1 import requests
2 import json
3 from bs4 import BeautifulSoup #网页解析获取数据
4 import sys
5 import re
6 import urllib.request,urllib.error #制定url，获取网页数据
7 import sqlite3
8 import xlwt #excel操作
9
10 def get_ten():
11 url="https://v.qq.com/channel/movie?_all=1&channel=movie&listpage=1&sort=18"
12 headers={
13 'user-agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '+
14 'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36'
15 }
16 # res = urllib.request.urlopen(url)
17 res = urllib.request.Request(url=url,headers=headers) #编辑request请求
18 response=urllib.request.urlopen(res).read().decode() #读取
19 html=BeautifulSoup(response,"html.parser") #解析
20 #
21 # list=html.select(".figure_score")
22 # for item in list:
23 # print(item)
24 dataRes=[]
25 findLink=re.compile(r'href="(.*?)"') #链接
26 findName=re.compile(r'title="(.*?)"') #影片名
27 soup=html.find_all(r"a",class_="figure")
28 for i in soup:
29 # print(i)
30 words=str(i)
31 dataRes.append(re.findall(findLink,words)) #添加链接
32 dataRes.append(re.findall(findName,words)) #添加影片名
33 for i in dataRes:
34 print(i)
35 # print(html)
36 # print(html.head.contents) #输出tag的所有子节点（list）
37 # print(response)
38 return res
39 if __name__ == '__main__':
40 get_ten()
