diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/mtv.py | 8 | ||||
| -rw-r--r-- | youtube_dl/extractor/vevo.py | 44 | ||||
| -rw-r--r-- | youtube_dl/extractor/youtube.py | 19 |
5 files changed, 67 insertions, 8 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e27f58496..7b291f907 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -45,6 +45,7 @@ from .ted import TEDIE from .tumblr import TumblrIE from .ustream import UstreamIE from .vbox7 import Vbox7IE +from .vevo import VevoIE from .vimeo import VimeoIE from .vine import VineIE from .worldstarhiphop import WorldStarHipHopIE @@ -126,6 +127,7 @@ def gen_extractors(): GametrailersIE(), StatigramIE(), BreakIE(), + VevoIE(), JukeboxIE(), GenericIE() ] diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 062f4cf1e..64d63e109 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -211,7 +211,7 @@ class InfoExtractor(object): raise ExtractorError(u'Unable to extract %s' % _name) else: self._downloader.report_warning(u'unable to extract %s; ' - u'please report this issue on GitHub.' % _name) + u'please report this issue on http://yt-dl.org/bug' % _name) return None def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0): diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index a801c8123..969db7113 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -27,6 +27,14 @@ class MTVIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + # Some videos come from Vevo.com + m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";', + webpage, re.DOTALL) + if m_vevo: + vevo_id = m_vevo.group(1); + self.to_screen(u'Vevo video detected: %s' % vevo_id) + return self.url_result('vevo:%s' % vevo_id, ie='Vevo') + #song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>', # webpage, u'song name', fatal=False) diff --git a/youtube_dl/extractor/vevo.py b/youtube_dl/extractor/vevo.py new file mode 100644 index 000000000..aa88e1a92 --- /dev/null +++ b/youtube_dl/extractor/vevo.py @@ -0,0 +1,44 @@ +import re +import json + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + ExtractorError, +) + +class VevoIE(InfoExtractor): + """ + Accecps urls from vevo.com or in the format 'vevo:{id}' + (currently used by MTVIE) + """ + _VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*)$' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + json_url = 'http://www.vevo.com/data/video/%s' % video_id + base_url = 'http://smil.lvl3.vevo.com' + videos_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (base_url, video_id, video_id.lower()) + info_json = self._download_webpage(json_url, video_id, u'Downloading json info') + links_webpage = self._download_webpage(videos_url, video_id, u'Downloading videos urls') + + self.report_extraction(video_id) + video_info = json.loads(info_json) + m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):(?P<url>.*?)"', links_webpage)) + if m_urls is None or len(m_urls) == 0: + raise ExtractorError(u'Unable to extract video url') + # They are sorted from worst to best quality + m_url = m_urls[-1] + video_url = base_url + m_url.group('url') + ext = m_url.group('ext') + + return {'url': video_url, + 'ext': ext, + 'id': video_id, + 'title': video_info['title'], + 'thumbnail': video_info['img'], + 'upload_date': video_info['launchDate'].replace('/',''), + 'uploader': video_info['Artists'][0]['title'], + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index fbe8d63a3..de653cb3d 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -58,7 +58,7 @@ class YoutubeIE(InfoExtractor): '18': 'mp4', '22': 'mp4', '37': 'mp4', - '38': 'video', # You actually don't know if this will be MOV, AVI or whatever + '38': 'mp4', '43': 'webm', '44': 'webm', '45': 'webm', @@ -129,12 +129,13 @@ class YoutubeIE(InfoExtractor): """Indicate the download will use the RTMP protocol.""" self.to_screen(u'RTMP download detected') - @staticmethod - def _decrypt_signature(s): + def _decrypt_signature(self, s): """Decrypt the key the two subkeys must have a length of 43""" (a,b) = s.split('.') if len(a) != 43 or len(b) != 43: - raise ExtractorError(u'Unable to decrypt signature, subkeys lengths not valid') + raise ExtractorError(u'Unable to decrypt signature, subkeys lengths %d.%d not supported; retrying might work' % (len(a), len(b))) + if self._downloader.params.get('verbose'): + self.to_screen('encrypted signature length %d.%d' % (len(a), len(b))) b = ''.join([b[:8],a[0],b[9:18],b[-4],b[19:39], b[18]])[0:40] a = a[-40:] s_dec = '.'.join((a,b))[::-1] @@ -484,11 +485,15 @@ class YoutubeIE(InfoExtractor): try: mobj = re.search(r';ytplayer.config = ({.*?});', video_webpage) + if not mobj: + raise ValueError('Could not find vevo ID') info = json.loads(mobj.group(1)) args = info['args'] - if args.get('ptk','') == 'vevo' or 'dashmpd': - # Vevo videos with encrypted signatures - self.to_screen(u'%s: Vevo video detected.' % video_id) + # Easy way to know if the 's' value is in url_encoded_fmt_stream_map + # this signatures are encrypted + m_s = re.search(r'[&,]s=', args['url_encoded_fmt_stream_map']) + if m_s is not None: + self.to_screen(u'%s: Encrypted signatures detected.' % video_id) video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']] except ValueError: pass |