Python爬取梨视频的示例

video_url = tree.xpath("//div[@id='JprismPlayer']/video/@src")

{
	"resultCode":"1",
	"resultMsg":"success", "reqId":"fd1c910d-f49a-431a-b9a4-9c193c3c1983",
	"systemTime": "1611666178518",
	"videoInfo":{"playSta":"1","video_image":"https://image1.pearvideo.com/cont/20210125/11107897-184717-1.png","videos":{"hdUrl":"","hdflvUrl":"","sdUrl":"","sdflvUrl":"","srcUrl":"https://video.pearvideo.com/mp4/third/20210125/1611666178518-11107897-181816-hd.mp4"}}
}

# 爬取梨视频

import requests
from lxml import etree
import os
from multiprocessing import Pool

# 梨视频首页url
url = "https://www.pearvideo.com/category_6"
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'
  }

# 获取响应，并用etree解析
response = requests.get(url=url, headers=headers).text
tree = etree.HTML(response)

# 拿到视频的名字和视频号
video_id_list = tree.xpath("//ul[@class='listvideo-list clearfix']/li[@class='categoryem ']//a[@class='vervideo-lilink actplay']/@href")
video_name_list = tree.xpath("//ul[@class='listvideo-list clearfix']/li[@class='categoryem ']//a/div[@class='vervideo-title']/text()")
data_list = [{"name": video_name_list[i], "idNum": video_id_list[i][6:]} for i in range(len(video_name_list))]

# 创建一个存放视频的文件夹
if not os.path.exists("./videos"):
  os.mkdir("./videos")

# 获取视频的函数
def down_video(data):
  name = data['name']
  idNum = data['idNum']

  # 获取视频需要的headers，注意这里的Referer要和视频的id匹配
  headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36',
    'Referer': f'https://www.pearvideo.com/video_{idNum}'
  }
  # 获取接近真正视频url的url，这里的id也需要和视频id匹配才行
  url = f'https://www.pearvideo.com/videoStatus.jsp?contId={idNum}'

  # 得到包含视频地址json响应数据
  response = requests.get(url=url, headers=headers).json()
  video_url = response["videoInfo"]["videos"]["srcUrl"]

  # 将视频地址中的数字替换成 cont-视频编号 拿到真正的视频地址
  video_url = video_url.replace(video_url.split("/")[-1].split("-")[0], "cont-" + idNum)

  # 拿到视频并保存
  video = requests.get(url=video_url, headers=headers).content
  with open(f"./videos/{name}.mp4", "wb") as f:
    print(f"正在下载视频 {name} ...")
    f.write(video)
    print(f"视频 {name} 下载完成！")

if __name__ == '__main__':
  # 创建进程池并使用
  pool = Pool(3)
  pool.map(down_video, data_list)
  pool.close()
  pool.join()