Python爬虫

最新推荐文章于 2024-06-21 21:57:46 发布

zy20221209

最新推荐文章于 2024-06-21 21:57:46 发布

阅读量942

点赞数 10

文章标签： python 爬虫

本文链接：https://blog.csdn.net/zy20221209/article/details/136274665

版权

#按F12在浏览器中查看
"User-Agent":"浏览器的User-Agent",
"Cookie": "浏览器的Cookie",
"Referer": "浏览器的Referer"

# 导入数据请求模块
import requests
# 导入正则表达式模块
import re
import json
from bs4 import BeautifulSoup
def ask(url):
    # 模拟浏览器
    headers = {
    #按F12在浏览器中查看
        "User-Agent":"浏览器的User-Agent",
        "Cookie": "浏览器的Cookie",
        "Referer": "浏览器的Referer"
    }
    # 发送请求
    response = requests.get(url=url, headers=headers)
    # 获取服务器返回相应文本数据
    html = response.text
    # json字符串数据转成json字典数据
    json_data = json.loads(html)
    return json_data    
def ask1(url):
    # 模拟浏览器
    headers = {
    #按F12在浏览器中查看
        "User-Agent":"浏览器的User-Agent",
        "Cookie": "浏览器的Cookie",
        "Referer": "浏览器的Referer"
    }
    # 发送请求
    response = requests.get(url=url, headers=headers)
    # 获取服务器返回相应文本数据
    html = response.text
    return html

# 请求链接
url ="想要爬取的b站up视频主页链接"
json_data = ask(url)
j = 0
for i in range(30):
    # 提取视频标题
    title = json_data['data']['list']['vlist'][i]['title']
    # 提取视频bv号
    bv = json_data['data']['list']['vlist'][i]['bvid']
    print(title)
    print(bv)
    bl_url = "https://www.bilibili.com/"
    v_url = bl_url+bv

    # 发起网络请求，获取服务器响应的页面内容
    response = requests.get(v_url, timeout=30, headers=headers)
    content = response.text  # 获取响应的文本内容
    soup = BeautifulSoup(content, "html.parser")
    text = soup.find_all(
        "meta", attrs={"data-vue-meta": "true", "itemprop": "description"})

    text_str = str(text)

    # 根据逗号分隔文本内容，得到一个列表
    text_list = text_str.split(',')

    # 在列表中找到包含"视频播放量"信息的元素
    play_count_info = [item for item in text_list if '视频播放量' in item]
    print(play_count_info)