使用python爬取網(wǎng)頁信息的方法

if html.status_code!=200 print('status_code if {}'.format(html.status_code))

# @author： limingxuan 
# @contect： limx2011@hotmail.com
# @blog： https://www.jianshu.com/p/a5907362ba72
# @time： 2018-07-21
import requests
from bs4 import BeautifulSoup
import time
from pymongo import MongoClient
headers = {  
  'accept': "application/json, text/javascript, */*; q=0.01",
  'accept-encoding': "gzip, deflate, br",
  'accept-language': "zh-CN,zh;q=0.9,en;q=0.8",
  'content-type': "application/x-www-form-urlencoded; charset=UTF-8",
  'cookie': "JSESSIONID=""; __c=1530137184; sid=sem_pz_bdpc_dasou_title; __g=sem_pz_bdpc_dasou_title; __l=r=https%3A%2F%2Fwww.zhipin.com%2Fgongsi%2F5189f3fadb73e42f1HN40t8~.html&l=%2Fwww.zhipin.com%2Fgongsir%2F5189f3fadb73e42f1HN40t8~.html%3Fka%3Dcompany-jobs&g=%2Fwww.zhipin.com%2F%3Fsid%3Dsem_pz_bdpc_dasou_title; Hm_lvt_194df3105ad7148dcf2b98a91b5e727a=1531150234,1531231870,1531573701,1531741316; lastCity=101010100; toUrl=https%3A%2F%2Fwww.zhipin.com%2Fjob_detail%2F%3Fquery%3Dpython%26scity%3D101010100; Hm_lpvt_194df3105ad7148dcf2b98a91b5e727a=1531743361; __a=26651524.1530136298.1530136298.1530137184.286.2.285.199",
  'origin': "https://www.zhipin.com",
  'referer': "https://www.zhipin.com/job_detail/?query=python&scity=101010100",
  'user-agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36"
  }
conn = MongoClient('127.0.0.1',27017)
db = conn.zhipin_jobs
def init():
  items = db.Python_jobs.find().sort('pid')
  for item in items:
    if 'detial' in item.keys(): #當(dāng)爬蟲掛掉時(shí)，跳過已爬取的頁
      continue
    detail_url = 'https://www.zhipin.com/job_detail/{}.html'.format(item['pid']) #單引號和雙引號相同，str.format()新格式化方式
    #第一階段順利打印出崗位頁面的url
    print(detail_url)
    #返回的html是 Response 類的結(jié)果
    html = requests.get(detail_url,headers = headers)
    if html.status_code != 200:
      print('status_code is {}'.format(html.status_code))
      break
    #返回值soup表示一個(gè)文檔的全部內(nèi)容（html.praser是html解析器）
    soup = BeautifulSoup(html.text,'html.parser')
    job = soup.select('.job-sec .text')
    print(job)
    #???
    if len(job)<1:
    item['detail'] = job[0].text.strip() #職位描述
    location = soup.select(".job-sec .job-location .location-address") 
    item['location'] = location[0].text.strip() #工作地點(diǎn)
    item['updated_at'] = time.strftime("%Y-%m-%d %H:%M:%S",time.localtime()) #實(shí)時(shí)爬取時(shí)間
    #print(item['detail'])
    #print(item['location'])
    #print(item['updated_at'])
    res = save(item) #調(diào)用保存數(shù)據(jù)結(jié)構(gòu)
    print(res)
    time.sleep(40)#爬太快IP被封了24小時(shí)==
#保存數(shù)據(jù)到MongoDB中
def save(item):
  return db.Python_jobs.update_one({'_id':item['_id']},{'$set':item}) #why item &#63;&#63;&#63;
   
# 保存數(shù)據(jù)到MongoDB
     
if __name__ == '__main__':
  init()