X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Finstagram.py;h=98f408c18650cf8393869432a861a3486575b533;hb=ec85ded83cbfa652ba94cb080aab52d8b270212a;hp=fc0197ae19d2c3db4a504268256400d6ef81702d;hpb=98960c911c9bacc0c366dd11b194963a82606850;p=youtube-dl diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index fc0197ae1..98f408c18 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -22,13 +22,14 @@ class InstagramIE(InfoExtractor): 'ext': 'mp4', 'title': 'Video by naomipq', 'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'timestamp': 1371748545, 'upload_date': '20130620', 'uploader_id': 'naomipq', 'uploader': 'Naomi Leonor Phan-Quang', 'like_count': int, 'comment_count': int, + 'comments': list, }, }, { # missing description @@ -36,15 +37,15 @@ class InstagramIE(InfoExtractor): 'info_dict': { 'id': 'BA-pQFBG8HZ', 'ext': 'mp4', - 'uploader_id': 'britneyspears', 'title': 'Video by britneyspears', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'timestamp': 1453760977, 'upload_date': '20160125', 'uploader_id': 'britneyspears', 'uploader': 'Britney Spears', 'like_count': int, 'comment_count': int, + 'comments': list, }, 'params': { 'skip_download': True, @@ -83,7 +84,7 @@ class InstagramIE(InfoExtractor): webpage = self._download_webpage(url, video_id) (video_url, description, thumbnail, timestamp, uploader, - uploader_id, like_count, comment_count) = [None] * 8 + uploader_id, like_count, comment_count, height, width) = [None] * 10 shared_data = self._parse_json( self._search_regex( @@ -95,6 +96,8 @@ class InstagramIE(InfoExtractor): shared_data, lambda x: x['entry_data']['PostPage'][0]['media'], dict) if media: video_url = media.get('video_url') + height = int_or_none(media.get('dimensions', {}).get('height')) + width = int_or_none(media.get('dimensions', {}).get('width')) description = media.get('caption') thumbnail = media.get('display_src') timestamp = int_or_none(media.get('date')) @@ -102,10 +105,24 @@ class InstagramIE(InfoExtractor): uploader_id = media.get('owner', {}).get('username') like_count = int_or_none(media.get('likes', {}).get('count')) comment_count = int_or_none(media.get('comments', {}).get('count')) + comments = [{ + 'author': comment.get('user', {}).get('username'), + 'author_id': comment.get('user', {}).get('id'), + 'id': comment.get('id'), + 'text': comment.get('text'), + 'timestamp': int_or_none(comment.get('created_at')), + } for comment in media.get( + 'comments', {}).get('nodes', []) if comment.get('text')] if not video_url: video_url = self._og_search_video_url(webpage, secure=False) + formats = [{ + 'url': video_url, + 'width': width, + 'height': height, + }] + if not uploader_id: uploader_id = self._search_regex( r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"', @@ -122,7 +139,7 @@ class InstagramIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, + 'formats': formats, 'ext': 'mp4', 'title': 'Video by %s' % uploader_id, 'description': description, @@ -132,6 +149,7 @@ class InstagramIE(InfoExtractor): 'uploader': uploader, 'like_count': like_count, 'comment_count': comment_count, + 'comments': comments, } @@ -151,7 +169,7 @@ class InstagramUserIE(InfoExtractor): 'id': '614605558512799803_462752227', 'ext': 'mp4', 'title': '#Porsche Intelligent Performance.', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'uploader': 'Porsche', 'uploader_id': 'porsche', 'timestamp': 1387486713,