From 020cf5ebfd86d039b542e37b1a70e81afe2e034c Mon Sep 17 00:00:00 2001 From: =?utf8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Tue, 25 Feb 2014 23:57:54 +0100 Subject: [PATCH] [nbc] Add an extractor for the main nbc.com site MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Some of the videos are encrypted, the f4m downloader doesn’t support them. --- youtube_dl/extractor/__init__.py | 5 ++++- youtube_dl/extractor/nbc.py | 24 ++++++++++++++++++++++++ youtube_dl/extractor/theplatform.py | 14 ++++++++++---- 3 files changed, 38 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 8eff3df41..c276fad0c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -152,7 +152,10 @@ from .myspass import MySpassIE from .myvideo import MyVideoIE from .naver import NaverIE from .nba import NBAIE -from .nbc import NBCNewsIE +from .nbc import ( + NBCIE, + NBCNewsIE, +) from .ndr import NDRIE from .ndtv import NDTVIE from .newgrounds import NewgroundsIE diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index ff750de3f..1a63ab56a 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -6,6 +6,30 @@ from .common import InfoExtractor from ..utils import find_xpath_attr, compat_str +class NBCIE(InfoExtractor): + _VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?Pn?\d+)' + + _TEST = { + 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', + 'md5': '54d0fbc33e0b853a65d7b4de5c06d64e', + 'info_dict': { + 'id': 'u1RInQZRN7QJ', + 'ext': 'flv', + 'title': 'I Am a Firefighter', + 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url') + if theplatform_url.startswith('//'): + theplatform_url = 'http:' + theplatform_url + return self.url_result(theplatform_url) + + class NBCNewsIE(InfoExtractor): _VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P\d+)' diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index d60702325..91f2453eb 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -13,7 +13,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language class ThePlatformIE(InfoExtractor): _VALID_URL = r'''(?x) (?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/ - (?P[^/\?]+/(?:swf|config)/select/)? + (?P(?:[^/\?]+/(?:swf|config)|onsite)/select/)? |theplatform:)(?P[^/\?&]+)''' _TEST = { @@ -54,10 +54,15 @@ class ThePlatformIE(InfoExtractor): f4m_node = body.find(_x('smil:seq/smil:video')) if f4m_node is not None: + f4m_url = f4m_node.attrib['src'] + if 'manifest.f4m?' not in f4m_url: + f4m_url += '?' + # the parameters are from syfy.com, other sites may use others, + # they also work for nbc.com + f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3' formats = [{ 'ext': 'flv', - # the parameters are from syfy.com, other sites may use others - 'url': f4m_node.attrib['src'] + '?g=UXWGVKRWHFSP&hdcore=3.0.3', + 'url': f4m_url, }] else: base_url = head.find(_x('smil:meta')).attrib['base'] @@ -95,9 +100,10 @@ class ThePlatformIE(InfoExtractor): if mobj.group('config'): config_url = url+ '&form=json' config_url = config_url.replace('swf/', 'config/') + config_url = config_url.replace('onsite/', 'onsite/config/') config_json = self._download_webpage(config_url, video_id, u'Downloading config') config = json.loads(config_json) - smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4' + smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m' else: smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' 'format=smil&mbr=true'.format(video_id)) -- 2.39.5