猫史档案馆

在 【Python作品分享】用Python爬虫爬取电影信息【作品秀】 中回复

import requests import re import time import csv url = ' https://dytt89.com/'
header = { 'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KH喵L, like Gecko) Chrome/102.0.0.0 Safari/537.36' }
resp = requests.get(url=url,headers=header) resp.encoding = 'gb2312' resp.close()
obj1 = re.compile(r"2023必看热片.*?<ul>(?P<ul>.*?)</ul>",re.S) obj2 = re.compile(r"<a href='(?P<href>.*?)'",re.S) obj3 = re.compile(r'◎片　　名(?P<name>.*?)<br />.*?<td ' r'style="WORD-WRAP: break-word" bgcolor="#fdfddf"><a href="(?P<downurl>.*?)"',re.S)

ret1 = obj1.finditer(resp.text) for it in ret1: ul = it.group('ul') ret2 = obj2.finditer(ul) child_list = []
for itt in ret2: child_href = url + itt.group('href').strip('/') child_list.append(child_href)
resp_list = []
f = open('moive.csv',mode='w',encoding='utf-8') csvw = csv.writer(f) for href in child_list: child_resp = requests.get(href,headers=header) child_resp.encoding = 'gb2312' ret3 = obj3.search(child_resp.text) dic = ret3.groupdict() csvw.writerow(dic.values()) #把间隔时间改长一点，不然会被封 time.sleep(0.5) child_resp.close() print("over")

2023-08-28T14:45:30 点赞:0