06、豆瓣爬虫

    把豆瓣TOP250里面的 序号/电影名/评分/推荐语/链接 都爬取下来，结果就是全部展示打印出来

 

    URL  https://movie.douban.com/top250?start=

 

#6、豆瓣爬虫
#    把豆瓣TOP250里面的 序号/电影名/评分/推荐语/链接 都爬取下来，结果就是全部展示打印出来
#    URL  https://movie.douban.com/top250?start=

import requests
from bs4 import BeautifulSoup

for i in range(0,250,25):
    res = requests.get('https://movie.douban.com/top250?start={}'.format(i))
    html = res.text
    soup = BeautifulSoup(html,'html.parser')
    items = soup.find_all('div',class_='item')

    for item in items:
        print(item.find('em').text,end='	')
        print(item.find('span').text,end='	')
        print(item.find('span',class_='rating_num').text,end='	')
        try:
            print(item.find('span',class_='inq').text,end='	')
        except AttributeError:
            print('',end='	')
        print(item.find('a')['href'])

'''
老师的代码

import requests
# 引用requests模块
from bs4 import BeautifulSoup
for x in range(10):
    url = 'https://movie.douban.com/top250?start=' + str(x*25) + '&filter='
    res = requests.get(url)
    bs = BeautifulSoup(res.text, 'html.parser')
    tag_num = bs.find_all('div', class_="item")
    # 查找包含序号，电影名，链接的<div>标签
    tag_comment = bs.find_all('div', class_='star')
    # 查找包含评分的<div>标签
    tag_word = bs.find_all('span', class_='inq')
    # 查找推荐语


    list_all = []
    for x in range(len(tag_num)):
        if tag_num[x].text[2:5] == '223' or tag_num[x].text[2:5] =='244':
            list_movie = [tag_num[x].text[2:5], tag_num[x].find('img')['alt'], tag_comment[x].text[2:5], tag_num[x].find('a')['href'] ]
        else:
            list_movie = [tag_num[x].text[2:5], tag_num[x].find('img')['alt'], tag_comment[x].text[2:5], tag_word[x].text, tag_num[x].find('a')['href']]
        list_all.append(list_movie)
    print(list_all)
'''

 

items中每个Tag的内容如下

 

<div class="item">
    <div class="pic">
        <em class="">151</em>
        <a href="https://movie.douban.com/subject/24750126/">
            <img width="100" alt="荒蛮故事"
                src="https://img3.doubanio.com/view/photo/s_ratio_poster/public/p2192834364.webp" class="">
        </a>
    </div>
    <div class="info">
        <div class="hd">
            <a href="https://movie.douban.com/subject/24750126/" class="">
                <span class="title">荒蛮故事</span>
                <span class="title">&nbsp;/&nbsp;Relatos salvajes</span>
                <span class="other">&nbsp;/&nbsp;蛮荒故事 / 生命中最抓狂的小事(台)</span>
            </a>
            <span class="playable">[可播放]</span>
        </div>
        <div class="bd">
            <p class="">
                导演: 达米安·斯兹弗隆 Damián Szifron&nbsp;&nbsp;&nbsp;主演: 达里奥·葛兰帝内提 Darío...

                2014&nbsp;/&nbsp;阿根廷 西班牙&nbsp;/&nbsp;剧情 喜剧 犯罪
            </p>
            <div class="star">
                <span class="rating45-t"></span>
                <span class="rating_num" property="v:average">8.8</span>
                <span property="v:best" content="10.0"></span>
                <span>203246人评价</span>
            </div>
            <p class="quote">
                <span class="inq">始于荒诞，止于更荒诞。</span>
            </p>
        </div>
    </div>
</div>