dntt1
commit
b4c763e660
1
AUTHORS
1
AUTHORS
@ -168,3 +168,4 @@ José Joaquín Atria
|
||||
Viťas Strádal
|
||||
Kagami Hiiragi
|
||||
Philip Huppert
|
||||
blahgeek
|
||||
|
||||
@ -1,13 +1,9 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
qualities,
|
||||
unified_strdate,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
@ -19,14 +15,14 @@ class CCCIE(InfoExtractor):
|
||||
'url': 'https://media.ccc.de/v/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor#video',
|
||||
'md5': '3a1eda8f3a29515d27f5adb967d7e740',
|
||||
'info_dict': {
|
||||
'id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
|
||||
'id': '1839',
|
||||
'ext': 'mp4',
|
||||
'title': 'Introduction to Processor Design',
|
||||
'description': 'md5:80be298773966f66d56cb11260b879af',
|
||||
'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'view_count': int,
|
||||
'upload_date': '20131228',
|
||||
'duration': 3660,
|
||||
'timestamp': 1388188800,
|
||||
'duration': 3710,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
|
||||
@ -34,79 +30,48 @@ class CCCIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
event_id = self._search_regex("data-id='(\d+)'", webpage, 'event id')
|
||||
event_data = self._download_json('https://media.ccc.de/public/events/%s' % event_id, event_id)
|
||||
|
||||
if self._downloader.params.get('prefer_free_formats'):
|
||||
preference = qualities(['mp3', 'opus', 'mp4-lq', 'webm-lq', 'h264-sd', 'mp4-sd', 'webm-sd', 'mp4', 'webm', 'mp4-hd', 'h264-hd', 'webm-hd'])
|
||||
else:
|
||||
preference = qualities(['opus', 'mp3', 'webm-lq', 'mp4-lq', 'webm-sd', 'h264-sd', 'mp4-sd', 'webm', 'mp4', 'webm-hd', 'mp4-hd', 'h264-hd'])
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'(?s)<h1>(.*?)</h1>', webpage, 'title')
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<h3>About</h3>(.+?)<h3>',
|
||||
webpage, 'description', fatal=False)
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r"(?s)<span[^>]+class='[^']*fa-calendar-o'[^>]*>(.+?)</span>",
|
||||
webpage, 'upload date', fatal=False))
|
||||
view_count = int_or_none(self._html_search_regex(
|
||||
r"(?s)<span class='[^']*fa-eye'></span>(.*?)</li>",
|
||||
webpage, 'view count', fatal=False))
|
||||
duration = parse_duration(self._html_search_regex(
|
||||
r'(?s)<span[^>]+class=(["\']).*?fa-clock-o.*?\1[^>]*></span>(?P<duration>.+?)</li',
|
||||
webpage, 'duration', fatal=False, group='duration'))
|
||||
|
||||
matches = re.finditer(r'''(?xs)
|
||||
<(?:span|div)\s+class='label\s+filetype'>(?P<format>[^<]*)</(?:span|div)>\s*
|
||||
<(?:span|div)\s+class='label\s+filetype'>(?P<lang>[^<]*)</(?:span|div)>\s*
|
||||
<a\s+download\s+href='(?P<http_url>[^']+)'>\s*
|
||||
(?:
|
||||
.*?
|
||||
<a\s+(?:download\s+)?href='(?P<torrent_url>[^']+\.torrent)'
|
||||
)?''', webpage)
|
||||
formats = []
|
||||
for m in matches:
|
||||
format = m.group('format')
|
||||
format_id = self._search_regex(
|
||||
r'.*/([a-z0-9_-]+)/[^/]*$',
|
||||
m.group('http_url'), 'format id', default=None)
|
||||
if format_id:
|
||||
format_id = m.group('lang') + '-' + format_id
|
||||
vcodec = 'h264' if 'h264' in format_id else (
|
||||
'none' if format_id in ('mp3', 'opus') else None
|
||||
for recording in event_data.get('recordings', []):
|
||||
recording_url = recording.get('recording_url')
|
||||
if not recording_url:
|
||||
continue
|
||||
language = recording.get('language')
|
||||
folder = recording.get('folder')
|
||||
format_id = None
|
||||
if language:
|
||||
format_id = language
|
||||
if folder:
|
||||
if language:
|
||||
format_id += '-' + folder
|
||||
else:
|
||||
format_id = folder
|
||||
vcodec = 'h264' if 'h264' in folder else (
|
||||
'none' if folder in ('mp3', 'opus') else None
|
||||
)
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'format': format,
|
||||
'language': m.group('lang'),
|
||||
'url': m.group('http_url'),
|
||||
'url': recording_url,
|
||||
'width': int_or_none(recording.get('width')),
|
||||
'height': int_or_none(recording.get('height')),
|
||||
'filesize': int_or_none(recording.get('size'), invscale=1024 * 1024),
|
||||
'language': language,
|
||||
'vcodec': vcodec,
|
||||
'preference': preference(format_id),
|
||||
})
|
||||
|
||||
if m.group('torrent_url'):
|
||||
formats.append({
|
||||
'format_id': 'torrent-%s' % (format if format_id is None else format_id),
|
||||
'format': '%s (torrent)' % format,
|
||||
'proto': 'torrent',
|
||||
'format_note': '(unsupported; will just download the .torrent file)',
|
||||
'vcodec': vcodec,
|
||||
'preference': -100 + preference(format_id),
|
||||
'url': m.group('torrent_url'),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._html_search_regex(
|
||||
r"<video.*?poster='([^']+)'", webpage, 'thumbnail', fatal=False)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'view_count': view_count,
|
||||
'upload_date': upload_date,
|
||||
'duration': duration,
|
||||
'id': event_id,
|
||||
'display_id': display_id,
|
||||
'title': event_data['title'],
|
||||
'description': event_data.get('description'),
|
||||
'thumbnail': event_data.get('thumb_url'),
|
||||
'timestamp': parse_iso8601(event_data.get('date')),
|
||||
'duration': int_or_none(event_data.get('length')),
|
||||
'tags': event_data.get('tags'),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -33,6 +33,7 @@ class DiscoveryIE(InfoExtractor):
|
||||
'duration': 156,
|
||||
'timestamp': 1302032462,
|
||||
'upload_date': '20110405',
|
||||
'uploader_id': '103207',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # requires ffmpeg
|
||||
@ -54,7 +55,11 @@ class DiscoveryIE(InfoExtractor):
|
||||
'upload_date': '20140725',
|
||||
'timestamp': 1406246400,
|
||||
'duration': 116,
|
||||
'uploader_id': '103207',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # requires ffmpeg
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -66,13 +71,19 @@ class DiscoveryIE(InfoExtractor):
|
||||
entries = []
|
||||
|
||||
for idx, video_info in enumerate(info['playlist']):
|
||||
formats = self._extract_m3u8_formats(
|
||||
video_info['src'], display_id, 'mp4', 'm3u8_native', m3u8_id='hls',
|
||||
note='Download m3u8 information for video %d' % (idx + 1))
|
||||
self._sort_formats(formats)
|
||||
subtitles = []
|
||||
caption_url = video_info.get('captionsUrl')
|
||||
if caption_url:
|
||||
subtitles = {
|
||||
'en': [{
|
||||
'url': caption_url,
|
||||
}]
|
||||
}
|
||||
|
||||
entries.append({
|
||||
'_type': 'url_transparent',
|
||||
'url': 'http://players.brightcove.net/103207/default_default/index.html?videoId=ref:%s' % video_info['referenceId'],
|
||||
'id': compat_str(video_info['id']),
|
||||
'formats': formats,
|
||||
'title': video_info['title'],
|
||||
'description': video_info.get('description'),
|
||||
'duration': parse_duration(video_info.get('video_length')),
|
||||
@ -80,6 +91,7 @@ class DiscoveryIE(InfoExtractor):
|
||||
'thumbnail': video_info.get('thumbnailURL'),
|
||||
'alt_title': video_info.get('secondary_title'),
|
||||
'timestamp': parse_iso8601(video_info.get('publishedDate')),
|
||||
'subtitles': subtitles,
|
||||
})
|
||||
|
||||
return self.playlist_result(entries, display_id, video_title)
|
||||
|
||||
@ -724,7 +724,10 @@ from .svt import (
|
||||
from .swrmediathek import SWRMediathekIE
|
||||
from .syfy import SyfyIE
|
||||
from .sztvhu import SztvHuIE
|
||||
from .tagesschau import TagesschauIE
|
||||
from .tagesschau import (
|
||||
TagesschauPlayerIE,
|
||||
TagesschauIE,
|
||||
)
|
||||
from .tapely import TapelyIE
|
||||
from .tass import TassIE
|
||||
from .tdslifeway import TDSLifewayIE
|
||||
|
||||
@ -125,10 +125,12 @@ class RtlNlIE(InfoExtractor):
|
||||
try:
|
||||
# Find hls format with the same width and height corresponding
|
||||
# to progressive format and copy metadata from it.
|
||||
f = next(f for f in formats
|
||||
if f.get('width') == width and f.get('height') == height).copy()
|
||||
f.update(pg_format(format_id, width, height))
|
||||
pg_formats.append(f)
|
||||
f = next(f for f in formats if f.get('height') == height)
|
||||
# hls formats may have invalid width
|
||||
f['width'] = width
|
||||
f_copy = f.copy()
|
||||
f_copy.update(pg_format(format_id, width, height))
|
||||
pg_formats.append(f_copy)
|
||||
except StopIteration:
|
||||
# Missing hls format does mean that no progressive format with
|
||||
# such width and height exists either.
|
||||
|
||||
@ -4,42 +4,178 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import parse_filesize
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
js_to_json,
|
||||
parse_iso8601,
|
||||
parse_filesize,
|
||||
)
|
||||
|
||||
|
||||
class TagesschauPlayerIE(InfoExtractor):
|
||||
IE_NAME = 'tagesschau:player'
|
||||
_VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?P<kind>audio|video)/(?P=kind)-(?P<id>\d+)~player(?:_[^/?#&]+)?\.html'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tagesschau.de/multimedia/video/video-179517~player.html',
|
||||
'md5': '8d09548d5c15debad38bee3a4d15ca21',
|
||||
'info_dict': {
|
||||
'id': '179517',
|
||||
'ext': 'mp4',
|
||||
'title': 'Marie Kristin Boese, ARD Berlin, über den zukünftigen Kurs der AfD',
|
||||
'thumbnail': 're:^https?:.*\.jpg$',
|
||||
'formats': 'mincount:6',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.tagesschau.de/multimedia/audio/audio-29417~player.html',
|
||||
'md5': '76e6eec6ebd40740671cf0a2c88617e5',
|
||||
'info_dict': {
|
||||
'id': '29417',
|
||||
'ext': 'mp3',
|
||||
'title': 'Trabi - Bye, bye Rennpappe',
|
||||
'thumbnail': 're:^https?:.*\.jpg$',
|
||||
'formats': 'mincount:2',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417~player_autoplay-true.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_FORMATS = {
|
||||
'xs': {'quality': 0},
|
||||
's': {'width': 320, 'height': 180, 'quality': 1},
|
||||
'm': {'width': 512, 'height': 288, 'quality': 2},
|
||||
'l': {'width': 960, 'height': 540, 'quality': 3},
|
||||
'xl': {'width': 1280, 'height': 720, 'quality': 4},
|
||||
'xxl': {'quality': 5},
|
||||
}
|
||||
|
||||
def _extract_via_api(self, kind, video_id):
|
||||
info = self._download_json(
|
||||
'https://www.tagesschau.de/api/multimedia/{0}/{0}-{1}.json'.format(kind, video_id),
|
||||
video_id)
|
||||
title = info['headline']
|
||||
formats = []
|
||||
for media in info['mediadata']:
|
||||
for format_id, format_url in media.items():
|
||||
if determine_ext(format_url) == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, video_id, 'mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='hls'))
|
||||
else:
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': format_id,
|
||||
'vcodec': 'none' if kind == 'audio' else None,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
timestamp = parse_iso8601(info.get('date'))
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'timestamp': timestamp,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
# kind = mobj.group('kind').lower()
|
||||
# if kind == 'video':
|
||||
# return self._extract_via_api(kind, video_id)
|
||||
|
||||
# JSON api does not provide some audio formats (e.g. ogg) thus
|
||||
# extractiong audio via webpage
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._og_search_title(webpage).strip()
|
||||
formats = []
|
||||
|
||||
for media_json in re.findall(r'({src\s*:\s*["\']http[^}]+type\s*:[^}]+})', webpage):
|
||||
media = self._parse_json(js_to_json(media_json), video_id, fatal=False)
|
||||
if not media:
|
||||
continue
|
||||
src = media.get('src')
|
||||
if not src:
|
||||
return
|
||||
quality = media.get('quality')
|
||||
kind = media.get('type', '').split('/')[0]
|
||||
ext = determine_ext(src)
|
||||
f = {
|
||||
'url': src,
|
||||
'format_id': '%s_%s' % (quality, ext) if quality else ext,
|
||||
'ext': ext,
|
||||
'vcodec': 'none' if kind == 'audio' else None,
|
||||
}
|
||||
f.update(self._FORMATS.get(quality, {}))
|
||||
formats.append(f)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class TagesschauIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tagesschau\.de/multimedia/(?:[^/]+/)*?[^/#?]+?(?P<id>-?[0-9]+)(?:~_[^/#?]+?)?\.html'
|
||||
_VALID_URL = r'https?://(?:www\.)?tagesschau\.de/(?P<path>[^/]+/(?:[^/]+/)*?(?P<id>[^/#?]+?(?:-?[0-9]+)?))(?:~_?[^/#?]+?)?\.html'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tagesschau.de/multimedia/video/video-102143.html',
|
||||
'md5': '917a228bc7df7850783bc47979673a09',
|
||||
'md5': 'f7c27a0eff3bfe8c7727e65f8fe1b1e6',
|
||||
'info_dict': {
|
||||
'id': '102143',
|
||||
'id': 'video-102143',
|
||||
'ext': 'mp4',
|
||||
'title': 'Regierungsumbildung in Athen: Neue Minister in Griechenland vereidigt',
|
||||
'description': 'md5:171feccd9d9b3dd54d05d501568f6359',
|
||||
'description': '18.07.2015 20:10 Uhr',
|
||||
'thumbnail': 're:^https?:.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/multimedia/sendung/ts-5727.html',
|
||||
'md5': '3c54c1f6243d279b706bde660ceec633',
|
||||
'info_dict': {
|
||||
'id': '5727',
|
||||
'id': 'ts-5727',
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:695c01bfd98b7e313c501386327aea59',
|
||||
'title': 'Sendung: tagesschau \t04.12.2014 20:00 Uhr',
|
||||
'description': 'md5:695c01bfd98b7e313c501386327aea59',
|
||||
'thumbnail': 're:^https?:.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/multimedia/politikimradio/audio-18407.html',
|
||||
'md5': 'aef45de271c4bf0a5db834aa40bf774c',
|
||||
# exclusive audio
|
||||
'url': 'http://www.tagesschau.de/multimedia/audio/audio-29417.html',
|
||||
'md5': '76e6eec6ebd40740671cf0a2c88617e5',
|
||||
'info_dict': {
|
||||
'id': '18407',
|
||||
'id': 'audio-29417',
|
||||
'ext': 'mp3',
|
||||
'title': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
|
||||
'description': 'Flüchtlingsdebatte: Hitzig, aber wenig hilfreich',
|
||||
'title': 'Trabi - Bye, bye Rennpappe',
|
||||
'description': 'md5:8687dda862cbbe2cfb2df09b56341317',
|
||||
'thumbnail': 're:^https?:.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
# audio in article
|
||||
'url': 'http://www.tagesschau.de/inland/bnd-303.html',
|
||||
'md5': 'e0916c623e85fc1d2b26b78f299d3958',
|
||||
'info_dict': {
|
||||
'id': 'bnd-303',
|
||||
'ext': 'mp3',
|
||||
'title': 'Viele Baustellen für neuen BND-Chef',
|
||||
'description': 'md5:1e69a54be3e1255b2b07cdbce5bcd8b4',
|
||||
'thumbnail': 're:^https?:.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/inland/afd-parteitag-135.html',
|
||||
'info_dict': {
|
||||
'id': 'afd-parteitag-135',
|
||||
'title': 'Möchtegern-Underdog mit Machtanspruch',
|
||||
},
|
||||
'playlist_count': 2,
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/multimedia/sendung/tsg-3771.html',
|
||||
'only_matching': True,
|
||||
@ -61,88 +197,108 @@ class TagesschauIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/multimedia/video/video-102303~_bab-sendung-211.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.tagesschau.de/100sekunden/index.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# playlist article with collapsing sections
|
||||
'url': 'http://www.tagesschau.de/wirtschaft/faq-freihandelszone-eu-usa-101.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_FORMATS = {
|
||||
's': {'width': 256, 'height': 144, 'quality': 1},
|
||||
'm': {'width': 512, 'height': 288, 'quality': 2},
|
||||
'l': {'width': 960, 'height': 544, 'quality': 3},
|
||||
}
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if TagesschauPlayerIE.suitable(url) else super(TagesschauIE, cls).suitable(url)
|
||||
|
||||
def _extract_formats(self, download_text, media_kind):
|
||||
links = re.finditer(
|
||||
r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
|
||||
download_text)
|
||||
formats = []
|
||||
for l in links:
|
||||
link_url = l.group('url')
|
||||
if not link_url:
|
||||
continue
|
||||
format_id = self._search_regex(
|
||||
r'.*/[^/.]+\.([^/]+)\.[^/.]+$', link_url, 'format ID',
|
||||
default=determine_ext(link_url))
|
||||
format = {
|
||||
'format_id': format_id,
|
||||
'url': l.group('url'),
|
||||
'format_name': l.group('name'),
|
||||
}
|
||||
title = l.group('title')
|
||||
if title:
|
||||
if media_kind.lower() == 'video':
|
||||
m = re.match(
|
||||
r'''(?x)
|
||||
Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
|
||||
(?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
|
||||
(?P<vbr>[0-9]+)kbps&\#10;
|
||||
Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
|
||||
Größe:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
|
||||
title)
|
||||
if m:
|
||||
format.update({
|
||||
'format_note': m.group('audio_desc'),
|
||||
'vcodec': m.group('vcodec'),
|
||||
'width': int(m.group('width')),
|
||||
'height': int(m.group('height')),
|
||||
'abr': int(m.group('abr')),
|
||||
'vbr': int(m.group('vbr')),
|
||||
'filesize_approx': parse_filesize(m.group('filesize_approx')),
|
||||
})
|
||||
else:
|
||||
m = re.match(
|
||||
r'(?P<format>.+?)-Format\s*:\s*(?P<abr>\d+)kbps\s*,\s*(?P<note>.+)',
|
||||
title)
|
||||
if m:
|
||||
format.update({
|
||||
'format_note': '%s, %s' % (m.group('format'), m.group('note')),
|
||||
'vcodec': 'none',
|
||||
'abr': int(m.group('abr')),
|
||||
})
|
||||
formats.append(format)
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id') or mobj.group('path')
|
||||
display_id = video_id.lstrip('-')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
player_url = self._html_search_meta(
|
||||
'twitter:player', webpage, 'player URL', default=None)
|
||||
if player_url:
|
||||
playerpage = self._download_webpage(
|
||||
player_url, display_id, 'Downloading player page')
|
||||
title = self._html_search_regex(
|
||||
r'<span[^>]*class="headline"[^>]*>(.+?)</span>',
|
||||
webpage, 'title', default=None) or self._og_search_title(webpage)
|
||||
|
||||
formats = []
|
||||
for media in re.finditer(
|
||||
r'''(?x)
|
||||
(?P<q_url>["\'])(?P<url>http://media.+?)(?P=q_url)
|
||||
,\s*type:(?P<q_type>["\'])(?P<type>video|audio)/(?P<ext>.+?)(?P=q_type)
|
||||
(?:,\s*quality:(?P<q_quality>["\'])(?P<quality>.+?)(?P=q_quality))?
|
||||
''', playerpage):
|
||||
url = media.group('url')
|
||||
type_ = media.group('type')
|
||||
ext = media.group('ext')
|
||||
res = media.group('quality')
|
||||
f = {
|
||||
'format_id': '%s_%s' % (res, ext) if res else ext,
|
||||
'url': url,
|
||||
'ext': ext,
|
||||
'vcodec': 'none' if type_ == 'audio' else None,
|
||||
}
|
||||
f.update(self._FORMATS.get(res, {}))
|
||||
formats.append(f)
|
||||
thumbnail = self._og_search_thumbnail(playerpage)
|
||||
title = self._og_search_title(webpage).strip()
|
||||
description = self._og_search_description(webpage).strip()
|
||||
else:
|
||||
DOWNLOAD_REGEX = r'(?s)<p>Wir bieten dieses (?P<kind>Video|Audio) in folgenden Formaten zum Download an:</p>\s*<div class="controls">(?P<links>.*?)</div>\s*<p>'
|
||||
|
||||
webpage_type = self._og_search_property('type', webpage, default=None)
|
||||
if webpage_type == 'website': # Article
|
||||
entries = []
|
||||
for num, (entry_title, media_kind, download_text) in enumerate(re.findall(
|
||||
r'(?s)<p[^>]+class="infotext"[^>]*>\s*(?:<a[^>]+>)?\s*<strong>(.+?)</strong>.*?</p>.*?%s' % DOWNLOAD_REGEX,
|
||||
webpage), 1):
|
||||
entries.append({
|
||||
'id': '%s-%d' % (display_id, num),
|
||||
'title': '%s' % entry_title,
|
||||
'formats': self._extract_formats(download_text, media_kind),
|
||||
})
|
||||
if len(entries) > 1:
|
||||
return self.playlist_result(entries, display_id, title)
|
||||
formats = entries[0]['formats']
|
||||
else: # Assume single video
|
||||
download_text = self._search_regex(
|
||||
r'(?s)<p>Wir bieten dieses Video in folgenden Formaten zum Download an:</p>\s*<div class="controls">(.*?)</div>\s*<p>',
|
||||
webpage, 'download links')
|
||||
links = re.finditer(
|
||||
r'<div class="button" title="(?P<title>[^"]*)"><a href="(?P<url>[^"]+)">(?P<name>.+?)</a></div>',
|
||||
download_text)
|
||||
formats = []
|
||||
for l in links:
|
||||
format_id = self._search_regex(
|
||||
r'.*/[^/.]+\.([^/]+)\.[^/.]+', l.group('url'), 'format ID')
|
||||
format = {
|
||||
'format_id': format_id,
|
||||
'url': l.group('url'),
|
||||
'format_name': l.group('name'),
|
||||
}
|
||||
m = re.match(
|
||||
r'''(?x)
|
||||
Video:\s*(?P<vcodec>[a-zA-Z0-9/._-]+)\s*&\#10;
|
||||
(?P<width>[0-9]+)x(?P<height>[0-9]+)px&\#10;
|
||||
(?P<vbr>[0-9]+)kbps&\#10;
|
||||
Audio:\s*(?P<abr>[0-9]+)kbps,\s*(?P<audio_desc>[A-Za-z\.0-9]+)&\#10;
|
||||
Größe:\s*(?P<filesize_approx>[0-9.,]+\s+[a-zA-Z]*B)''',
|
||||
l.group('title'))
|
||||
if m:
|
||||
format.update({
|
||||
'format_note': m.group('audio_desc'),
|
||||
'vcodec': m.group('vcodec'),
|
||||
'width': int(m.group('width')),
|
||||
'height': int(m.group('height')),
|
||||
'abr': int(m.group('abr')),
|
||||
'vbr': int(m.group('vbr')),
|
||||
'filesize_approx': parse_filesize(m.group('filesize_approx')),
|
||||
})
|
||||
formats.append(format)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<p class="teasertext">(.*?)</p>',
|
||||
webpage, 'description', default=None)
|
||||
title = self._html_search_regex(
|
||||
r'<span class="headline".*?>(.*?)</span>', webpage, 'title')
|
||||
DOWNLOAD_REGEX, webpage, 'download links', group='links')
|
||||
media_kind = self._search_regex(
|
||||
DOWNLOAD_REGEX, webpage, 'media kind', default='Video', group='kind')
|
||||
formats = self._extract_formats(download_text, media_kind)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<p class="teasertext">(.*?)</p>',
|
||||
webpage, 'description', default=None)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
||||
@ -389,23 +389,30 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
|
||||
class FFmpegMetadataPP(FFmpegPostProcessor):
|
||||
def run(self, info):
|
||||
metadata = {}
|
||||
if info.get('title') is not None:
|
||||
metadata['title'] = info['title']
|
||||
if info.get('upload_date') is not None:
|
||||
metadata['date'] = info['upload_date']
|
||||
if info.get('artist') is not None:
|
||||
metadata['artist'] = info['artist']
|
||||
elif info.get('uploader') is not None:
|
||||
metadata['artist'] = info['uploader']
|
||||
elif info.get('uploader_id') is not None:
|
||||
metadata['artist'] = info['uploader_id']
|
||||
if info.get('description') is not None:
|
||||
metadata['description'] = info['description']
|
||||
metadata['comment'] = info['description']
|
||||
if info.get('webpage_url') is not None:
|
||||
metadata['purl'] = info['webpage_url']
|
||||
if info.get('album') is not None:
|
||||
metadata['album'] = info['album']
|
||||
|
||||
def add(meta_list, info_list=None):
|
||||
if not info_list:
|
||||
info_list = meta_list
|
||||
if not isinstance(meta_list, (list, tuple)):
|
||||
meta_list = (meta_list,)
|
||||
if not isinstance(info_list, (list, tuple)):
|
||||
info_list = (info_list,)
|
||||
for info_f in info_list:
|
||||
if info.get(info_f) is not None:
|
||||
for meta_f in meta_list:
|
||||
metadata[meta_f] = info[info_f]
|
||||
break
|
||||
|
||||
add('title', ('track', 'title'))
|
||||
add('date', 'upload_date')
|
||||
add(('description', 'comment'), 'description')
|
||||
add('purl', 'webpage_url')
|
||||
add('track', 'track_number')
|
||||
add('artist', ('artist', 'creator', 'uploader', 'uploader_id'))
|
||||
add('genre')
|
||||
add('album')
|
||||
add('album_artist')
|
||||
add('disc', 'disc_number')
|
||||
|
||||
if not metadata:
|
||||
self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add')
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user