爬虫案例—爬取豆瓣电影最受欢迎的影评

news2024/10/7 12:24:34

爬虫案例—爬取豆瓣电影最受欢迎的影评

豆瓣影评网址：https://movie.douban.com/review/best/

目标：爬取第一页的影评封面标题、评论内容、完整的评论内容

第一页页面截图如下：

Screenshot 2024-01-14 at 20.16.28

import requests
from lxml import etree
import re
from bs4 import BeautifulSoup

# headers字典里要添加cookie键值对，因为此案例抓取需要登录
headers = {
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
    'Cookie': 'll="32144"; bid=3RohyNWVHj0; _pk_id.100001.4cf6=23907e7ebb54271c.1686100051.; __yadk_uid=OGVnwlTfotLSH5XdI6JXtqA5kQsN0x89; _vwo_uuid_v2=D1E8222BE3569A942B9687BFC0D7D966C|59c360096de363c25bd7c2994af63c64; __gads=ID=0902d3edd87ac6ff-222ef5a967e2003d:T=1688109672:RT=1688109672:S=ALNI_MaZQ_lI9mzmEI5AhRb_5LLQVCGQBA; __gpi=UID=00000c7cae331650:T=1688109672:RT=1688109672:S=ALNI_MaqXeTvGSxmShelBp8foNJqyq8o4g; __utmv=30149280.25330; __utmc=30149280; __utmc=223695111; dbcl2="253305871:w8B2qq3cOOA"; ck=PU0Q; __utmz=30149280.1705207739.16._pk_ref.100001.4cf6=%5B%22%22%2C%22%22%2C1705215531%2C%22https%3A%2F%2Faccounts.douban.com%2F%22%5D; _pk_ses.100001.4cf6=1; __utma=30149280.522421068.1686100051.1705207739.1705215531.17; __utmb=30149280.0.10.1705215531; __utma=223695111.711123561.1686100051.1705207739.1705215531.14; __utmb=223695111.0.10.1705215531'
}
# 第一页的影评网址
url = 'https://movie.douban.com/review/best/?start=0'
# 请求页面，获取页面响应
res = requests.get(url, headers=headers)
res.encoding = res.apparent_encoding
# 解码页面内容并赋值给变量data
data = res.content.decode()

# 解析字符串格式的HTML文档对象为_Element对象
tree = etree.HTML(data)
# 用xpath匹配所有的class属性值为"main-bd"的标签
reivew_lst = tree.xpath('//div[@class="review-list chart "]//div[@class="main-bd"]')

# 遍历所有的影评div，然后再分别匹配标题title,短评，完整评论
for review in reivew_lst:
  	# 匹配标题
    title = review.xpath('./h2/a/text()')
    # 匹配短评
    short_content = review.xpath('.//div[@class="short-content"]/text()')
    print('标题：', title[0].strip())
    print('评论内容：', ''.join(short_content).strip('()').strip().strip('()').strip())
		
    # 匹配影评data-id，因为点击页面的展开加载完整评论，属于异步加载，需要单独请求完整评论的url
    data_id = review.xpath('./div[1]/@data-rid')
    # 获取完整影评的data-id并构造完整评论url
    full_review_url = f'https://movie.douban.com/j/review/{data_id[0]}/full'
    res = requests.get(full_review_url, headers=headers)
    res.encoding = res.apparent_encoding
    print('完整评论：')
    # 响应值为json格式，取字典的'html'的键的值
    full_content = res.json()['html']
    # 用BeautifulSoup解析成lxml
    soup = BeautifulSoup(full_content, 'lxml')
    # 获取所有的p标签
    p_lst = soup.find_all('p')
    # 遍历p标签，然后获取text文本
    for p in p_lst:
        print(p.get_text().strip(),end='')
    print()
    # 打印分割线
    print('~ ' * 70)