mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[dplay] Improve, extract all formats and metadata (Closes #8463)
This commit is contained in:
Sergey M․
parent
9505053704
commit
940b606a07
1 changed files with 103 additions and 69 deletions
|
|
@ -1,97 +1,131 @@
|
||||||
# encoding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import json
|
||||||
|
import re
|
||||||
import time
|
import time
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import int_or_none
|
from ..utils import int_or_none
|
||||||
from ..compat import compat_urlparse
|
|
||||||
|
|
||||||
class DPlayIE(InfoExtractor):
|
class DPlayIE(InfoExtractor):
|
||||||
_VALID_URL = r'(?P<domain>http://(?:it|www)\.dplay\.(?:com|dk|se))/[^/]+/(?P<id>[^/?#]+)'
|
_VALID_URL = r'http://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se))/[^/]+/(?P<id>[^/?#]+)'
|
||||||
|
|
||||||
_TESTS = [
|
_TESTS = [{
|
||||||
{
|
|
||||||
'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',
|
'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '1255600',
|
'id': '1255600',
|
||||||
'ext': 'mp4',
|
|
||||||
'display_id': 'stagione-1-episodio-25',
|
'display_id': 'stagione-1-episodio-25',
|
||||||
|
'ext': 'mp4',
|
||||||
'title': 'Episodio 25',
|
'title': 'Episodio 25',
|
||||||
|
'description': 'md5:cae5f40ad988811b197d2d27a53227eb',
|
||||||
'duration': 2761,
|
'duration': 2761,
|
||||||
'description': "Gabriele Corsi conduce un nuovo provocante e divertente dating show. 30 ragazze single hanno l'opportunità di conoscere un ragazzo e decidere se tenerlo in gioco oppure no accendendo o spegnendo le luci.",
|
'timestamp': 1454701800,
|
||||||
|
'upload_date': '20160205',
|
||||||
|
'creator': 'RTIT',
|
||||||
|
'series': 'Take me out',
|
||||||
'season_number': 1,
|
'season_number': 1,
|
||||||
'episode_number': 25,
|
'episode_number': 25,
|
||||||
|
'age_limit': 0,
|
||||||
},
|
},
|
||||||
},
|
'expected_warnings': ['Unable to download f4m manifest'],
|
||||||
{
|
}, {
|
||||||
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
|
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '3172',
|
'id': '3172',
|
||||||
'ext': 'mp4',
|
|
||||||
'display_id': 'season-1-svensken-lar-sig-njuta-av-livet',
|
'display_id': 'season-1-svensken-lar-sig-njuta-av-livet',
|
||||||
|
'ext': 'flv',
|
||||||
'title': 'Svensken lär sig njuta av livet',
|
'title': 'Svensken lär sig njuta av livet',
|
||||||
|
'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
|
||||||
'duration': 2650,
|
'duration': 2650,
|
||||||
'description': "\"Svensken lär sig njuta av livet\". Införandet av systembolaget, industrisemestern och Skarastadgan. Med hjälp av arkivmaterial, experter och fakta ska händelserna dissekeras, analyseras och dras till sin absoluta underhållningsspets.",
|
'timestamp': 1365454320,
|
||||||
|
'upload_date': '20130408',
|
||||||
|
'creator': 'Kanal 5 (Home)',
|
||||||
|
'series': 'Nugammalt - 77 händelser som format Sverige',
|
||||||
'season_number': 1,
|
'season_number': 1,
|
||||||
'episode_number': 1,
|
'episode_number': 1,
|
||||||
|
'age_limit': 0,
|
||||||
},
|
},
|
||||||
},
|
}, {
|
||||||
{
|
|
||||||
'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
|
'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '70816',
|
'id': '70816',
|
||||||
'ext': 'mp4',
|
|
||||||
'display_id': 'season-6-episode-12',
|
'display_id': 'season-6-episode-12',
|
||||||
|
'ext': 'flv',
|
||||||
'title': 'Episode 12',
|
'title': 'Episode 12',
|
||||||
|
'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
|
||||||
'duration': 2563,
|
'duration': 2563,
|
||||||
'description': " I sæsonafslutningen sker der store ting for mor og datter.\nDagen er endelig kommet for den højgravide Irina - hun skal føde! Men det bliver en lang og sej kamp for Irina, som selvfølgelig har mor Mila med som støtte hele vejen.\nMor Jette og Jessica er igen hjemme i Danmark efter deres store USA-eventyr. Og for at holde fast i den amerikanske ånd, tager pigerne i dag til gospel-undervisning. \nOg så skal Joy og mor Mia under kniven - de skal nemlig have gjort lårene mindre og ballerne større. \n ",
|
'timestamp': 1429696800,
|
||||||
|
'upload_date': '20150422',
|
||||||
|
'creator': 'Kanal 4',
|
||||||
|
'series': 'Mig og min mor',
|
||||||
'season_number': 6,
|
'season_number': 6,
|
||||||
'episode_number': 12,
|
'episode_number': 12,
|
||||||
|
'age_limit': 0,
|
||||||
},
|
},
|
||||||
}
|
}]
|
||||||
]
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
#this extrator works with it.dplay.com, www.dplay.se and www.dplay.dk
|
mobj = re.match(self._VALID_URL, url)
|
||||||
# so we need to determine the domain to send the requests to
|
display_id = mobj.group('id')
|
||||||
domain = self._search_regex(self._VALID_URL, url, 'domain')
|
domain = mobj.group('domain')
|
||||||
display_id = self._match_id(url)
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
video_id = self._search_regex(
|
video_id = self._search_regex(
|
||||||
r'data-video-id="(\d+)"', webpage, 'video id')
|
r'data-video-id=["\'](\d+)', webpage, 'video id')
|
||||||
|
|
||||||
video_url = compat_urlparse.urljoin(domain, 'api/v2/ajax/videos?video_id=')
|
info = self._download_json(
|
||||||
|
'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
|
||||||
info = self._download_json(video_url + video_id,
|
|
||||||
video_id)['data'][0]
|
video_id)['data'][0]
|
||||||
|
|
||||||
# TODO: consider adding support for 'stream_type=hds', it seems to
|
title = info['title']
|
||||||
# require setting some cookies
|
|
||||||
# get url's TLD to determine which cookie and url to use
|
PROTOCOLS = ('hls', 'hds')
|
||||||
|
formats = []
|
||||||
|
|
||||||
|
def extract_formats(protocol, manifest_url):
|
||||||
|
if protocol == 'hls':
|
||||||
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
manifest_url, video_id, ext='mp4',
|
||||||
|
entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False))
|
||||||
|
elif protocol == 'hds':
|
||||||
|
formats.extend(self._extract_f4m_formats(
|
||||||
|
manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
|
||||||
|
video_id, f4m_id=protocol, fatal=False))
|
||||||
|
|
||||||
domain_tld = domain.split('.')[-1]
|
domain_tld = domain.split('.')[-1]
|
||||||
if domain_tld == 'se' or domain_tld == 'dk':
|
if domain_tld in ('se', 'dk'):
|
||||||
|
for protocol in PROTOCOLS:
|
||||||
self._set_cookie(
|
self._set_cookie(
|
||||||
'secure.dplay.%s' % domain_tld, 'dsc-geo',
|
'secure.dplay.%s' % domain_tld, 'dsc-geo',
|
||||||
'{"countryCode":"%s","expiry":%d}' % (domain_tld.upper(), ((time.time() + 20 * 60) * 1000)))
|
json.dumps({
|
||||||
|
'countryCode': domain_tld.upper(),
|
||||||
manifest_url = self._download_json(
|
'expiry': (time.time() + 20 * 60) * 1000,
|
||||||
'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=hls' % (domain_tld, video_id),
|
}))
|
||||||
video_id, 'Getting manifest url for hls stream')['hls']
|
stream = self._download_json(
|
||||||
|
'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
|
||||||
|
% (domain_tld, video_id, protocol), video_id,
|
||||||
|
'Downloading %s stream JSON' % protocol, fatal=False)
|
||||||
|
if stream and stream.get(protocol):
|
||||||
|
extract_formats(protocol, stream[protocol])
|
||||||
else:
|
else:
|
||||||
#.it requires no cookies at this point
|
for protocol in PROTOCOLS:
|
||||||
manifest_url = info['hls']
|
if info.get(protocol):
|
||||||
|
extract_formats(protocol, info[protocol])
|
||||||
formats = self._extract_m3u8_formats(
|
|
||||||
manifest_url, video_id, ext='mp4', entry_protocol='m3u8_native')
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
'title': info['title'],
|
'title': title,
|
||||||
'formats': formats,
|
|
||||||
'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
|
|
||||||
'description': info.get('video_metadata_longDescription'),
|
'description': info.get('video_metadata_longDescription'),
|
||||||
|
'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
|
||||||
|
'timestamp': int_or_none(info.get('video_publish_date')),
|
||||||
|
'creator': info.get('video_metadata_homeChannel'),
|
||||||
|
'series': info.get('video_metadata_show'),
|
||||||
'season_number': int_or_none(info.get('season')),
|
'season_number': int_or_none(info.get('season')),
|
||||||
'episode_number': int_or_none(info.get('episode')),
|
'episode_number': int_or_none(info.get('episode')),
|
||||||
|
'age_limit': int_or_none(info.get('minimum_age')),
|
||||||
|
'formats': formats,
|
||||||
}
|
}
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue