爬取梨视频

爬取梨视频

#categoryId=9 分类id
#start=0 从哪个位置开始，每次加载12个
# https://www.pearvideo.com/category_loading.jsp?reqType=5&categoryId=9&start=0

import requests
import re

ret = requests.get('https://www.pearvideo.com/category_loading.jsp?reqType=5&categoryId=3&start=3')
# print(ret.text)
# 正则解析
reg = '<a href="(.*?)" class="vervideo-lilink actplay">'
video_urls = re.findall(reg, ret.text)
print(video_urls)
for url in video_urls:
    ret_detail = requests.get('https://www.pearvideo.com/'+url)
    # print(ret_detail.text)
    # break
    reg = 'srcUrl="(.*?)",vdoUrl=srcUrl'
    mp4_url = re.findall(reg, ret_detail.text)[0]
    # print(mp4_url)
    # break
    # 下载视频
    video_content = requests.get(mp4_url)
    video_name = mp4_url.rsplit('/', 1)[1]
    with open(video_name, 'wb') as f:
        for line in video_content.iter_content():
            f.write(line)