From 3baa62e8d1aa98bdb42ddf91e8b139d2dd36ff9e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 2 Sep 2014 20:54:00 +0700 Subject: [PATCH] [beeg] Extract all formats --- youtube_dl/extractor/beeg.py | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index d7301fe18..314e37f8b 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -27,8 +27,16 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) - video_url = self._html_search_regex( - r"'480p'\s*:\s*'([^']+)'", webpage, 'video URL') + quality_arr = self._search_regex( + r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats') + + formats = [{ + 'url': fmt[1], + 'format_id': fmt[0], + 'height': int(fmt[0][:-1]), + } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)] + + self._sort_formats(formats) title = self._html_search_regex( r'([^<]+)\s*-\s*beeg\.?', webpage, 'title') @@ -48,10 +56,10 @@ def _real_extract(self, url): return { 'id': video_id, - 'url': video_url, 'title': title, 'description': description, 'thumbnail': thumbnail, 'categories': categories, + 'formats': formats, 'age_limit': 18, }