diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/cbc.py | 113 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 8 | ||||
| -rw-r--r-- | youtube_dl/extractor/theplatform.py | 2 |
4 files changed, 121 insertions, 6 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index f1e5a5e86..7056cf323 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -89,6 +89,10 @@ from .camdemy import ( from .canalplus import CanalplusIE from .canalc2 import Canalc2IE from .canvas import CanvasIE +from .cbc import ( + CBCIE, + CBCPlayerIE, +) from .cbs import CBSIE from .cbsnews import ( CBSNewsIE, diff --git a/youtube_dl/extractor/cbc.py b/youtube_dl/extractor/cbc.py new file mode 100644 index 000000000..d8aa31038 --- /dev/null +++ b/youtube_dl/extractor/cbc.py @@ -0,0 +1,113 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import js_to_json + + +class CBCIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?:[^/]+/)+(?P<id>[^/?#]+)' + _TESTS = [{ + # with mediaId + 'url': 'http://www.cbc.ca/22minutes/videos/clips-season-23/don-cherry-play-offs', + 'info_dict': { + 'id': '2682904050', + 'ext': 'flv', + 'title': 'Don Cherry – All-Stars', + 'description': 'Don Cherry has a bee in his bonnet about AHL player John Scott because that guy’s got heart.', + 'timestamp': 1454475540, + 'upload_date': '20160203', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # with clipId + 'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live', + 'info_dict': { + 'id': '2487345465', + 'ext': 'flv', + 'title': 'Robin Williams freestyles on 90 Minutes Live', + 'description': 'Wacky American comedian Robin Williams shows off his infamous "freestyle" comedic talents while being interviewed on CBC\'s 90 Minutes Live.', + 'upload_date': '19700101', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # multiple iframes + 'url': 'http://www.cbc.ca/natureofthings/blog/birds-eye-view-from-vancouvers-burrard-street-bridge-how-we-got-the-shot', + 'playlist': [{ + 'info_dict': { + 'id': '2680832926', + 'ext': 'flv', + 'title': 'An Eagle\'s-Eye View Off Burrard Bridge', + 'description': 'Hercules the eagle flies from Vancouver\'s Burrard Bridge down to a nearby park with a mini-camera strapped to his back.', + 'upload_date': '19700101', + }, + }, { + 'info_dict': { + 'id': '2658915080', + 'ext': 'flv', + 'title': 'Fly like an eagle!', + 'description': 'Eagle equipped with a mini camera flies from the world\'s tallest tower', + 'upload_date': '19700101', + }, + }], + 'params': { + # rtmp download + 'skip_download': True, + }, + }] + + @classmethod + def suitable(cls, url): + return False if CBCPlayerIE.suitable(url) else super(CBCIE, cls).suitable(url) + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + player_init = self._search_regex( + r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage, 'player init', + default=None) + if player_init: + player_info = self._parse_json(player_init, display_id, js_to_json) + media_id = player_info.get('mediaId') + if not media_id: + clip_id = player_info['clipId'] + media_id = self._download_json( + 'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id, + clip_id)['entries'][0]['id'].split('/')[-1] + return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) + else: + entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)] + return self.playlist_result(entries) + + +class CBCPlayerIE(InfoExtractor): + _VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)' + _TEST = { + 'url': 'http://www.cbc.ca/player/play/2683190193', + 'info_dict': { + 'id': '2683190193', + 'ext': 'flv', + 'title': 'Gerry Runs a Sweat Shop', + 'description': 'md5:b457e1c01e8ff408d9d801c1c2cd29b0', + 'timestamp': 1455067800, + 'upload_date': '20160210', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + return self.url_result( + 'http://feed.theplatform.com/f/ExhSPC/vms_5akSXx4Ng_Zn?byGuid=%s' % video_id, + 'ThePlatformFeed', video_id) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 00645feed..6b40a8323 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -1186,12 +1186,13 @@ class InfoExtractor(object): http_count = 0 m3u8_count = 0 - src_urls = [] + srcs = [] videos = smil.findall(self._xpath_ns('.//video', namespace)) for video in videos: src = video.get('src') - if not src: + if not src or src in srcs: continue + srcs.append(src) bitrate = float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) filesize = int_or_none(video.get('size') or video.get('fileSize')) @@ -1223,9 +1224,6 @@ class InfoExtractor(object): continue src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src) - if src_url in src_urls: - continue - src_urls.append(src_url) if proto == 'm3u8' or src_ext == 'm3u8': m3u8_formats = self._extract_m3u8_formats( diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 10f2cad55..f2e975ab0 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -284,7 +284,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): duration = None for item in entry['media$content']: smil_url = item['plfile$url'] + '&format=SMIL&Tracking=true&Embedded=true&formats=MPEG4,F4M' - cur_video_id = url_basename(smil_url) + cur_video_id = ThePlatformIE._match_id(smil_url) if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$duration')) |