From dd0a58f5f028980ba76450998b218ea7a4920420 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 20 Feb 2015 01:19:38 +0600 Subject: [PATCH 1/4] [blinkx] Fix extraction --- youtube_dl/extractor/blinkx.py | 49 ++++++++++++++++------------------ 1 file changed, 23 insertions(+), 26 deletions(-) diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py index 3e461e715..3b8eabe8f 100644 --- a/youtube_dl/extractor/blinkx.py +++ b/youtube_dl/extractor/blinkx.py @@ -1,40 +1,35 @@ from __future__ import unicode_literals import json -import re from .common import InfoExtractor -from ..utils import remove_start +from ..utils import ( + remove_start, + int_or_none, +) class BlinkxIE(InfoExtractor): - _VALID_URL = r'^(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P[^?]+)' + _VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P[^?]+)' IE_NAME = 'blinkx' _TEST = { - 'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB', - 'md5': '2e9a07364af40163a908edbf10bb2492', + 'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ', + 'md5': '337cf7a344663ec79bf93a526a2e06c7', 'info_dict': { - 'id': '8aQUy7GV', + 'id': 'Da0Gw3xc', 'ext': 'mp4', - 'title': 'Police Car Rolls Away', - 'uploader': 'stupidvideos.com', - 'upload_date': '20131215', - 'timestamp': 1387068000, - 'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!', - 'duration': 14.886, - 'thumbnails': [{ - 'width': 100, - 'height': 76, - 'resolution': '100x76', - 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg', - }], + 'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News', + 'uploader': 'IGN News', + 'upload_date': '20150217', + 'timestamp': 1424215740, + 'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.', + 'duration': 47.743333, }, } - def _real_extract(self, rl): - m = re.match(self._VALID_URL, rl) - video_id = m.group('id') + def _real_extract(self, url): + video_id = self._match_id(url) display_id = video_id[:8] api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' + @@ -60,18 +55,20 @@ def _real_extract(self, rl): elif m['type'] in ('flv', 'mp4'): vcodec = remove_start(m['vcodec'], 'ff') acodec = remove_start(m['acodec'], 'ff') - tbr = (int(m['vbr']) + int(m['abr'])) // 1000 + vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000) + abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000) + tbr = vbr + abr if vbr and abr else None format_id = '%s-%sk-%s' % (vcodec, tbr, m['w']) formats.append({ 'format_id': format_id, 'url': m['link'], 'vcodec': vcodec, 'acodec': acodec, - 'abr': int(m['abr']) // 1000, - 'vbr': int(m['vbr']) // 1000, + 'abr': abr, + 'vbr': vbr, 'tbr': tbr, - 'width': int(m['w']), - 'height': int(m['h']), + 'width': int_or_none(m.get('w')), + 'height': int_or_none(m.get('h')), }) self._sort_formats(formats) From 50efb383f01071fe5ae6ec6da2557031da54abde Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Fri, 20 Feb 2015 14:13:41 +0200 Subject: [PATCH 2/4] [tv4] Add new extractor (Closes #4839) (Closes #2103) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/tv4.py | 100 +++++++++++++++++++++++++++++++ 2 files changed, 101 insertions(+) create mode 100644 youtube_dl/extractor/tv4.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index f225ac654..7d0c6b5ac 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -490,6 +490,7 @@ from .tunein import TuneInIE from .turbo import TurboIE from .tutv import TutvIE +from .tv4 import TV4IE from .tvigle import TvigleIE from .tvp import TvpIE, TvpSeriesIE from .tvplay import TVPlayIE diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py new file mode 100644 index 000000000..1c4b6d635 --- /dev/null +++ b/youtube_dl/extractor/tv4.py @@ -0,0 +1,100 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) + + +class TV4IE(InfoExtractor): + IE_DESC = 'tv4.se and tv4play.se' + _VALID_URL = r'''(?x)https?://(?:www\.)? + (?: + tv4\.se/(?:[^/]+)/klipp/(?:.*)-| + tv4play\.se/ + (?: + (?:program|barn)/(?:[^\?]+)\?video_id=| + iframe/video/| + film/| + sport/| + ) + )(?P[0-9]+)''' + _TESTS = [ + { + 'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650', + 'md5': '909d6454b87b10a25aa04c4bdd416a9b', + 'info_dict': { + 'id': '2491650', + 'ext': 'mp4', + 'title': 'Kalla Fakta 5 (english subtitles)', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': int, + 'upload_date': '20131125', + }, + }, + { + 'url': 'http://www.tv4play.se/iframe/video/3054113', + 'md5': '77f851c55139ffe0ebd41b6a5552489b', + 'info_dict': { + 'id': '3054113', + 'ext': 'mp4', + 'title': 'Så här jobbar ficktjuvarna - se avslöjande bilder', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Unika bilder avslöjar hur turisternas fickor vittjas mitt på Stockholms central. Två experter på ficktjuvarna avslöjar knepen du ska se upp för.', + 'timestamp': int, + 'upload_date': '20150130', + }, + }, + { + 'url': 'http://www.tv4play.se/sport/3060959', + 'only_matching': True, + }, + { + 'url': 'http://www.tv4play.se/film/2378136', + 'only_matching': True, + }, + { + 'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + info = self._download_json( + 'http://www.tv4play.se/player/assets/%s.json' % video_id, video_id, 'Downloading video info JSON') + + # If is_geo_restricted is true, it doesn't neceserally mean we can't download it + if info['is_geo_restricted']: + self.report_warning('This content might not be available in your country due to licensing restrictions.') + if info['requires_subscription']: + raise ExtractorError('This content requires subscription.', expected=True) + + sources_data = self._download_json( + 'https://prima.tv4play.se/api/web/asset/%s/play.json?protocol=http&videoFormat=MP4' % video_id, video_id, 'Downloading sources JSON') + sources = sources_data['playback'] + + formats = [] + for item in sources.get('items', {}).get('item', []): + ext, bitrate = item['mediaFormat'], item['bitrate'] + formats.append({ + 'format_id': '%s_%s' % (ext, bitrate), + 'tbr': bitrate, + 'ext': ext, + 'url': item['url'], + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': info['title'], + 'formats': formats, + 'description': info.get('description'), + 'timestamp': parse_iso8601(info.get('broadcast_date_time')), + 'duration': info.get('duration'), + 'thumbnail': info.get('image'), + 'is_live': sources.get('live'), + } From 1bd838608fda2da789c8991ec7fc194ed5ec0a1f Mon Sep 17 00:00:00 2001 From: minusf Date: Fri, 20 Feb 2015 18:24:20 +0100 Subject: [PATCH 3/4] prefer 'code' to 'uri' if present --- youtube_dl/extractor/ted.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 10b3b706a..5e5322974 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -134,9 +134,13 @@ def _talk_info(self, url, video_name): if talk_info.get('external') is not None: self.to_screen('Found video from %s' % talk_info['external']['service']) + if 'code' in talk_info['external']: + ext_url = talk_info['external']['code'] + else: + ext_url = talk_info['external']['uri'] return { '_type': 'url', - 'url': talk_info['external']['uri'], + 'url': ext_url, } formats = [{ From a461a11989e147c30e3611005861cc63dcd16af3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 21 Feb 2015 00:14:38 +0600 Subject: [PATCH 4/4] [ted] Improve external video handling and add test --- youtube_dl/extractor/ted.py | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 5e5322974..59678399d 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -83,6 +83,22 @@ class TEDIE(SubtitlesInfoExtractor): 'params': { 'skip_download': True, }, + }, { + # YouTube video + 'url': 'http://www.ted.com/talks/jeffrey_kluger_the_sibling_bond', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': 'aFBIPO-P7LM', + 'ext': 'mp4', + 'title': 'The hidden power of siblings: Jeff Kluger at TEDxAsheville', + 'description': 'md5:3d7a4f50d95ca5dd67104e2a20f43fe1', + 'uploader': 'TEDx Talks', + 'uploader_id': 'TEDxTalks', + 'upload_date': '20111216', + }, + 'params': { + 'skip_download': True, + }, }] _NATIVE_FORMATS = { @@ -132,15 +148,16 @@ def _talk_info(self, url, video_name): talk_info = self._extract_info(webpage)['talks'][0] - if talk_info.get('external') is not None: - self.to_screen('Found video from %s' % talk_info['external']['service']) - if 'code' in talk_info['external']: - ext_url = talk_info['external']['code'] - else: - ext_url = talk_info['external']['uri'] + external = talk_info.get('external') + if external: + service = external['service'] + self.to_screen('Found video from %s' % service) + ext_url = None + if service.lower() == 'youtube': + ext_url = external.get('code') return { '_type': 'url', - 'url': ext_url, + 'url': ext_url or external['uri'], } formats = [{