Python爬虫入门教程：下载企鹅动漫视频

好看的动漫当然要一口气看完，但是他又有广告，为了节约时间，我直接就把它们爬下来了~

image

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,如有问题请及时联系我们以作处理。

基本开发环境

• Python 3.8

• Pycharm

相关模块的使用

• import requests

• import re

安装Python并添加到环境变量，pip安装需要的相关模块即可。

需求数据来源分析

image

其实深圳腾家的视频还是比较好下载的，就是m3u8的视频格式而已，和之前爬取A站视频是一样的。

image image.png image

通过开发者工具这些数据内容都是可以一一抓包分析出来的，不过需要注意的是post请求的。

image.png image.png

如果想要爬取多个视频的呀，他的参数主要变化的是url地址，每一集的url地址。

image.png

是通过URL编码的，通过解码可以发现其实就url地址的变化就可以爬取多个视频内容了。

代码实现

import requests
import re
from tqdm import tqdm
url = 'https://vd.l.qq.com/proxyhttp'
data = {"buid":"vinfoad","adparam":"pf=in&ad_type=LD%7CKB%7CPVL&pf_ex=pc&url=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fm441e3rjq9kwpsc.html&refer=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fm441e3rjq9kwpsc.html&ty=web&plugin=1.0.0&v=3.5.57&coverid=m441e3rjq9kwpsc&vid=m00253deqqo&pt=&flowid=6ee7a12b36edccc1298ca3c4a1279361_10201&vptag=www_baidu_com%7Cx&pu=2&chid=0&adaptor=2&dtype=1&live=0&resp_type=json&guid=4b4e192e83f4abaf8b68df3e4f5be769&req_type=1&from=0&appversion=1.0.166&uid=522810848&tkn=PZiKadvwBqjt1VRYEWFcLw..&lt=qq&platform=10201&opid=5FE180427A4C883F69CADDED665CE99B&atkn=49C1A486316C8D269AC65AAC080CFB29&appid=101483052&tpid=3","vinfoparam":"spsrt=1&charge=0&defaultfmt=auto&otype=ojson&guid=4b4e192e83f4abaf8b68df3e4f5be769&flowid=6ee7a12b36edccc1298ca3c4a1279361_10201&platform=10201&sdtfrom=v1010&defnpayver=1&appVer=3.5.57&host=v.qq.com&ehost=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fm441e3rjq9kwpsc.html&refer=v.qq.com&sphttps=1&tm=1633760593&spwm=4&logintoken=%7B%22main_login%22%3A%22qq%22%2C%22openid%22%3A%225FE180427A4C883F69CADDED665CE99B%22%2C%22appid%22%3A%22101483052%22%2C%22access_token%22%3A%2249C1A486316C8D269AC65AAC080CFB29%22%2C%22vuserid%22%3A%22522810848%22%2C%22vusession%22%3A%22PZiKadvwBqjt1VRYEWFcLw..%22%7D&vid=m00253deqqo&defn=&fhdswitch=0&show1080p=1&isHLS=1&dtype=3&sphls=2&spgzip=1&dlver=2&drm=32&hdcp=0&spau=1&spaudio=15&defsrc=1&encryptVer=9.1&cKey=5DdFIhZoCTh6L5EItZs_lpJX5WB4a2CdS8kEIuoKVaqtHEZQ1c_W6myJ8hQAnmDDGMN6HtSKNTvj2vPBr-xE-uhvZyEMY131vUh1H4pgCXe2Op9Lrzb_fbB32kFt6bl1q30sVBkIXYfWkOdABnbLUo4RgzSXkBHF3N3K7dNKPg_56X9JO3gwBMyBeAex05x8SbbQKY5AXaDVSM7hsBQ8XEeHzIEGJzlCt94OJgnPQjUjJKF82JUds1R0-cHhfOLSlSKkRfXJvCgPorVuLVB8vGkZ9SUNglJgQYGpVikdTUgXRIOHHObmqSLLKn4jYCmTQKXhvP_ARCxg07_d7CuHkmkZ3RplMNDtdQRyXVHoQHKn5vzNKGxIiW5AhdIEBAQEW_tymg&fp2p=1&spadseg=3"}
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36'
}
response = requests.post(url=url, json=data, headers=headers)
html_data = response.json()['vinfo']
m3u8_url = re.findall("url(.*?),", html_data)[3].split('"')[2]
m3u8_data = requests.get(url=m3u8_url).text
m3u8_data = re.sub('#EXTM3U', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-VERSION:\d', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-MEDIA-SEQUENCE:\d', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-TARGETDURATION:\d+', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-PLAYLIST-TYPE:VOD', '', m3u8_data)
m3u8_data = re.sub('#EXTINF:\d+\.\d+,', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-ENDLIST', '', m3u8_data).split()
for ts in tqdm(m3u8_data):
    ts_url = 'https://apd-565555bc66fc61b759c9b3d174974007.v.smtcdns.com/moviets.tc.qq.com/AljnQkp9aX_s0xghcGyUDvSrsDw-60Juazgu71dVgpw8/uwMROfz2r5xgoaQXGdGnC2df645GziNP4fCTXzcc9dfItw5M/MwE4f2JnwaJD4DIrFImz_B51hCanEvH3_a3pTvopgHoqDuCXu22oHCXO-_aZh79YTmXQ-8fQX66xUs9NEzpkLfyLY5Wbes8W1mnPl983JuGgWWPVLlyh-76C2rGHa1COTMDOMc58Y6-fWzZkbfboxyd3NUyMe6tpaPBkhz2gFABB1Vjqii_6nQ/' + ts
    ts_content = requests.get(url=ts_url).content
    with open('斗罗001.mp4', mode='ab') as f:
        f.write(ts_content)
print('下载完成')

image.png image