From 70851a95c307880f016fcb6f37427a8eeae73cad Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 12 Aug 2017 17:18:23 +0700 Subject: [PATCH] [aparat] Extract all formats (closes #13887) --- youtube_dl/extractor/aparat.py | 49 +++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 025e29aa4..e394cb661 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -3,13 +3,13 @@ from .common import InfoExtractor from ..utils import ( - ExtractorError, - HEADRequest, + int_or_none, + mimetype2ext, ) class AparatIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P[a-zA-Z0-9]+)' _TEST = { 'url': 'http://www.aparat.com/v/wP8On', @@ -29,30 +29,41 @@ def _real_extract(self, url): # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id # but the URL in there does not work - embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id - webpage = self._download_webpage(embed_url, video_id) - - file_list = self._parse_json(self._search_regex( - r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id) - for i, item in enumerate(file_list[0]): - video_url = item['file'] - req = HEADRequest(video_url) - res = self._request_webpage( - req, video_id, note='Testing video URL %d' % i, errnote=False) - if res: - break - else: - raise ExtractorError('No working video URLs found') + webpage = self._download_webpage( + 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id, + video_id) title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title') + + file_list = self._parse_json( + self._search_regex( + r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, + 'file list'), + video_id) + + formats = [] + for item in file_list[0]: + file_url = item.get('file') + if not file_url: + continue + ext = mimetype2ext(item.get('type')) + label = item.get('label') + formats.append({ + 'url': file_url, + 'ext': ext, + 'format_id': label or ext, + 'height': int_or_none(self._search_regex( + r'(\d+)[pP]', label or '', 'height', default=None)), + }) + self._sort_formats(formats) + thumbnail = self._search_regex( r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) return { 'id': video_id, 'title': title, - 'url': video_url, - 'ext': 'mp4', 'thumbnail': thumbnail, 'age_limit': self._family_friendly_search(webpage), + 'formats': formats, }