python 抓取知乎指定回答下视频的方法

{
	"playlist": {
		"ld": {
			"width": 360,
			"format": "mp4",
			"play_url": "https://vdn.vzuu.com/LD/05fc411e-d8e0-11e8-bb8b-0242ac112a0b.mp4?auth_key=1541477643-0-0-987c2c504d14ab1165ce2ed47759d927&expiration=1541477643&disable_local_cache=1",
			"duration": 17,
			"size": 1123111,
			"bitrate": 509,
			"height": 640
		},
		"hd": {
			"width": 720,
			"format": "mp4",
			"play_url": "https://vdn.vzuu.com/HD/05fc411e-d8e0-11e8-bb8b-0242ac112a0b.mp4?auth_key=1541477643-0-0-8b8024a22a62f097ca31b8b06b7233a1&expiration=1541477643&disable_local_cache=1",
			"duration": 17,
			"size": 4354364,
			"bitrate": 1974,
			"height": 1280
		},
		"sd": {
			"width": 480,
			"format": "mp4",
			"play_url": "https://vdn.vzuu.com/SD/05fc411e-d8e0-11e8-bb8b-0242ac112a0b.mp4?auth_key=1541477643-0-0-5948c2562d817218c9a9fc41abad1df8&expiration=1541477643&disable_local_cache=1",
			"duration": 17,
			"size": 1920976,
			"bitrate": 871,
			"height": 848
		}
	},
	"title": "",
	"duration": 17,
	"cover_info": {
		"width": 720,
		"thumbnail": "https://pic2.zhimg.com/80/v2-97b9435a0c32d01c7c931bd00120327d_b.jpg",
		"height": 1280
	},
	"type": "video",
	"id": "1039146361396174848",
	"misc_info": {}
}

# -*- encoding: utf-8 -*-

import re
import requests
import uuid
import datetime


class DownloadVideo:

  __slots__ = [
    'url', 'video_name', 'url_format', 'download_url', 'video_number',
    'video_api', 'clarity_list', 'clarity'
  ]

  def __init__(self, url, clarity='ld', video_name=None):
    self.url = url
    self.video_name = video_name
    self.url_format = "https://www.zhihu.com/question/\d+/answer/\d+"
    self.clarity = clarity
    self.clarity_list = ['ld', 'sd', 'hd']
    self.video_api = 'https://lens.zhihu.com/api/videos'

  def check_url_format(self):
    pattern = re.compile(self.url_format)
    matches = re.match(pattern, self.url)
    if matches is None:
      raise ValueError(
        "链接格式应符合:https://www.zhihu.com/question/{number}/answer/{number}"
      )
    return True

  def get_video_number(self):
    try:
      headers = {
        'User-Agent':
        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36'
      }
      response = requests.get(self.url, headers=headers)
      response.encoding = 'utf-8'
      html = response.text
      video_ids = re.findall(r'data-lens-id="(\d+)"', html)
      if video_ids:
        video_id_list = list(set([video_id for video_id in video_ids]))
        self.video_number = video_id_list[0]
        return self
      raise ValueError("获取视频编号异常:{}".format(self.url))
    except Exception as e:
      raise Exception(e)

  def get_video_url_by_number(self):
    url = "{}/{}".format(self.video_api, self.video_number)

    headers = {}
    headers['Referer'] = 'https://v.vzuu.com/video/{}'.format(
      self.video_number)
    headers['Origin'] = 'https://v.vzuu.com'
    headers[
      'User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36'
    headers['Content-Type'] = 'application/json'

    try:
      response = requests.get(url, headers=headers)
      response_dict = response.json()
      if self.clarity in response_dict['playlist']:
        self.download_url = response_dict['playlist'][
          self.clarity]['play_url']
      else:
        for clarity in self.clarity_list:
          if clarity in response_dict['playlist']:
            self.download_url = response_dict['playlist'][
              self.clarity]['play_url']
            break
      return self
    except Exception as e:
      raise Exception(e)

  def get_video_by_video_url(self):
    response = requests.get(self.download_url)
    datetime_str = datetime.datetime.now().strftime("%Y-%m-%d %H-%M-%S")
    if self.video_name is not None:
      video_name = "{}-{}.mp4".format(self.video_name, datetime_str)
    else:
      video_name = "{}-{}.mp4".format(str(uuid.uuid1()), datetime_str)
    path = "{}".format(video_name)
    with open(path, 'wb') as f:
      f.write(response.content)

  def download_video(self):

    if self.clarity not in self.clarity_list:
      raise ValueError("清晰度参数异常,仅支持:ld(普清),sd(标清),hd(高清)")

    if self.check_url_format():
      return self.get_video_number().get_video_url_by_number().get_video_by_video_url()


if __name__ == '__main__':
  a = DownloadVideo('https://www.zhihu.com/question/53031925/answer/524158069')
  print(a.download_video())