|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
- import requests
- import bs4
- import re
- def open_url(url):
- headers = {
- 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36',
- 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
- 'Accept-Language':'en-US,en;q=0.5',
- 'Accept-Encoding':'gzip',
- 'DNT':'1',
- 'Connection':'close'
- }
-
- res =requests.get(url,headers=headers)
- print(res.text)
- with open("save.txt","w",encoding="utf-8") as f:
- f.write(res.text)
- return res
- def main():
- #url = "https://search.51job.com/list/000000,000000,0000,00,9,99,+,2,1.html?lang=c&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare="
- url = "https://search.51job.com/list/000000,000000,0000,00,9,99,%25E5%2590%258E%25E7%25AB%25AF%25E5%25BC%2580%25E5%258F%2591,2,1.html?lang=c&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare="
-
- open_url(url)
-
- if __name__ =='__main__':
- main()
复制代码
爬取下来保存的txt文件里的window.__SEARCH_RESULT__ ={}里的内容在网页端找不到,网页端的东西在txt文件里也找不到,请问各位大佬是什么原因呢
这要看你想提取啥数据了
很多网站 有些数据不登录 无法提取
|
|