From ea63e4998bd8ed84f7479d1283eea4074ac8dba6 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Sun, 23 Jun 2013 20:50:22 +0200 Subject: [PATCH] Move comedycentral into its own file --- youtube_dl/InfoExtractors.py | 167 +----------------------- youtube_dl/extractor/comedycentral.py | 179 ++++++++++++++++++++++++++ 2 files changed, 180 insertions(+), 166 deletions(-) create mode 100644 youtube_dl/extractor/comedycentral.py diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 5c6152427..c9cf96ea3 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -21,6 +21,7 @@ from .extractor.common import InfoExtractor, SearchInfoExtractor from .extractor.ard import ARDIE from .extractor.arte import ArteTvIE from .extractor.bliptv import BlipTVIE, BlipTVUserIE +from .extractor.comedycentral import ComedyCentralIE from .extractor.dailymotion import DailymotionIE from .extractor.gametrailers import GametrailersIE from .extractor.generic import GenericIE @@ -196,172 +197,6 @@ class FacebookIE(InfoExtractor): -class ComedyCentralIE(InfoExtractor): - """Information extractor for The Daily Show and Colbert Report """ - - # urls can be abbreviations like :thedailyshow or :colbert - # urls for episodes like: - # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day - # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news - # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 - _VALID_URL = r"""^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport) - |(https?://)?(www\.)? - (?Pthedailyshow|colbertnation)\.com/ - (full-episodes/(?P.*)| - (?P - (the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?)) - |(watch/(?P[^/]*)/(?P.*))))) - $""" - - _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] - - _video_extensions = { - '3500': 'mp4', - '2200': 'mp4', - '1700': 'mp4', - '1200': 'mp4', - '750': 'mp4', - '400': 'mp4', - } - _video_dimensions = { - '3500': '1280x720', - '2200': '960x540', - '1700': '768x432', - '1200': '640x360', - '750': '512x288', - '400': '384x216', - } - - @classmethod - def suitable(cls, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url, re.VERBOSE) is not None - - def _print_formats(self, formats): - print('Available formats:') - for x in formats: - print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) - - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - - if mobj.group('shortname'): - if mobj.group('shortname') in ('tds', 'thedailyshow'): - url = u'http://www.thedailyshow.com/full-episodes/' - else: - url = u'http://www.colbertnation.com/full-episodes/' - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - assert mobj is not None - - if mobj.group('clip'): - if mobj.group('showname') == 'thedailyshow': - epTitle = mobj.group('tdstitle') - else: - epTitle = mobj.group('cntitle') - dlNewest = False - else: - dlNewest = not mobj.group('episode') - if dlNewest: - epTitle = mobj.group('showname') - else: - epTitle = mobj.group('episode') - - self.report_extraction(epTitle) - webpage,htmlHandle = self._download_webpage_handle(url, epTitle) - if dlNewest: - url = htmlHandle.geturl() - mobj = re.match(self._VALID_URL, url, re.VERBOSE) - if mobj is None: - raise ExtractorError(u'Invalid redirected URL: ' + url) - if mobj.group('episode') == '': - raise ExtractorError(u'Redirected URL is still not specific: ' + url) - epTitle = mobj.group('episode') - - mMovieParams = re.findall('(?:gsp.comedystor/.*)$', rtmp_video_url) - if not m: - raise ExtractorError(u'Cannot transform RTMP url') - base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' - video_url = base + m.group('finalid') - - effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) - info = { - 'id': shortMediaId, - 'url': video_url, - 'uploader': showId, - 'upload_date': officialDate, - 'title': effTitle, - 'ext': 'mp4', - 'format': format, - 'thumbnail': None, - 'description': officialTitle, - } - results.append(info) - - return results class EscapistIE(InfoExtractor): diff --git a/youtube_dl/extractor/comedycentral.py b/youtube_dl/extractor/comedycentral.py new file mode 100644 index 000000000..1bb359046 --- /dev/null +++ b/youtube_dl/extractor/comedycentral.py @@ -0,0 +1,179 @@ +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + compat_str, + compat_urllib_parse, + + ExtractorError, + unified_strdate, +) + + +class ComedyCentralIE(InfoExtractor): + """Information extractor for The Daily Show and Colbert Report """ + + # urls can be abbreviations like :thedailyshow or :colbert + # urls for episodes like: + # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day + # or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news + # or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524 + _VALID_URL = r"""^(:(?Ptds|thedailyshow|cr|colbert|colbertnation|colbertreport) + |(https?://)?(www\.)? + (?Pthedailyshow|colbertnation)\.com/ + (full-episodes/(?P.*)| + (?P + (the-colbert-report-(videos|collections)/(?P[0-9]+)/[^/]*/(?P.*?)) + |(watch/(?P[^/]*)/(?P.*))))) + $""" + + _available_formats = ['3500', '2200', '1700', '1200', '750', '400'] + + _video_extensions = { + '3500': 'mp4', + '2200': 'mp4', + '1700': 'mp4', + '1200': 'mp4', + '750': 'mp4', + '400': 'mp4', + } + _video_dimensions = { + '3500': '1280x720', + '2200': '960x540', + '1700': '768x432', + '1200': '640x360', + '750': '512x288', + '400': '384x216', + } + + @classmethod + def suitable(cls, url): + """Receives a URL and returns True if suitable for this IE.""" + return re.match(cls._VALID_URL, url, re.VERBOSE) is not None + + def _print_formats(self, formats): + print('Available formats:') + for x in formats: + print('%s\t:\t%s\t[%s]' %(x, self._video_extensions.get(x, 'mp4'), self._video_dimensions.get(x, '???'))) + + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + if mobj is None: + raise ExtractorError(u'Invalid URL: %s' % url) + + if mobj.group('shortname'): + if mobj.group('shortname') in ('tds', 'thedailyshow'): + url = u'http://www.thedailyshow.com/full-episodes/' + else: + url = u'http://www.colbertnation.com/full-episodes/' + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + assert mobj is not None + + if mobj.group('clip'): + if mobj.group('showname') == 'thedailyshow': + epTitle = mobj.group('tdstitle') + else: + epTitle = mobj.group('cntitle') + dlNewest = False + else: + dlNewest = not mobj.group('episode') + if dlNewest: + epTitle = mobj.group('showname') + else: + epTitle = mobj.group('episode') + + self.report_extraction(epTitle) + webpage,htmlHandle = self._download_webpage_handle(url, epTitle) + if dlNewest: + url = htmlHandle.geturl() + mobj = re.match(self._VALID_URL, url, re.VERBOSE) + if mobj is None: + raise ExtractorError(u'Invalid redirected URL: ' + url) + if mobj.group('episode') == '': + raise ExtractorError(u'Redirected URL is still not specific: ' + url) + epTitle = mobj.group('episode') + + mMovieParams = re.findall('(?:gsp.comedystor/.*)$', rtmp_video_url) + if not m: + raise ExtractorError(u'Cannot transform RTMP url') + base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' + video_url = base + m.group('finalid') + + effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1) + info = { + 'id': shortMediaId, + 'url': video_url, + 'uploader': showId, + 'upload_date': officialDate, + 'title': effTitle, + 'ext': 'mp4', + 'format': format, + 'thumbnail': None, + 'description': officialTitle, + } + results.append(info) + + return results