From bf4b3b6bd91137b94d5ae8ac6dc421e64a647355 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 23 Feb 2016 18:47:13 +0600 Subject: [PATCH] [vk] Extract video URL from extra_data (Closes #8646) --- youtube_dl/extractor/vk.py | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 0805e3c08..670a438af 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -11,6 +11,7 @@ ) from ..utils import ( ExtractorError, + int_or_none, orderedSet, sanitized_Request, str_to_int, @@ -151,6 +152,19 @@ class VKIE(InfoExtractor): 'view_count': int, }, }, + { + # video key is extra_data not url\d+ + 'url': 'http://vk.com/video-110305615_171782105', + 'md5': 'e13fcda136f99764872e739d13fac1d1', + 'info_dict': { + 'id': '171782105', + 'ext': 'mp4', + 'title': 'S-Dance, репетиции к The way show', + 'uploader': 'THE WAY SHOW | 17 апреля', + 'upload_date': '20160207', + 'view_count': int, + }, + }, { # removed video, just testing that we match the pattern 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', @@ -298,12 +312,17 @@ def _real_extract(self, url): view_count = str_to_int(self._search_regex( r'([\d,.]+)', views, 'view count', fatal=False)) - formats = [{ - 'format_id': k, - 'url': v, - 'width': int(k[len('url'):]), - } for k, v in data.items() - if k.startswith('url')] + formats = [] + for k, v in data.items(): + if not k.startswith('url') and k != 'extra_data' or not v: + continue + height = int_or_none(self._search_regex( + r'^url(\d+)', k, 'height', default=None)) + formats.append({ + 'format_id': k, + 'url': v, + 'height': height, + }) self._sort_formats(formats) return {