72727272 发表于 2020-9-12 19:47

爬虫

爬取某某共享游戏排行榜
import requests
import re

for i in range(1,50):
    url="http://www.yx7088.com/gamelist/index.html?&p={0}".format(i)
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36'}
    a = requests.get(url, headers=headers)
    a.encoding = 'utf-8'
    bb = re.compile('<em>.*?<a.*?>(.*?)</a>', re.S)
    position=re.findall(bb,a.text)
    print(position)
    with open("Steam.txt", "a", encoding="utf-8") as f:
      for positions in position:
            f.write(positions + "\n")
页: [1]
查看完整版本: 爬虫