Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/imgur.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urlparse
   7 from ..utils import (
   8     int_or_none,
   9     js_to_json,
  10     mimetype2ext,
  11     ExtractorError,
  12 )
  13
  14
  15 class ImgurIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P<id>[a-zA-Z0-9]+)'
  17
  18     _TESTS = [{
  19         'url': 'https://i.imgur.com/A61SaA1.gifv',
  20         'info_dict': {
  21             'id': 'A61SaA1',
  22             'ext': 'mp4',
  23             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
  24             'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
  25         },
  26     }, {
  27         'url': 'https://imgur.com/A61SaA1',
  28         'info_dict': {
  29             'id': 'A61SaA1',
  30             'ext': 'mp4',
  31             'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
  32             'description': 're:The origin of the Internet\'s most viral images$|The Internet\'s visual storytelling community\. Explore, share, and discuss the best visual stories the Internet has to offer\.$',
  33         },
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38         webpage = self._download_webpage(
  39             compat_urlparse.urljoin(url, video_id), video_id)
  40
  41         width = int_or_none(self._search_regex(
  42             r'<param name="width" value="([0-9]+)"',
  43             webpage, 'width', fatal=False))
  44         height = int_or_none(self._search_regex(
  45             r'<param name="height" value="([0-9]+)"',
  46             webpage, 'height', fatal=False))
  47
  48         video_elements = self._search_regex(
  49             r'(?s)<div class="video-elements">(.*?)</div>',
  50             webpage, 'video elements', default=None)
  51         if not video_elements:
  52             raise ExtractorError(
  53                 'No sources found for video %s. Maybe an image?' % video_id,
  54                 expected=True)
  55
  56         formats = []
  57         for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements):
  58             formats.append({
  59                 'format_id': m.group('type').partition('/')[2],
  60                 'url': self._proto_relative_url(m.group('src')),
  61                 'ext': mimetype2ext(m.group('type')),
  62                 'acodec': 'none',
  63                 'width': width,
  64                 'height': height,
  65                 'http_headers': {
  66                     'User-Agent': 'youtube-dl (like wget)',
  67                 },
  68             })
  69
  70         gif_json = self._search_regex(
  71             r'(?s)var\s+videoItem\s*=\s*(\{.*?\})',
  72             webpage, 'GIF code', fatal=False)
  73         if gif_json:
  74             gifd = self._parse_json(
  75                 gif_json, video_id, transform_source=js_to_json)
  76             formats.append({
  77                 'format_id': 'gif',
  78                 'preference': -10,
  79                 'width': width,
  80                 'height': height,
  81                 'ext': 'gif',
  82                 'acodec': 'none',
  83                 'vcodec': 'gif',
  84                 'container': 'gif',
  85                 'url': self._proto_relative_url(gifd['gifUrl']),
  86                 'filesize': gifd.get('size'),
  87                 'http_headers': {
  88                     'User-Agent': 'youtube-dl (like wget)',
  89                 },
  90             })
  91
  92         self._sort_formats(formats)
  93
  94         return {
  95             'id': video_id,
  96             'formats': formats,
  97             'description': self._og_search_description(webpage),
  98             'title': self._og_search_title(webpage),
  99         }
 100
 101
 102 class ImgurAlbumIE(InfoExtractor):
 103     _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P<id>[a-zA-Z0-9]+)'
 104
 105     _TEST = {
 106         'url': 'http://imgur.com/gallery/Q95ko',
 107         'info_dict': {
 108             'id': 'Q95ko',
 109         },
 110         'playlist_count': 25,
 111     }
 112
 113     def _real_extract(self, url):
 114         album_id = self._match_id(url)
 115
 116         album_images = self._download_json(
 117             'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id,
 118             album_id)['data']['images']
 119
 120         entries = [
 121             self.url_result('http://imgur.com/%s' % image['hash'])
 122             for image in album_images if image.get('hash')]
 123
 124         return self.playlist_result(entries, album_id)