From 969c0fe31c066621520f6d03abc47d05aee9caac Mon Sep 17 00:00:00 2001 From: Christopher Smith Date: Thu, 29 Jun 2017 13:10:45 -0600 Subject: [PATCH 1/3] [cjsw] Add new extractor --- youtube_dl/extractor/cjsw.py | 50 ++++++++++++++++++++++++++++++ youtube_dl/extractor/extractors.py | 1 + 2 files changed, 51 insertions(+) create mode 100644 youtube_dl/extractor/cjsw.py diff --git a/youtube_dl/extractor/cjsw.py b/youtube_dl/extractor/cjsw.py new file mode 100644 index 000000000..5a6fce175 --- /dev/null +++ b/youtube_dl/extractor/cjsw.py @@ -0,0 +1,50 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + unescapeHTML, +) + + +class CJSWIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P[\S]+)/(?P[0-9]+)/?' + IE_NAME = 'cjsw' + _TEST = { + 'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620', + 'md5': 'cee14d40f1e9433632c56e3d14977120', + 'info_dict': { + 'id': '20170620', + 'ext': 'mp3', + 'title': 'Freshly Squeezed', + 'description': 'Sled Island artists featured // Live session with Phi Pho, followed by a live session with Sinzere & The Late Nights! // Stay Fresh Y\'all!!', + } + } + + def _real_extract(self, url): + episode_id = self._match_id(url) + + webpage = self._download_webpage(url, episode_id) + + episode_controls = re.search(r']+class=(["\'])episode-controls\1[^>]*>', webpage) + if not episode_controls: + raise ExtractorError('No streamable podcast', video_id=episode_id, expected=True) + + title = unescapeHTML(self._search_regex( + r']+data-showname=(["\'])(?P.*?)\1[^>]*>', webpage, 'title', group='title')) + description = unescapeHTML(self._html_search_regex( + r'<p>(?P<description>.*?)</p>', webpage, 'description', fatal=False)) + formats = [{ + 'url': self._html_search_regex( + r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.*?)\1[^>]*>', webpage, 'audio_url', group='audio_url'), + 'ext': 'mp3', + }] + return { + 'id': episode_id, + 'title': title, + 'description': description, + 'formats': formats, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 45591f2a7..a7cea5429 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -178,6 +178,7 @@ from .chirbit import ( ChirbitProfileIE, ) from .cinchcast import CinchcastIE +from .cjsw import CJSWIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE from .cliprs import ClipRsIE From dbae412d05ce3d198dbc2f8e6e6ce3bf96f73164 Mon Sep 17 00:00:00 2001 From: Christopher Smith <ctsmi@ucalgary.ca> Date: Tue, 4 Jul 2017 15:36:48 -0600 Subject: [PATCH 2/3] [cjsw] Requested fixes --- youtube_dl/extractor/cjsw.py | 18 ++++++++---------- 1 file changed, 8 insertions(+), 10 deletions(-) diff --git a/youtube_dl/extractor/cjsw.py b/youtube_dl/extractor/cjsw.py index 5a6fce175..81c1ae4df 100644 --- a/youtube_dl/extractor/cjsw.py +++ b/youtube_dl/extractor/cjsw.py @@ -1,17 +1,14 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( ExtractorError, - unescapeHTML, ) class CJSWIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program_name>[\S]+)/(?P<id>[0-9]+)/?' + _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/\S+/(?P<id>[0-9]+)' IE_NAME = 'cjsw' _TEST = { 'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620', @@ -29,18 +26,19 @@ class CJSWIE(InfoExtractor): webpage = self._download_webpage(url, episode_id) - episode_controls = re.search(r'<div[^>]+class=(["\'])episode-controls\1[^>]*>', webpage) + episode_controls = self._search_regex(r'<div[^>]+class=(["\'])episode-controls\1[^>]*>', webpage, 'episode_controls', fatal=False) if not episode_controls: raise ExtractorError('No streamable podcast', video_id=episode_id, expected=True) - title = unescapeHTML(self._search_regex( - r'<button[^>]+data-showname=(["\'])(?P<title>.*?)\1[^>]*>', webpage, 'title', group='title')) - description = unescapeHTML(self._html_search_regex( - r'<p>(?P<description>.*?)</p>', webpage, 'description', fatal=False)) + title = self._html_search_regex( + r'<button[^>]+data-showname=(["\'])(?P<title>.+?)\1[^>]*>', webpage, 'title', group='title') + description = self._html_search_regex( + r'<p>(?P<description>.+?)</p>', webpage, 'description', fatal=False) formats = [{ 'url': self._html_search_regex( - r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.*?)\1[^>]*>', webpage, 'audio_url', group='audio_url'), + r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.+?)\1[^>]*>', webpage, 'audio_url', group='audio_url'), 'ext': 'mp3', + 'vcodec': 'none', }] return { 'id': episode_id, From 1fd6d40c9aa11f36d9985021f3e6b051a4b853e7 Mon Sep 17 00:00:00 2001 From: Christopher Smith <ctsmi@ucalgary.ca> Date: Wed, 5 Jul 2017 22:49:58 -0600 Subject: [PATCH 3/3] [cjsw] Requested fixes --- youtube_dl/extractor/cjsw.py | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/youtube_dl/extractor/cjsw.py b/youtube_dl/extractor/cjsw.py index 81c1ae4df..087cac9bc 100644 --- a/youtube_dl/extractor/cjsw.py +++ b/youtube_dl/extractor/cjsw.py @@ -2,9 +2,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class CJSWIE(InfoExtractor): @@ -26,17 +23,13 @@ class CJSWIE(InfoExtractor): webpage = self._download_webpage(url, episode_id) - episode_controls = self._search_regex(r'<div[^>]+class=(["\'])episode-controls\1[^>]*>', webpage, 'episode_controls', fatal=False) - if not episode_controls: - raise ExtractorError('No streamable podcast', video_id=episode_id, expected=True) - - title = self._html_search_regex( - r'<button[^>]+data-showname=(["\'])(?P<title>.+?)\1[^>]*>', webpage, 'title', group='title') + title = self._search_regex( + r'<button[^>]+data-showname=(["\'])(?P<title>(?!\1).+?)\1[^>]*>', webpage, 'title', group='title') description = self._html_search_regex( r'<p>(?P<description>.+?)</p>', webpage, 'description', fatal=False) formats = [{ - 'url': self._html_search_regex( - r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.+?)\1[^>]*>', webpage, 'audio_url', group='audio_url'), + 'url': self._search_regex( + r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>(?!\1).+?)\1[^>]*>', webpage, 'audio_url', group='audio_url'), 'ext': 'mp3', 'vcodec': 'none', }]