Python爬虫训练：爬取酷燃网视频数据

前言

本文的文字及图片来源于网络,仅供学习、交流使用,不具有任何商业用途,版权归原作者所有,如有问题请及时联系我们以作处理

项目目标

爬取酷燃网视频数据

https://krcom.cn/

环境

Python3.6

pycharm

爬虫代码

import pprint
import requests
import re

def download_video(title, url):
    filename_video = 'C:\\Users\\Administrator\\Desktop\\酷燃网\\' + title + '.mp4'
    response_video = requests.get(url=url)
    with open(filename_video, mode='wb') as f:
        f.write(response_video.content)

def download_mp3(title, url):
    filename_mp3 = 'C:\\Users\\Administrator\\Desktop\\酷燃网\\' + title + '.mp3'
    response_mp3 = requests.get(url=url)
    with open(filename_mp3, mode='wb') as f:
        f.write(response_mp3.content)

for page in range(0, 101, 20):
    url = 'https://krcom.cn/aj/hot/loadingmore?ajwvr=6&cursor=0;2020102014&YmdH=&__rnd=1603176486876'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'
    }
    response = requests.get(url=url, headers=headers)
    html_data = response.text.encode('utf-8').decode('unicode_escape')
    urls = re.findall('vid=(.*?)\"', html_data, re.S)
    titles = re.findall('<h3 class="V_autocut_2l">(.*?)<', html_data, re.S)
    data = zip(urls, titles)
    for i in data:
        vid = i[0]
        title = i[1]
        page_url = 'https://krcom.cn/aj/dash/media?media_ids={}&protocols=dash&watermarks=krcom'.format(vid)
        response_2 = requests.get(url=page_url, headers=headers)
        html_json = response_2.json()
        video_url = html_json['data']['list'][0]['details'][1]['play_info']['url']
        mp3_url = html_json['data']['list'][0]['details'][-1]['play_info']['url']
        download_video(title, video_url)
        download_mp3(title, mp3_url)
        print(title)