From 3e123c1e2887cb144f1b73cabb78ab34c43d10bc Mon Sep 17 00:00:00 2001 From: "Sergey M." Date: Sun, 23 Feb 2014 04:50:05 +0700 Subject: [PATCH] [videobam] Add support for videobam.com (Closes #2411) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/videobam.py | 79 ++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 youtube_dl/extractor/videobam.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3badcc238..6dccd5ae7 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -241,6 +241,7 @@ from .vesti import VestiIE from .vevo import VevoIE from .vice import ViceIE from .viddler import ViddlerIE +from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE from .videopremium import VideoPremiumIE diff --git a/youtube_dl/extractor/videobam.py b/youtube_dl/extractor/videobam.py new file mode 100644 index 000000000..3366d982c --- /dev/null +++ b/youtube_dl/extractor/videobam.py @@ -0,0 +1,79 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import int_or_none + + +class VideoBamIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?videobam\.com/(?:videos/download/)?(?P[a-zA-Z]+)' + + _TESTS = [ + { + 'url': 'http://videobam.com/OiJQM', + 'md5': 'db471f27763a531f10416a0c58b5a1e0', + 'info_dict': { + 'id': 'OiJQM', + 'ext': 'mp4', + 'title': 'Is Alcohol Worse Than Ecstasy?', + 'description': 'md5:d25b96151515c91debc42bfbb3eb2683', + 'uploader': 'frihetsvinge', + }, + }, + { + 'url': 'http://videobam.com/pqLvq', + 'md5': 'd9a565b5379a99126ef94e1d7f9a383e', + 'note': 'HD video', + 'info_dict': { + 'id': 'pqLvq', + 'ext': 'mp4', + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + page = self._download_webpage('http://videobam.com/%s' % video_id, video_id, 'Downloading page') + + formats = [] + + for preference, format_id in enumerate(['low', 'high']): + mobj = re.search(r"%s: '(?P[^']+)'" % format_id, page) + if not mobj: + continue + formats.append({ + 'url': mobj.group('url'), + 'ext': 'mp4', + 'format_id': format_id, + 'preference': preference, + }) + + if not formats: + player_config = json.loads(self._html_search_regex(r'var player_config = ({.+?});', page, 'player config')) + formats = [{ + 'url': item['url'], + 'ext': 'mp4', + } for item in player_config['playlist'] if 'autoPlay' in item] + + self._sort_formats(formats) + + title = self._og_search_title(page, default='VideoBam', fatal=False) + description = self._og_search_description(page, default=None) + thumbnail = self._og_search_thumbnail(page) + uploader = self._html_search_regex(r'Upload by ([^<]+)', page, 'uploader', fatal=False, default=None) + view_count = int_or_none( + self._html_search_regex(r'Views: (\d+) ', page, 'view count', fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'view_count': view_count, + 'formats': formats, + } \ No newline at end of file