Browse Source
Merge branch 'srgssr' of https://github.com/remitamine/youtube-dl into remitamine-srgssr
master
Merge branch 'srgssr' of https://github.com/remitamine/youtube-dl into remitamine-srgssr
master
remitamine
9 years ago
4 changed files with 213 additions and 176 deletions
Split View
Diff Options
-
5youtube_dl/extractor/__init__.py
-
97youtube_dl/extractor/rts.py
-
120youtube_dl/extractor/srf.py
-
167youtube_dl/extractor/srgssr.py
@ -1,120 +0,0 @@ |
|||
# coding: utf-8 |
|||
from __future__ import unicode_literals |
|||
|
|||
import re |
|||
from .common import InfoExtractor |
|||
from ..utils import ( |
|||
determine_ext, |
|||
parse_iso8601, |
|||
xpath_text, |
|||
) |
|||
|
|||
|
|||
class SrfIE(InfoExtractor): |
|||
_VALID_URL = r'https?://(?:www\.srf\.ch/play(?:er)?/(?:tv|radio)/[^/]+/(?P<media_type>video|audio)/(?P<display_id>[^?]+)\?id=|tp\.srgssr\.ch/p/flash\?urn=urn:srf:ais:video:)(?P<id>[0-9a-f\-]{36})' |
|||
_TESTS = [{ |
|||
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', |
|||
'md5': '4cd93523723beff51bb4bee974ee238d', |
|||
'info_dict': { |
|||
'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5', |
|||
'display_id': 'snowden-beantragt-asyl-in-russland', |
|||
'ext': 'm4v', |
|||
'upload_date': '20130701', |
|||
'title': 'Snowden beantragt Asyl in Russland', |
|||
'timestamp': 1372713995, |
|||
} |
|||
}, { |
|||
# No Speichern (Save) button |
|||
'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa', |
|||
'md5': 'd97e236e80d1d24729e5d0953d276a4f', |
|||
'info_dict': { |
|||
'id': '677f5829-e473-4823-ac83-a1087fe97faa', |
|||
'display_id': 'jaguar-xk120-shadow-und-tornado-dampflokomotive', |
|||
'ext': 'flv', |
|||
'upload_date': '20130710', |
|||
'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive', |
|||
'timestamp': 1373493600, |
|||
}, |
|||
}, { |
|||
'url': 'http://www.srf.ch/play/radio/hoerspielarchiv-srf-musikwelle/audio/saegel-ohni-wind-von-jakob-stebler?id=415bf3d3-6429-4de7-968d-95866e37cfbc', |
|||
'md5': '', |
|||
'info_dict': { |
|||
'id': '415bf3d3-6429-4de7-968d-95866e37cfbc', |
|||
'display_id': 'saegel-ohni-wind-von-jakob-stebler', |
|||
'ext': 'mp3', |
|||
'upload_date': '20080518', |
|||
'title': '«Sägel ohni Wind» von Jakob Stebler', |
|||
'timestamp': 1211112000, |
|||
}, |
|||
'params': { |
|||
'skip_download': True, # requires rtmpdump |
|||
}, |
|||
}, { |
|||
'url': 'http://www.srf.ch/player/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', |
|||
'only_matching': True, |
|||
}, { |
|||
'url': 'https://tp.srgssr.ch/p/flash?urn=urn:srf:ais:video:28e1a57d-5b76-4399-8ab3-9097f071e6c5', |
|||
'only_matching': True, |
|||
}] |
|||
|
|||
def _real_extract(self, url): |
|||
mobj = re.match(self._VALID_URL, url) |
|||
video_id = mobj.group('id') |
|||
media_type = mobj.group('media_type') |
|||
display_id = mobj.group('display_id') or video_id |
|||
|
|||
video_data = self._download_xml( |
|||
'http://il.srgssr.ch/integrationlayer/1.0/ue/srf/%s/play/%s.xml' % (media_type, video_id), |
|||
display_id) |
|||
|
|||
title = xpath_text( |
|||
video_data, './AssetMetadatas/AssetMetadata/title', fatal=True) |
|||
thumbnails = [{ |
|||
'url': s.text |
|||
} for s in video_data.findall('.//ImageRepresentation/url')] |
|||
timestamp = parse_iso8601(xpath_text(video_data, './createdDate')) |
|||
# The <duration> field in XML is different from the exact duration, skipping |
|||
|
|||
formats = [] |
|||
for item in video_data.findall('./Playlists/Playlist') + video_data.findall('./Downloads/Download'): |
|||
for url_node in item.findall('url'): |
|||
quality = url_node.attrib['quality'] |
|||
full_url = url_node.text |
|||
original_ext = determine_ext(full_url).lower() |
|||
format_id = '%s-%s' % (quality, item.attrib['protocol']) |
|||
if original_ext == 'f4m': |
|||
formats.extend(self._extract_f4m_formats( |
|||
full_url + '?hdcore=3.4.0', display_id, f4m_id=format_id)) |
|||
elif original_ext == 'm3u8': |
|||
formats.extend(self._extract_m3u8_formats( |
|||
full_url, display_id, 'mp4', m3u8_id=format_id)) |
|||
else: |
|||
formats.append({ |
|||
'url': full_url, |
|||
'ext': original_ext, |
|||
'format_id': format_id, |
|||
'quality': 0 if 'HD' in quality else -1, |
|||
'preference': 1, |
|||
}) |
|||
|
|||
self._sort_formats(formats) |
|||
|
|||
subtitles = {} |
|||
subtitles_data = video_data.find('Subtitles') |
|||
if subtitles_data is not None: |
|||
subtitles_list = [{ |
|||
'url': sub.text, |
|||
'ext': determine_ext(sub.text), |
|||
} for sub in subtitles_data] |
|||
if subtitles_list: |
|||
subtitles['de'] = subtitles_list |
|||
|
|||
return { |
|||
'id': video_id, |
|||
'display_id': display_id, |
|||
'formats': formats, |
|||
'title': title, |
|||
'thumbnails': thumbnails, |
|||
'timestamp': timestamp, |
|||
'subtitles': subtitles, |
|||
} |
|||
@ -0,0 +1,167 @@ |
|||
# coding: utf-8 |
|||
from __future__ import unicode_literals |
|||
|
|||
import re |
|||
|
|||
from .common import InfoExtractor |
|||
from ..utils import ( |
|||
ExtractorError, |
|||
parse_iso8601, |
|||
qualities, |
|||
) |
|||
|
|||
|
|||
class SRGSSRIE(InfoExtractor): |
|||
_VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)' |
|||
|
|||
_ERRORS = { |
|||
'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.', |
|||
'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.', |
|||
# 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.', |
|||
'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.', |
|||
'LEGAL': 'The video cannot be transmitted for legal reasons.', |
|||
'STARTDATE': 'This video is not yet available. Please try again later.', |
|||
} |
|||
|
|||
def get_media_data(self, bu, media_type, media_id): |
|||
media_data = self._download_json( |
|||
'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id), |
|||
media_id)[media_type.capitalize()] |
|||
|
|||
if media_data.get('block') and media_data['block'] in self._ERRORS: |
|||
raise ExtractorError('%s said: %s' % (self.IE_NAME, self._ERRORS[media_data['block']]), expected=True) |
|||
|
|||
return media_data |
|||
|
|||
def _real_extract(self, url): |
|||
bu, media_type, media_id = re.match(self._VALID_URL, url).groups() |
|||
|
|||
if bu == 'rts': |
|||
return self.url_result('rts:%s' % media_id, 'RTS') |
|||
|
|||
media_data = self.get_media_data(bu, media_type, media_id) |
|||
|
|||
metadata = media_data['AssetMetadatas']['AssetMetadata'][0] |
|||
title = metadata['title'] |
|||
description = metadata.get('description') |
|||
created_date = media_data.get('createdDate') or metadata.get('createdDate') |
|||
timestamp = parse_iso8601(created_date) |
|||
|
|||
thumbnails = [] |
|||
if 'Image' in media_data: |
|||
for image in media_data['Image']['ImageRepresentations']['ImageRepresentation']: |
|||
thumbnails.append({ |
|||
'id': image.get('id'), |
|||
'url': image['url'], |
|||
}) |
|||
|
|||
preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD']) |
|||
formats = [] |
|||
for source in media_data['Playlists']['Playlist']: |
|||
assets = {} |
|||
protocol = source.get('@protocol') |
|||
if protocol in ('HTTP-HDS', 'HTTP-HLS'): |
|||
for quality in source['url']: |
|||
assets[quality['@quality']] = quality['text'] |
|||
asset_url = assets.get('HD') or assets.get('HQ') or assets.get('SD') or assets.get('MQ') or assets.get('LQ') |
|||
if '.f4m' in asset_url: |
|||
f4m_formats = formats.extend(self._extract_f4m_formats(asset_url + '?hdcore=3.4.0', media_id, f4m_id='hds', fatal=False)) |
|||
if f4m_formats: |
|||
formats.extend(f4m_formats) |
|||
elif '.m3u8' in asset_url: |
|||
m3u8_formats = formats.extend(self._extract_m3u8_formats(asset_url, media_id, m3u8_id='hls', fatal=False)) |
|||
if m3u8_formats: |
|||
formats.extend(m3u8_formats) |
|||
else: |
|||
for asset in source['url']: |
|||
asset_url = asset['text'] |
|||
ext = None |
|||
if asset_url.startswith('rtmp'): |
|||
ext = self._search_regex(r'([a-z0-9]+):[^/]+', asset_url, 'ext') |
|||
formats.append({ |
|||
'format_id': asset['@quality'], |
|||
'url': asset_url, |
|||
'preference': preference(asset['@quality']), |
|||
'ext': ext, |
|||
}) |
|||
|
|||
if 'Downloads' in media_data: |
|||
for source in media_data['Downloads']['Download']: |
|||
for asset in source['url']: |
|||
formats.append({ |
|||
'format_id': asset['@quality'], |
|||
'url': asset['text'], |
|||
'preference': preference(asset['@quality']) |
|||
}) |
|||
self._sort_formats(formats) |
|||
|
|||
return { |
|||
'id': media_id, |
|||
'title': title, |
|||
'description': description, |
|||
'timestamp': timestamp, |
|||
'thumbnails': thumbnails, |
|||
'formats': formats, |
|||
} |
|||
|
|||
|
|||
class SRGSSRPlayIE(InfoExtractor): |
|||
_VALID_URL = r'https?://(?:(?:www|play)\.)?(?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/[^/]+/(?P<type>video|audio)/[^?]+\?id=(?P<id>[0-9a-f\-]{36}|\d+)' |
|||
|
|||
_TESTS = [{ |
|||
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5', |
|||
'md5': '4cd93523723beff51bb4bee974ee238d', |
|||
'info_dict': { |
|||
'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5', |
|||
'ext': 'm4v', |
|||
'upload_date': '20130701', |
|||
'title': 'Snowden beantragt Asyl in Russland', |
|||
'timestamp': 1372713995, |
|||
} |
|||
}, { |
|||
# No Speichern (Save) button |
|||
'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa', |
|||
'md5': '0a274ce38fda48c53c01890651985bc6', |
|||
'info_dict': { |
|||
'id': '677f5829-e473-4823-ac83-a1087fe97faa', |
|||
'ext': 'flv', |
|||
'upload_date': '20130710', |
|||
'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive', |
|||
'description': 'md5:88604432b60d5a38787f152dec89cd56', |
|||
'timestamp': 1373493600, |
|||
}, |
|||
}, { |
|||
'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc', |
|||
'info_dict': { |
|||
'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc', |
|||
'ext': 'mp3', |
|||
'upload_date': '20151013', |
|||
'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem', |
|||
'timestamp': 1444750398, |
|||
}, |
|||
'params': { |
|||
# rtmp download |
|||
'skip_download': True, |
|||
}, |
|||
}, { |
|||
'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260', |
|||
'md5': '67a2a9ae4e8e62a68d0e9820cc9782df', |
|||
'info_dict': { |
|||
'id': '6348260', |
|||
'display_id': '6348260', |
|||
'ext': 'flv', |
|||
'duration': 1796, |
|||
'title': 'Le 19h30', |
|||
'description': '', |
|||
'uploader': '19h30', |
|||
'upload_date': '20141201', |
|||
'timestamp': 1417458600, |
|||
'thumbnail': 're:^https?://.*\.image', |
|||
'view_count': int, |
|||
}, |
|||
}] |
|||
|
|||
def _real_extract(self, url): |
|||
bu, media_type, media_id = re.match(self._VALID_URL, url).groups() |
|||
# other info can be extracted from url + '&layout=json' |
|||
return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR') |
|||
Write
Preview
Loading…
Cancel
Save