yt_dlp/extractor/snapchat.py

   1 from .common import InfoExtractor
   2 from ..utils import float_or_none, int_or_none, url_or_none
   3 from ..utils.traversal import traverse_obj
   4
   5
   6 class SnapchatSpotlightIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?snapchat\.com/spotlight/(?P<id>\w+)'
   8
   9     _TESTS = [{
  10         'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA',
  11         'md5': '46c580f63592d0cbb76e974d2f9f0fcc',
  12         'info_dict': {
  13             'id': 'W7_EDlXWTBiXAEEniNoMPwAAYYWtidGhudGZpAX1TKn0JAX1TKnXJAAAAAA',
  14             'ext': 'mp4',
  15             'title': 'Views 💕',
  16             'description': '',
  17             'thumbnail': r're:https://cf-st\.sc-cdn\.net/d/kKJHIR1QAznRKK9jgYYDq\.256\.IRZXSOY',
  18             'duration': 4.665,
  19             'timestamp': 1637777831.369,
  20             'upload_date': '20211124',
  21             'repost_count': int,
  22             'uploader': 'shreypatel57',
  23             'uploader_url': 'https://www.snapchat.com/add/shreypatel57',
  24         },
  25     }, {
  26         'url': 'https://www.snapchat.com/spotlight/W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ',
  27         'md5': '4cd9626458c1a0e3e6dbe72c544a9ec2',
  28         'info_dict': {
  29             'id': 'W7_EDlXWTBiXAEEniNoMPwAAYcnVjYWdwcGV1AZEaIYn5AZEaIYnrAAAAAQ',
  30             'ext': 'mp4',
  31             'title': 'Spotlight Snap',
  32             'description': 'How he flirt her teacher🤭🤭🤩😍 #kdrama#cdrama #dramaclips #dramaspotlight',
  33             'thumbnail': r're:https://cf-st\.sc-cdn\.net/i/ztfr6xFs0FOcFhwVczWfj\.256\.IRZXSOY',
  34             'duration': 10.91,
  35             'timestamp': 1722720291.307,
  36             'upload_date': '20240803',
  37             'view_count': int,
  38             'repost_count': int,
  39             'uploader': 'ganda0535',
  40             'uploader_url': 'https://www.snapchat.com/add/ganda0535',
  41             'tags': ['#dramaspotlight', '#dramaclips', '#cdrama', '#kdrama'],
  42         },
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47         webpage = self._download_webpage(url, video_id)
  48         page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
  49         video_data = traverse_obj(page_props, (
  50             'spotlightFeed', 'spotlightStories',
  51             lambda _, v: v['story']['storyId']['value'] == video_id, 'metadata', any), None)
  52
  53         return {
  54             'id': video_id,
  55             'ext': 'mp4',
  56             **traverse_obj(video_data, ('videoMetadata', {
  57                 'title': ('name', {str}),
  58                 'description': ('description', {str}),
  59                 'timestamp': ('uploadDateMs', {lambda x: float_or_none(x, 1000)}),
  60                 'view_count': ('viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
  61                 'repost_count': ('shareCount', {int_or_none}),
  62                 'url': ('contentUrl', {url_or_none}),
  63                 'width': ('width', {int_or_none}),
  64                 'height': ('height', {int_or_none}),
  65                 'duration': ('durationMs', {lambda x: float_or_none(x, 1000)}),
  66                 'thumbnail': ('thumbnailUrl', {url_or_none}),
  67                 'uploader': ('creator', 'personCreator', 'username', {str}),
  68                 'uploader_url': ('creator', 'personCreator', 'url', {url_or_none}),
  69             })),
  70             **traverse_obj(video_data, {
  71                 'description': ('description', {str}),
  72                 'tags': ('hashtags', ..., {str}),
  73                 'view_count': ('engagementStats', 'viewCount', {int_or_none}, {lambda x: None if x == -1 else x}),
  74                 'repost_count': ('engagementStats', 'shareCount', {int_or_none}),
  75             }),
  76         }