豆瓣电影爬虫编写教程

Posted 2022-05-08 secsafe

import  requests

from lxml import etree

headers =
    ‘User-Agent‘:"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/75.0.3770.142 Safari/537.36",
    ‘Referer‘:"https://movie.douban.com/"


url="https://movie.douban.com/cinema/nowplaying/shijiazhuang/"
response = requests.get(url,headers=headers)
text = response.text

html = etree.HTML(text)
ul = html.xpath("//ul[@class=‘lists‘]")[0]
#print(etree.tostring(ul,encoding=‘utf-8‘).decode("utf-8"))
lis = ul.xpath("./li")
movies = []
for li in lis:
        #print(etree.tostring(li,encoding=‘utf-8‘).decode("utf-8"))
    title = li.xpath("@data-title") [0]
    score = li.xpath("@data-score")[0]
    duration = li.xpath("@data-duration")[0]
    region = li.xpath("@data-region")[0]
    director = li.xpath("@data-director")[0]
    actors = li.xpath("@data-actors")[0]
    thumbnail = li.xpath(".//img/@src")[0]
    movie = 
        ‘title‘:title,
        ‘score‘:score,
        ‘duration‘:duration,
        ‘region‘:region,
        ‘director‘:director,
        ‘actors‘:actors,
        ‘thumbnail‘:thumbnail
    
    movies.append(movie)

print(movies)

以上代码仅供参考学习！