yt-dlp/yt_dlp/extractor/europa.py

174 lines
6.5 KiB
Python
Raw Normal View History

2015-08-12 16:59:04 +02:00
from .common import InfoExtractor
from ..utils import (
2015-10-02 18:29:15 +02:00
int_or_none,
orderedSet,
parse_duration,
parse_iso8601,
2021-08-22 21:02:00 +02:00
parse_qs,
2015-10-02 18:29:15 +02:00
qualities,
traverse_obj,
2015-10-02 18:29:15 +02:00
unified_strdate,
2015-08-12 16:59:04 +02:00
xpath_text
)
class EuropaIE(InfoExtractor):
2015-10-02 19:22:53 +02:00
_VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P<id>[A-Za-z0-9-]+)'
2015-10-02 18:29:15 +02:00
_TESTS = [{
2015-08-12 16:59:04 +02:00
'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758',
2015-10-02 18:29:15 +02:00
'md5': '574f080699ddd1e19a675b0ddf010371',
2015-08-12 16:59:04 +02:00
'info_dict': {
'id': 'I107758',
'ext': 'mp4',
'title': 'TRADE - Wikileaks on TTIP',
'description': 'NEW LIVE EC Midday press briefing of 11/08/2015',
'thumbnail': r're:^https?://.*\.jpg$',
2015-10-02 18:29:15 +02:00
'upload_date': '20150811',
'duration': 34,
'view_count': int,
'formats': 'mincount:3',
2015-08-12 16:59:04 +02:00
}
2015-10-02 18:29:15 +02:00
}, {
'url': 'http://ec.europa.eu/avservices/video/player.cfm?sitelang=en&ref=I107786',
'only_matching': True,
2015-10-02 19:22:53 +02:00
}, {
'url': 'http://ec.europa.eu/avservices/audio/audioDetails.cfm?ref=I-109295&sitelang=en',
'only_matching': True,
2015-10-02 18:29:15 +02:00
}]
2015-08-12 16:59:04 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2015-10-02 18:29:15 +02:00
playlist = self._download_xml(
'http://ec.europa.eu/avservices/video/player/playlist.cfm?ID=%s' % video_id, video_id)
2015-08-12 16:59:04 +02:00
2015-10-02 18:29:15 +02:00
def get_item(type_, preference):
items = {}
for item in playlist.findall('./info/%s/item' % type_):
lang, label = xpath_text(item, 'lg', default=None), xpath_text(item, 'label', default=None)
if lang and label:
items[lang] = label.strip()
for p in preference:
if items.get(p):
return items[p]
2015-08-12 16:59:04 +02:00
2021-08-22 21:02:00 +02:00
query = parse_qs(url)
2015-10-02 18:29:15 +02:00
preferred_lang = query.get('sitelang', ('en', ))[0]
2015-08-12 16:59:04 +02:00
2015-10-02 18:29:15 +02:00
preferred_langs = orderedSet((preferred_lang, 'en', 'int'))
2015-08-12 16:59:04 +02:00
2015-10-02 18:29:15 +02:00
title = get_item('title', preferred_langs) or video_id
description = get_item('description', preferred_langs)
2020-11-21 15:50:42 +01:00
thumbnail = xpath_text(playlist, './info/thumburl', 'thumbnail')
2015-10-02 18:29:15 +02:00
upload_date = unified_strdate(xpath_text(playlist, './info/date', 'upload date'))
duration = parse_duration(xpath_text(playlist, './info/duration', 'duration'))
view_count = int_or_none(xpath_text(playlist, './info/views', 'views'))
2015-08-12 16:59:04 +02:00
2015-10-02 18:29:15 +02:00
language_preference = qualities(preferred_langs[::-1])
2015-08-12 16:59:04 +02:00
2015-10-02 18:29:15 +02:00
formats = []
for file_ in playlist.findall('./files/file'):
video_url = xpath_text(file_, './url')
if not video_url:
continue
lang = xpath_text(file_, './lg')
formats.append({
'url': video_url,
'format_id': lang,
'format_note': xpath_text(file_, './lglabel'),
'language_preference': language_preference(lang)
})
2015-08-12 16:59:04 +02:00
return {
'id': video_id,
2015-10-02 18:29:15 +02:00
'title': title,
'description': description,
2020-11-21 15:50:42 +01:00
'thumbnail': thumbnail,
2015-10-02 18:29:15 +02:00
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
2015-08-12 16:59:04 +02:00
'formats': formats
}
class EuroParlWebstreamIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://multimedia\.europarl\.europa\.eu/[^/#?]+/
(?:(?!video)[^/#?]+/[\w-]+_)(?P<id>[\w-]+)
'''
_TESTS = [{
'url': 'https://multimedia.europarl.europa.eu/pl/webstreaming/plenary-session_20220914-0900-PLENARY',
'info_dict': {
'id': '62388b15-d85b-4add-99aa-ba12ccf64f0d',
'ext': 'mp4',
'title': 'Plenary session',
'release_timestamp': 1663139069,
'release_date': '20220914',
},
'params': {
'skip_download': True,
}
}, {
# live webstream
'url': 'https://multimedia.europarl.europa.eu/en/webstreaming/euroscola_20221115-1000-SPECIAL-EUROSCOLA',
'info_dict': {
'ext': 'mp4',
'id': '510eda7f-ba72-161b-7ee7-0e836cd2e715',
'release_timestamp': 1668502800,
'title': 'Euroscola 2022-11-15 19:21',
'release_date': '20221115',
'live_status': 'is_live',
},
'skip': 'not live anymore'
}, {
'url': 'https://multimedia.europarl.europa.eu/en/webstreaming/committee-on-culture-and-education_20230301-1130-COMMITTEE-CULT',
'info_dict': {
'id': '7355662c-8eac-445e-4bb9-08db14b0ddd7',
'ext': 'mp4',
'release_date': '20230301',
'title': 'Committee on Culture and Education',
'release_timestamp': 1677666641,
}
}, {
# live stream
'url': 'https://multimedia.europarl.europa.eu/en/webstreaming/committee-on-environment-public-health-and-food-safety_20230524-0900-COMMITTEE-ENVI',
'info_dict': {
'id': 'e4255f56-10aa-4b3c-6530-08db56d5b0d9',
'ext': 'mp4',
'release_date': '20230524',
'title': r're:Committee on Environment, Public Health and Food Safety \d{4}-\d{2}-\d{2}\s\d{2}:\d{2}',
'release_timestamp': 1684911541,
'live_status': 'is_live',
},
'skip': 'Not live anymore'
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage_nextjs = self._search_nextjs_data(webpage, display_id)['props']['pageProps']
json_info = self._download_json(
'https://acs-api.europarl.connectedviews.eu/api/FullMeeting', display_id,
query={
'api-version': 1.0,
'tenantId': 'bae646ca-1fc8-4363-80ba-2c04f06b4968',
'externalReference': display_id
})
formats, subtitles = [], {}
for hls_url in traverse_obj(json_info, ((('meetingVideo'), ('meetingVideos', ...)), 'hlsUrl')):
fmt, subs = self._extract_m3u8_formats_and_subtitles(hls_url, display_id)
formats.extend(fmt)
self._merge_subtitles(subs, target=subtitles)
return {
'id': json_info['id'],
'title': traverse_obj(webpage_nextjs, (('mediaItem', 'title'), ('title', )), get_all=False),
'formats': formats,
'subtitles': subtitles,
'release_timestamp': parse_iso8601(json_info.get('startDateTime')),
'is_live': traverse_obj(webpage_nextjs, ('mediaItem', 'mediaSubType')) == 'Live'
}