span').get_text().strip():
liepinItem['sub']=li.get_text().split()[0].strip()[5::].strip()
if u'性' in li.find('span').get_text().strip():
liepinItem['sex']=li.get_text().split()[0].strip()[5::].strip()
yield liepinItem
urls = response.selector.xpath("//a/@href[contains(.,'liepin')]").extract()
for url in urls:
if "m." not in url:
if "http" in url:
yield Request(url,callback = self.parse)
else:
yield Request("http://"+url,callback = self.parse)
def parse(self, response):
liepinItem = LiepinCompanyItem()
if Util.match_company(response.url):
if "company.liepin.com" in response.url:
normalLogo = response.selector.xpath("//img[@class='normalELogo']")
bigLogo = response.selector.xpath("//img[@class='bigELogo']")
bannerLogo = response.selector.xpath("//div[@class='banner']")
soup=BeautifulSoup(response.body,'lxml')
if bigLogo:
liepinItem['logo'] = soup.find('img',class_='bigELogo')['src']
liepinItem['name'] = soup.find('div',class_='company-name').find('h1').get_text().strip()
liepinItem['size'] = ""
liepinItem['property'] = ""
liepinItem['field'] = ""
liepinItem['finance'] = ""
liepinItem['website'] = ""
liepinItem['location'] = ""
liepinItem['address'] = soup.find('p',attrs={'data-selector':'company-address'}).get_text().strip()
tags = soup.find('section',class_="company-info").find('ul',class_='company-tags clearfix').find_all("li")
tag_text=','
for tag in tags:
tag_text = tag_text+tag.get_text().strip()+","
liepinItem['tag']=tag_text[::-1]
aboutuls = soup.find('ul',class_='about-list')
for ul in aboutuls:
if u"领" in ul.get_text().strip():
liepinItem['field'] = ul.get_text().strip()[3::]
if u"地" in ul.get_text().strip():
liepinItem['location'] = ul.get_text().strip()[3::]
if u"官" in ul.get_text().strip():
liepinItem['website'] = ul.get_text().strip()[3::]
if u"融" in ul.get_text().strip():
liepinItem['finance'] = ul.get_text().strip()[3::]
liepinItem['intro'] = ""
liepinItem['companyid'] = Util.pathnumber_company(response.url)
sadd("imperfect",liepinItem['companyid'])
elif normalLogo:
liepinItem['logo'] = soup.find('section',class_="introduction").find('img',class_='normalELogo')['src']
liepinItem['name'] = soup.find('section',class_="introduction").find('div',class_='einfo').find('h2').get_text().strip()
liepinItem['size'] = soup.find('section',class_="introduction").find('div',class_='e-menu').find('ul',class_='clearfix').find_all('li')[0].get_text().strip()
liepinItem['property'] = soup.find('section',class_="introduction").find('div',class_='e-menu').find('ul',class_='clearfix').find_all('li')[1].get_text().strip()
liepinItem['location'] = soup.find('section',class_="introduction").find('div',class_='e-menu').find('ul',class_='clearfix').find_all('li')[2].get_text().strip()
tag_list = soup.find('section',class_="introduction").find('div',class_='tag-list clearfix')
tag_text=''
if tag_list:
tags = tag_list.find_all('span',class_='tag')
for tag in tags:
tag_text = tag_text+tag.get_text().strip()+","
liepinItem['tag']=tag_text[::-1]
liepinItem['field']=''
liepinItem['finance'] = ""
liepinItem['website'] = ""
introdiv = soup.find('div',class_='intro-main')
liepinItem['intro'] = ""
liepinItem['address'] = ""
if introdiv:
liepinItem['intro'] = introdiv
if soup.find('p',class_='company-address'):
liepinItem['address'] = soup.find('p',class_='company-address').get_text().strip()
liepinItem['companyid'] = Util.pathnumber_company(response.url)
elif bannerLogo:
liepinItem['logo'] = ""
liepinItem['name'] = ""
liepinItem['size'] = ""
liepinItem['property'] = ""
liepinItem['location'] = ""
liepinItem['tag'] = ""
liepinItem['field']=''
liepinItem['finance'] = ""
liepinItem['website'] = ""
liepinItem['intro'] = ""
liepinItem['address'] = ""
liepinItem['companyid'] = Util.pathnumber_company(response.url)
sadd("imperfect",liepinItem['companyid'])
if int(liepinItem['companyid']) > 100000:
yield liepinItem
elif "vip.liepin.com" in response.url:
liepinItem['logo'] = ""
liepinItem['name'] = ""
liepinItem['size'] = ""
liepinItem['property'] = ""
liepinItem['location'] = ""
liepinItem['tag'] = ""
liepinItem['field'] = ''
liepinItem['finance'] = ""
liepinItem['website'] = ""
liepinItem['intro'] = ""
liepinItem['address'] = ""
liepinItem['companyid'] = Util.pathnumber_vip(response.url)
sadd("imperfect",liepinItem['companyid'])
urls = response.selector.xpath("//a/@href[contains(.,'liepin')]").extract()
for url in urls:
if "m." not in url:
if "http" in url:
yield Request(url,callback = self.parse)
else:
yield Request("http://"+url,callback = self.parse)
