爬豆瓣电影名

Posted 2020-10-04 byerHu

import urllib.request
from bs4 import BeautifulSoup

url = "https://movie.douban.com/chart"
req = urllib.request.Request(url)
req.add_header("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:54.0) Gecko/20100101 Firefox/54.0")
response = urllib.request.urlopen(url)
bsObj = BeautifulSoup(response, \'html.parser\')
bsObj = bsObj.find_all(\'div\', {\'class\': \'pl2\'})
print(bsObj[0].contents[1].get_text())
for tag in bsObj:

    div_tag = tag.contents[1].get_text()

    name = div_tag.strip(\'\\n\').replace(\' \', \'\') +\'\\n\'

    print(name)