豆瓣

提取豆瓣250：电影名、评分、评论人数

# 本案例使用 XPath 实现

from lxml import etree
import re

with open('/Users/will/Desktop/Top250.html', 'r') as f:
    data = f.read()

selector = etree.HTML(data)

items = selector.xpath('//div[@class="item"]')

infos = []

for item in items:
    title = item.xpath('.//span[@class="title"][1]/text()')[0]
    rating_num = item.xpath('.//span[@class="rating_num"]/text()')[0]
    comment = item.xpath('.//div[@class="star"]//span[last()]/text()')[0]
    comment_num = re.search('\d+', comment).group()

    info = (title, rating_num, comment_num)
    infos.append(info)

print(infos)

提取豆瓣“选电影”

https://movie.douban.com/explore

提示：此页面有referer反爬措施

import requests

url = 'https://m.douban.com/rexxar/api/v2/movie/recommend?refresh=0&start=0&count=20&selected_categories=%7B%7D&uncollect=false&tags='
header = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
    'Referer': 'https://movie.douban.com/explore'
}

res = requests.get(url, headers=header)

# requests对象提供的反序列化方式（不用调用json模块，更加方便）
data = res.json()['items']

print(res.status_code)

for item in data:
    if item.get('title'):
        print(item.get('title'))