Python爬取豆瓣电影TOP250(名字+年份+评分+评论人数)

晚风轻轻_1109

已于 2024-08-16 15:27:33 修改

阅读量695

点赞数 5

分类专栏：爬虫文章标签： python 开发语言爬虫

于 2024-08-16 15:26:09 首次发布

本文链接：https://blog.csdn.net/weixin_50710623/article/details/141261014

版权

爬虫专栏收录该内容

2 篇文章

订阅专栏

import re
import requests
import csv

# 拿到页面源代码
url = "https://movie.douban.com/top250"

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36'
}
params = {
    'start': 0,
    'filter': ''
}
lib = {}
# 爬取后面的页数
for i in range(0, 10):
    params['start'] = i * 25

    resp = requests.get(url, headers=headers, params=params)
    page_content = resp.text

    # 开始解析
    obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<name>.*?)'
                     r'</span>.*?<p class="">.*?<br>(?P<year>.*?)&nbsp.*?'
                     r'<span class="rating_num" property="v:average">(?P<print>.*?)</span>'
                     r'.*?<span>(?P<people>.*?)</span>', re.S)
    result = obj.finditer(page_content)
    # 将每次的结果都放到一个新的字典中
    for i in result:
        lib[i] = i.groupdict()


f = open("douban.csv", "w", encoding="utf-8")
writer = csv.writer(f)
for i in lib:
    # print("名字："+i.group('name')+" 年份："+i.group('year').strip()+" 评分："+i.group('print')+" 评价数："+i.group('people'))
    dic = i.groupdict()
    dic['year'] = dic['year'].strip()
    writer.writerow(dic.values())

f.close()
resp.close()
print("200")