当前位置：首页 > article >正文

python爬虫：实例讲解xpatch的基本使用

article 2024/10/26 22:25:37

在这个指南中，我们将学习如何使用Python的requests库来获取豆瓣电影分类排行榜中的爱情片数据，并进行初步分析。

1. 准备工作

首先，确保你已经安装了requests库。如果还没有安装，可以通过以下命令安装：

pip install requests

2. 发送请求获取数据

我们将使用requests库发送GET请求，获取豆瓣电影爱情片分类排行榜的数据。

import requests

# 请求的URL
url = "https://movie.douban.com/j/chart/top_list"

# 请求参数
my_params = {
    "type": "13",
    "interval_id": "100:90",
    "action": "",
    "start": "40",
    "limit": "20"
}

# 请求头
my_headers = {
    "Accept": "*/*",
    "Accept-Encoding": "gzip, deflate, br, zstd",
    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
    "Cache-Control": "no-cache",
    "Cookie": "_vwo_uuid_v2=D3880B2832E1DE94F2A4502388A6A4E8B|e66576862b2f0dabf793c79d46a0290b; douban-fav-remind=1; viewed=\"4828875\"; __utmz=30149280.1698314015.14.4.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utmz=223695111.1703160048.16.5.utmcsr=douban.com|utmccn=(referral)|utmcmd=referral|utmcct=/; bid=-HJeSGBZHSU; __yadk_uid=WminjqLK6idTP5Xmjyv7wom1JaU8PFDi; _pk_id.100001.4cf6=53b5e927c166163d.1715081880.; ll=\"108288\"; __gads=ID=af178901fae12160:T=1712663043:RT=1715862135:S=ALNI_MYzZ6mtwK7gICaEbskfbzrYc6H0wQ; __gpi=UID=00000de53fef4b9c:T=1712663043:RT=1715862135:S=ALNI_MYGyX8gzJU7sGryLj_Gu_tcGfZDFQ; __eoi=ID=c4f6a35514ed0bbd:T=1712663043:RT=1715862135:S=AA-AfjZpBBf1Co3P0tc0zM3H0bzx; __utmc=30149280; __utmc=223695111; ap_v=0,6.0; __utma=30149280.362504383.1679923907.1721649760.1721653343.58; __utmb=30149280.0.10.1721653343; __utma=223695111.1024054339.1679923907.1721649760.1721653343.55; __utmb=223695111.0.10.1721653343; _pk_ref.100001.4cf6=%5B%22%22%2C%22%22%2C1721653343%2C%22https%3A%2F%2Fwww.douban.com%2F%22%5D; _pk_ses.100001.4cf6=1",
    "Dnt": "1",
    "Pragma": "no-cache",
    "Priority": "u=1, i",
    "Referer": "https://movie.douban.com/typerank?type_name=%E7%88%B1%E6%83%85&type=13&interval_id=100:90&action=&#34;",
    "Sec-Ch-Ua": "\"Not/A)Brand\";v=\"8\", \"Chromium\";v=\"126\", \"Google Chrome\";v=\"126\"",
    "Sec-Ch-Ua-Mobile": "?0",
    "Sec-Ch-Ua-Platform": "\"Windows\"",
    "Sec-Fetch-Dest": "empty",
    "Sec-Fetch-Mode": "cors",
    "Sec-Fetch-Site": "same-origin",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
    "X-Requested-With": "XMLHttpRequest"
}

# 发送GET请求
resp = requests.get(url, params=my_params, headers=my_headers)
print(resp.text)  # 打印响应文本
print(resp.json())  # 将响应内容解析为JSON