import re
import requests
import random
from lxml import etree
import csv
base_url = 'https://movie.douban.com/top250'
# 随机设置UA与IP
headers_choice = [{
'User-Agent':'Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50safari 5.1 – Windows'},{
'User-Agent':'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Maxthon 2.0)TT'},{
'User-Agent':'?Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SE 2.X MetaSr 1.0; SE 2.X MetaSr 1.0; .NET CLR 2.0.50727; SE 2.X MetaSr 1.0)'},{
'User-Agent':'Mozilla/5.0 (iPhone; U; CPU iPhone OS 4_3_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8J2 Safari/6533.18.5'},{
'User-Agent':''},{
'User-Agent':'MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1'},{
'User-Agent':'Mozilla/5.0 (compatible; MSIE 9.0; Windows Phone OS 7.5; Trident/5.0; IEMobile/9.0; HTC; Titan)'},{
'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11'},{
'User-Agent':'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)Firefox 4.0.1 – MAC'}]
proxy_choice = [{
'http':'218.66.253.144:80'},{
'http':
爬取豆瓣电影信息且写入csv文件
最新推荐文章于 2024-04-15 15:58:17 发布
该博客讲述了如何爬取豆瓣电影的数据,并将获取的信息成功写入CSV文件,过程中遇到了未知错误,但未给出解决方案。
摘要由CSDN通过智能技术生成