from re import *
import requests
import json
import time
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36'
}
response=requests.get('https://movie.douban.com/top250',headers=headers)
re_str=r'(<em class="">(\d+)</em>)|(img width="100" alt="(.+?)")|(property="v:average">(\d\.\d))'
result=findall(re_str,response.text)
base='https://movie.douban.com/top250?start='
cookie='bid=7fqXAucekUY; __yadk_uid=Bv830K52qYhW5rmyhZQLTfJPOp6yLInX; ll="118318"; __utmc=30149280; __utmc=223695111; dbcl2="235252729:0f2joyxVeGo"; ck=so1z; push_doumail_num=0; push_noty_num=0; __utmt=1; __utmv=30149280.23525; _pk_ref.100001.4cf6=%5B%22%22%2C%22%22%2C1617015129%2C%22https%3A%2F%2Fwww.douban.com%2Fpeople%2F235252729%2F%22%5D; _pk_ses.100001.4cf6=*; _vwo_uuid_v2=D6572DC3DA06FB21E4214600AF3ED5665|5888de0ec4d9e5950fccc8d96450cd2b; __gads=ID=56c2fa7457ca603c-22911104e7c600bc:T=1617015183:RT=1617015183:S=ALNI_MYsycL0nbVvzdCsxfv0Ls5oauwNpw; __utma=30149280.169855030.1617004581.1617015087.1617015235.4; __utmb=30149280.0.10.1617015235; __utmz=30149280.1617015235.4.4.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utma=223695111.1679640269.1617004581.1617015129.1617015235.4; __utmz=223695111.1617015235.4.4.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utmb=223695111.1.10.1617015235; _pk_id.100001.4cf6=8a67d2a6606d1074.1617004580.3.1617015235.1617009163.'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36',
'Cookie':'bid=7fqXAucekUY; __yadk_uid=Bv830K52qYhW5rmyhZQLTfJPOp6yLInX; ll="118318"; __utmc=30149280; __utmc=223695111; dbcl2="235252729:0f2joyxVeGo"; ck=so1z; push_doumail_num=0; push_noty_num=0; __utmt=1; __utmv=30149280.23525; _pk_ref.100001.4cf6=%5B%22%22%2C%22%22%2C1617015129%2C%22https%3A%2F%2Fwww.douban.com%2Fpeople%2F235252729%2F%22%5D; _pk_ses.100001.4cf6=*; _vwo_uuid_v2=D6572DC3DA06FB21E4214600AF3ED5665|5888de0ec4d9e5950fccc8d96450cd2b; __gads=ID=56c2fa7457ca603c-22911104e7c600bc:T=1617015183:RT=1617015183:S=ALNI_MYsycL0nbVvzdCsxfv0Ls5oauwNpw; __utma=30149280.169855030.1617004581.1617015087.1617015235.4; __utmb=30149280.0.10.1617015235; __utmz=30149280.1617015235.4.4.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utma=223695111.1679640269.1617004581.1617015129.1617015235.4; __utmz=223695111.1617015235.4.4.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utmb=223695111.1.10.1617015235; _pk_id.100001.4cf6=8a67d2a6606d1074.1617004580.3.1617015235.1617009163.'
}
for x in range(10):
base1=base+str(x*25)
response=requests.get(base1,headers=headers)
result2=findall(re_str,response.text)
print(result2)
3.29作业
最新推荐文章于 2022-03-29 21:23:27 发布