第十二节 豆瓣电影实战

import requests
from lxml import etree


headers = {
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36‘,
    ‘Referer‘:‘https://pagead2.googlesyndication.com/pagead/s/cookie_push.html‘
}
url = ‘https://movie.douban.com/cinema/nowplaying/fuzhou/‘
resp = requests.get(url, headers = headers)
text = resp.text
html = etree.HTML(text)
ul = html.xpath(‘//ul[@class="lists"]‘)[0]
lis = ul.xpath(‘./li[@class="list-item"]‘)
movies = []
for li in lis:
    title = li.xpath(‘@data-title‘)
    score = li.xpath(‘@data-score‘)
    star = li.xpath(‘@data-star‘)
    duration = li.xpath(‘@data-duration‘)
    region = li.xpath(‘@data-region‘)
    director = li.xpath(‘@data-director‘)
    actors = li.xpath(‘@data-actors‘)
    movie = {
        "title":title,
        "score":score,
        "star":star,
        "duration":duration,
        "region":region,
        "director":director,
        "actors":actors
    }
    movies.append(movie)
for m in movies:
    print(m)