yt_dlp/extractor/ninegag.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     determine_ext,
   5     int_or_none,
   6     traverse_obj,
   7     unescapeHTML,
   8     url_or_none,
   9 )
  10
  11
  12 class NineGagIE(InfoExtractor):
  13     IE_NAME = '9gag'
  14     IE_DESC = '9GAG'
  15     _VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
  16
  17     _TESTS = [{
  18         'url': 'https://9gag.com/gag/ae5Ag7B',
  19         'info_dict': {
  20             'id': 'ae5Ag7B',
  21             'ext': 'webm',
  22             'title': 'Capybara Agility Training',
  23             'upload_date': '20191108',
  24             'timestamp': 1573237208,
  25             'thumbnail': 'https://img-9gag-fun.9cache.com/photo/ae5Ag7B_460s.jpg',
  26             'categories': ['Awesome'],
  27             'tags': ['Awesome'],
  28             'duration': 44,
  29             'like_count': int,
  30             'dislike_count': int,
  31             'comment_count': int,
  32         },
  33     }, {
  34         # HTML escaped title
  35         'url': 'https://9gag.com/gag/av5nvyb',
  36         'only_matching': True,
  37     }, {
  38         # Non Anonymous Uploader
  39         'url': 'https://9gag.com/gag/ajgp66G',
  40         'info_dict': {
  41             'id': 'ajgp66G',
  42             'ext': 'webm',
  43             'title': 'Master Shifu! Or Splinter! You decide:',
  44             'upload_date': '20220806',
  45             'timestamp': 1659803411,
  46             'thumbnail': 'https://img-9gag-fun.9cache.com/photo/ajgp66G_460s.jpg',
  47             'categories': ['Funny'],
  48             'tags': ['Funny'],
  49             'duration': 26,
  50             'like_count': int,
  51             'dislike_count': int,
  52             'comment_count': int,
  53             'uploader': 'Peter Klaus',
  54             'uploader_id': 'peterklaus12',
  55             'uploader_url': 'https://9gag.com/u/peterklaus12',
  56         },
  57     }]
  58
  59     def _real_extract(self, url):
  60         post_id = self._match_id(url)
  61         post = self._download_json(
  62             'https://9gag.com/v1/post', post_id, query={
  63                 'id': post_id,
  64             })['data']['post']
  65
  66         if post.get('type') != 'Animated':
  67             raise ExtractorError(
  68                 'The given url does not contain a video',
  69                 expected=True)
  70
  71         duration = None
  72         formats = []
  73         thumbnails = []
  74         for key, image in (post.get('images') or {}).items():
  75             image_url = url_or_none(image.get('url'))
  76             if not image_url:
  77                 continue
  78             ext = determine_ext(image_url)
  79             image_id = key.strip('image')
  80             common = {
  81                 'url': image_url,
  82                 'width': int_or_none(image.get('width')),
  83                 'height': int_or_none(image.get('height')),
  84             }
  85             if ext in ('jpg', 'png'):
  86                 webp_url = image.get('webpUrl')
  87                 if webp_url:
  88                     t = common.copy()
  89                     t.update({
  90                         'id': image_id + '-webp',
  91                         'url': webp_url,
  92                     })
  93                     thumbnails.append(t)
  94                 common.update({
  95                     'id': image_id,
  96                     'ext': ext,
  97                 })
  98                 thumbnails.append(common)
  99             elif ext in ('webm', 'mp4'):
 100                 if not duration:
 101                     duration = int_or_none(image.get('duration'))
 102                 common['acodec'] = 'none' if image.get('hasAudio') == 0 else None
 103                 for vcodec in ('vp8', 'vp9', 'h265'):
 104                     c_url = image.get(vcodec + 'Url')
 105                     if not c_url:
 106                         continue
 107                     c_f = common.copy()
 108                     c_f.update({
 109                         'format_id': image_id + '-' + vcodec,
 110                         'url': c_url,
 111                         'vcodec': vcodec,
 112                     })
 113                     formats.append(c_f)
 114                 common.update({
 115                     'ext': ext,
 116                     'format_id': image_id,
 117                 })
 118                 formats.append(common)
 119
 120         section = traverse_obj(post, ('postSection', 'name'))
 121
 122         tags = None
 123         post_tags = post.get('tags')
 124         if post_tags:
 125             tags = []
 126             for tag in post_tags:
 127                 tag_key = tag.get('key')
 128                 if not tag_key:
 129                     continue
 130                 tags.append(tag_key)
 131
 132         return {
 133             'id': post_id,
 134             'title': unescapeHTML(post.get('title')),
 135             'timestamp': int_or_none(post.get('creationTs')),
 136             'duration': duration,
 137             'uploader': traverse_obj(post, ('creator', 'fullName')),
 138             'uploader_id': traverse_obj(post, ('creator', 'username')),
 139             'uploader_url': url_or_none(traverse_obj(post, ('creator', 'profileUrl'))),
 140             'formats': formats,
 141             'thumbnails': thumbnails,
 142             'like_count': int_or_none(post.get('upVoteCount')),
 143             'dislike_count': int_or_none(post.get('downVoteCount')),
 144             'comment_count': int_or_none(post.get('commentsCount')),
 145             'age_limit': 18 if post.get('nsfw') == 1 else None,
 146             'categories': [section] if section else None,
 147             'tags': tags,
 148         }