Python爬蟲獲取Csdn文章

request獲取html

安裝:

pip install requests

使用：

import requests  
 HTTP請求：GET、POST、PUT、DELETE、HEAD、OPTIONS

1. get
   res = requests.get(“https://www.baidu.com”)
2. post
   res = requests.post(“https://www.baidu.com”);
3. put
   res = requests.put(“https://www.baidu.com”);
4. delete
   res = requests.delete(“https://www.baidu.com”);
5. head
   res = requests.head(“https://www.baidu.com”) ;
6. options
   res = requests.options(“https://www.baidu.com”)

#獲取文章的html
from urllib import request
import random
import time
import lxml
import re
from bs4 import BeautifulSoup as bs
def Get_Target_ip():
 	 headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}
     req = request.Request(r'#這裏寫你csdn主頁的url', headers=headers)
     response = request.urlopen(req)
     html = response.read().decode('utf-8')
     soup = bs(html, 'lxml')
     hList = soup.find_all(name='h4', attrs={'class': ''})
     for h in hList:
        href = h.find(name='a').get('href')
        requestList.append(request.Request(href))
     return requestList
     
if __name__ == '__main__':
    requestList = Get_Target_ip()

BeautifulSoup 可以用來獲取html中想要字段的文本