拉钩招聘网

以拉钩具体详情页为例，进行抓取

http://www.lagou.com/jobs/2101463.html

  1. from lxml import etree
  2. import requests
  3. import re
  5. response = requests.get('http://www.lagou.com/jobs/2101463.html')
  6. resHtml = response.text
  8. html = etree.HTML(resHtml)
  10. title = html.xpath('//h1[@title]')[0].attrib['title']
  11. #salary= html.xpath('//span[@class="red"]')[0].text
  13. salary = html.xpath('//dd[@class="job_request"]/p/span')[0].text
  14. worklocation = html.xpath('//dd[@class="job_request"]/p/span')[1].text
  15. experience = html.xpath('//dd[@class="job_request"]/p/span')[2].text
  16. education = html.xpath('//dd[@class="job_request"]/p/span')[3].text
  17. worktype = html.xpath('//dd[@class="job_request"]/p/span')[4].text
  18. Temptation = html.xpath('//dd[@class="job_request"]/p[2]')[0].text
  20. print salary,worklocation,experience,education,worktype,Temptation
  22. description_tag = html.xpath('//dd[@class="job_bt"]')[0]
  23. description =  etree.tostring( description_tag,encoding='utf-8')
  24. #print description
  25. deal_descp =  re.sub('<.*?>','',description)
  26. print deal_descp.strip()
  27. publisher_name =  html.xpath('//*[@class="publisher_name"]//@title')[0]
  28. pos =  html.xpath('//*[@class="pos"]')[0].text
  29. chuli_lv =  html.xpath('//*[@class="data"]')[0].text
  30. chuli_yongshi =  html.xpath('//*[@class="data"]')[1].text
  32. print chuli_lv,chuli_yongshi,pos,publisher_name