_ Git - youtube-dl/blob - youtube_dl/extractor/tiktok.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_str,
   7     int_or_none,
   8     str_or_none,
   9     try_get,
  10     url_or_none,
  11 )
  12
  13
  14 class TikTokIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:m\.)?tiktok\.com/v/(?P<id>[0-9]+)'
  16     _TEST = {
  17         'url': 'https://m.tiktok.com/v/6606727368545406213.html',
  18         'md5': 'd584b572e92fcd48888051f238022420',
  19         'info_dict': {
  20             'id': '6606727368545406213',
  21             'ext': 'mp4',
  22             'title': 'Zureeal on TikTok',
  23             'thumbnail': r're:^https?://.*~noop.image',
  24             'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
  25             'uploader': 'Zureeal',
  26             'width': 540,
  27             'height': 960,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34
  35         data = self._parse_json(
  36             self._search_regex(
  37                 r'var\s+data\s*=\s*({.+?});', webpage, 'data'
  38             ), video_id)
  39
  40         title = self._og_search_title(webpage)
  41
  42         description = str_or_none(try_get(data, lambda x: x['desc']))
  43         width = int_or_none(try_get(data, lambda x: x['video']['width']))
  44         height = int_or_none(try_get(data, lambda x: x['video']['height']))
  45
  46         formats = []
  47
  48         for count, (key, label) in enumerate((('play_addr_lowbr', 'Low'), ('play_addr', 'Normal'), ('download_addr', 'Download')), -2):
  49             for format in try_get(data, lambda x: x['video'][key]['url_list']):
  50                 format_url = url_or_none(format)
  51                 if not format_url:
  52                     continue
  53                 formats.append({
  54                     'url': format_url,
  55                     'ext': 'mp4',
  56                     'height': height,
  57                     'width': width,
  58                     'format_note': label,
  59                     'quality': count
  60                 })
  61
  62         self._sort_formats(formats)
  63
  64         uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
  65
  66         thumbnail = url_or_none(
  67             try_get(
  68                 data, lambda x: x['video']['cover']['url_list'][0], compat_str))
  69
  70         return {
  71             'id': video_id,
  72             'title': title,
  73             'description': description,
  74             'uploader': uploader,
  75             'formats': formats,
  76             'thumbnail': thumbnail,
  77             'width': width,
  78             'height': height,
  79         }