diff options
| -rw-r--r-- | AUTHORS | 1 | ||||
| -rw-r--r-- | youtube_dl/__init__.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/bloomberg.py | 25 | ||||
| -rw-r--r-- | youtube_dl/extractor/miomio.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/mixcloud.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/prosiebensat1.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/radiojavan.py | 66 | ||||
| -rw-r--r-- | youtube_dl/options.py | 3 | ||||
| -rw-r--r-- | youtube_dl/postprocessor/ffmpeg.py | 6 |
10 files changed, 98 insertions, 18 deletions
@@ -120,3 +120,4 @@ Jeff Buchbinder Amish Bhadeshia Joram Schrijver Will W. +Mohammad Teimori Pabandi diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 852b2fc3d..1c8b411b7 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -189,10 +189,6 @@ def _real_main(argv=None): if opts.allsubtitles and not opts.writeautomaticsub: opts.writesubtitles = True - if sys.version_info < (3,): - # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) - if opts.outtmpl is not None: - opts.outtmpl = opts.outtmpl.decode(preferredencoding()) outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2935d5b33..c05a43641 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -397,6 +397,7 @@ from .pyvideo import PyvideoIE from .quickvid import QuickVidIE from .r7 import R7IE from .radiode import RadioDeIE +from .radiojavan import RadioJavanIE from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 4a88ccd13..0dca29b71 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -6,32 +6,39 @@ from .common import InfoExtractor class BloombergIE(InfoExtractor): - _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<id>.+?)\.html' + _VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)' _TEST = { - 'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', + 'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2', # The md5 checksum changes 'info_dict': { 'id': 'qurhIVlJSB6hzkVi229d8g', 'ext': 'flv', 'title': 'Shah\'s Presentation on Foreign-Exchange Strategies', - 'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88', + 'description': 'md5:a8ba0302912d03d246979735c17d2761', }, } def _real_extract(self, url): name = self._match_id(url) webpage = self._download_webpage(url, name) - - f4m_url = self._search_regex( - r'<source src="(https?://[^"]+\.f4m.*?)"', webpage, - 'f4m url') + video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id') title = re.sub(': Video$', '', self._og_search_title(webpage)) + embed_info = self._download_json( + 'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id) + formats = [] + for stream in embed_info['streams']: + if stream["muxing_format"] == "TS": + formats.extend(self._extract_m3u8_formats(stream['url'], video_id)) + else: + formats.extend(self._extract_f4m_formats(stream['url'], video_id)) + self._sort_formats(formats) + return { - 'id': name.split('-')[-1], + 'id': video_id, 'title': title, - 'formats': self._extract_f4m_formats(f4m_url, name), + 'formats': formats, 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/miomio.py b/youtube_dl/extractor/miomio.py index 11608f730..cc3f27194 100644 --- a/youtube_dl/extractor/miomio.py +++ b/youtube_dl/extractor/miomio.py @@ -44,7 +44,7 @@ class MioMioIE(InfoExtractor): xml_config = self._search_regex( r'flashvars="type=sina&(.+?)&', webpage, 'xml config') - + # skipping the following page causes lags and eventually connection drop-outs self._request_webpage( 'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)), diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 21aea0c55..84f291558 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -97,7 +97,7 @@ class MixcloudIE(InfoExtractor): r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) description = self._og_search_description(webpage) like_count = str_to_int(self._search_regex( - r'\bbutton-favorite\b.+m-ajax-toggle-count="([^"]+)"', + r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"', webpage, 'like count', fatal=False)) view_count = str_to_int(self._search_regex( [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 385681d06..7cc799664 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -10,6 +10,7 @@ from ..compat import ( ) from ..utils import ( unified_strdate, + int_or_none, ) @@ -24,7 +25,7 @@ class ProSiebenSat1IE(InfoExtractor): 'info_dict': { 'id': '2104602', 'ext': 'mp4', - 'title': 'Staffel 2, Episode 18 - Jahresrückblick', + 'title': 'Episode 18 - Staffel 2', 'description': 'md5:8733c81b702ea472e069bc48bb658fc1', 'upload_date': '20131231', 'duration': 5845.04, @@ -266,6 +267,9 @@ class ProSiebenSat1IE(InfoExtractor): urls_sources = urls_sources.values() def fix_bitrate(bitrate): + bitrate = int_or_none(bitrate) + if not bitrate: + return None return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate for source in urls_sources: diff --git a/youtube_dl/extractor/radiojavan.py b/youtube_dl/extractor/radiojavan.py new file mode 100644 index 000000000..73ab78d6d --- /dev/null +++ b/youtube_dl/extractor/radiojavan.py @@ -0,0 +1,66 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import( + unified_strdate, + str_to_int, +) + + +class RadioJavanIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?' + _TEST = { + 'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam', + 'md5': 'e85208ffa3ca8b83534fca9fe19af95b', + 'info_dict': { + 'id': 'chaartaar-ashoobam', + 'ext': 'mp4', + 'title': 'Chaartaar - Ashoobam', + 'thumbnail': 're:^https?://.*\.jpe?g$', + 'upload_date': '20150215', + 'view_count': int, + 'like_count': int, + 'dislike_count': int, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + formats = [{ + 'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path, + 'format_id': '%sp' % height, + 'height': height, + } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)] + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + upload_date = unified_strdate(self._search_regex( + r'class="date_added">Date added: ([^<]+)<', + webpage, 'upload date', fatal=False)) + + view_count = str_to_int(self._search_regex( + r'class="views">Plays: ([\d,]+)', + webpage, 'view count', fatal=False)) + like_count = str_to_int(self._search_regex( + r'class="rating">([\d,]+) likes', + webpage, 'like count', fatal=False)) + dislike_count = str_to_int(self._search_regex( + r'class="rating">([\d,]+) dislikes', + webpage, 'dislike count', fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'view_count': view_count, + 'like_count': like_count, + 'dislike_count': dislike_count, + 'formats': formats, + } diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 35c7e5fb3..8e80e3759 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -13,6 +13,7 @@ from .compat import ( compat_kwargs, ) from .utils import ( + preferredencoding, write_string, ) from .version import __version__ @@ -797,7 +798,7 @@ def parseOpts(overrideArguments=None): # Workaround for Python 2.x, where argv is a byte list if sys.version_info < (3,): command_line_conf = [ - a.decode('utf-8', 'replace') for a in command_line_conf] + a.decode(preferredencoding(), 'replace') for a in command_line_conf] if '--ignore-config' in command_line_conf: system_conf = [] diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 55adf9685..0b60ac7e7 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -117,6 +117,10 @@ class FFmpegPostProcessor(PostProcessor): return self._paths[self.basename] @property + def probe_available(self): + return self.probe_basename is not None + + @property def probe_executable(self): return self._paths[self.probe_basename] @@ -168,7 +172,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): def get_audio_codec(self, path): - if not self.probe_executable: + if not self.probe_available: raise PostProcessingError('ffprobe or avprobe not found. Please install one.') try: cmd = [ |