youtube-dl/youtube_dl/extractor/mediaset.py

138 lines
5.4 KiB
Python
Raw Normal View History

2017-05-02 23:17:15 +09:00
# coding: utf-8
from __future__ import unicode_literals
2017-05-14 08:28:40 +09:00
import re
from .theplatform import ThePlatformBaseIE
2017-05-02 23:17:15 +09:00
from ..utils import (
ExtractorError,
int_or_none,
update_url_query,
2017-05-02 23:17:15 +09:00
)
class MediasetIE(ThePlatformBaseIE):
_TP_TLD = 'eu'
_VALID_URL = r'''(?x)
2017-05-14 08:28:40 +09:00
(?:
mediaset:|
https?://
(?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
2017-05-14 08:28:40 +09:00
(?:
(?:video|on-demand)/(?:[^/]+/)+[^/]+_|
player/index\.html\?.*?\bprogramGuid=
2017-05-14 08:28:40 +09:00
)
)(?P<id>[0-9A-Z]{16})
'''
2017-05-02 23:17:15 +09:00
_TESTS = [{
# full episode
'url': 'https://www.mediasetplay.mediaset.it/video/hellogoodbye/quarta-puntata_FAFU000000661824',
2017-05-02 23:17:15 +09:00
'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
'info_dict': {
'id': 'FAFU000000661824',
2017-05-02 23:17:15 +09:00
'ext': 'mp4',
'title': 'Quarta puntata',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1414.26,
2017-05-14 08:39:47 +09:00
'upload_date': '20161107',
'series': 'Hello Goodbye',
'timestamp': 1478532900,
'uploader': 'Rete 4',
'uploader_id': 'R4',
},
2018-06-18 18:50:06 +09:00
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
'md5': '288532f0ad18307705b01e581304cd7b',
2018-06-18 18:50:06 +09:00
'info_dict': {
'id': 'F309013801000501',
2018-06-18 18:50:06 +09:00
'ext': 'mp4',
'title': 'Puntata del 25 maggio',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2018-06-18 18:50:06 +09:00
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 6565.007,
'upload_date': '20180526',
2018-06-18 18:50:06 +09:00
'series': 'Matrix',
'timestamp': 1527326245,
'uploader': 'Canale 5',
'uploader_id': 'C5',
2018-06-18 18:50:06 +09:00
},
'expected_warnings': ['HTTP Error 403: Forbidden'],
2017-05-02 23:17:15 +09:00
}, {
# clip
'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
'only_matching': True,
2017-05-02 23:17:15 +09:00
}, {
# iframe simple
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
'only_matching': True,
2017-05-02 23:17:15 +09:00
}, {
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
'only_matching': True,
2017-05-14 08:28:40 +09:00
}, {
'url': 'mediaset:FAFU000000665924',
2017-05-14 08:28:40 +09:00
'only_matching': True,
2017-05-02 23:17:15 +09:00
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
webpage)]
2017-05-02 23:17:15 +09:00
def _real_extract(self, url):
guid = self._match_id(url)
tp_path = 'PR1GhC/media/guid/2702976343/' + guid
info = self._extract_theplatform_metadata(tp_path, guid)
2017-05-02 23:17:15 +09:00
formats = []
subtitles = {}
first_e = None
for asset_type in ('SD', 'HD'):
for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
'mbr': 'true',
'formats': f,
'assetTypes': asset_type,
}), guid, 'Downloading %s %s SMIL data' % (f, asset_type))
except ExtractorError as e:
if not first_e:
first_e = e
break
for tp_f in tp_formats:
tp_f['quality'] = 1 if asset_type == 'HD' else 0
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if first_e and not formats:
raise first_e
self._sort_formats(formats)
2017-05-02 23:17:15 +09:00
fields = []
for templ, repls in (('tvSeason%sNumber', ('', 'Episode')), ('mediasetprogram$%s', ('brandTitle', 'numberOfViews', 'publishInfo'))):
fields.extend(templ % repl for repl in repls)
feed_data = self._download_json(
'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs/guid/-/' + guid,
guid, fatal=False, query={'fields': ','.join(fields)})
if feed_data:
publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
info.update({
'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
'series': feed_data.get('mediasetprogram$brandTitle'),
'uploader': publish_info.get('description'),
'uploader_id': publish_info.get('channel'),
'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
})
2017-05-02 23:17:15 +09:00
info.update({
'id': guid,
'formats': formats,
'subtitles': subtitles,
})
return info