Mirroring
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Releases Wiki Activity

[ie/europa] Fix extractor

Browse Source
pull/12773/head
DTrombett 1 month ago
parent 6eaa574c82
commit b259e70379
No known key found for this signature in database
GPG Key ID: FD8700F69650F6AA
1 changed files with 74 additions and 72 deletions
Show Stats Download Patch File Download Diff File

144
yt_dlp/extractor/europa.py
Unescape Escape View File

@ -1,95 +1,97 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
int_or_none,
orderedSet,
parse_duration,
parse_iso8601, parse_iso8601,
parse_qs, str_or_none,
qualities,
traverse_obj, traverse_obj,
unified_strdate, url_or_none,
xpath_text, urljoin,
) )
class EuropaIE(InfoExtractor): class EuropaIE(InfoExtractor):
_WORKING = False _VALID_URL = r'https?://audiovisual\.ec\.europa\.eu/(?P<language>[^/]*)/video/(?P<id>[A-Za-z0-9-]+)'
_VALID_URL = r'https?://ec\.europa\.eu/avservices/(?:video/player|audio/audioDetails)\.cfm\?.*?\bref=(?P<id>[A-Za-z0-9-]+)' _FORMATS = {
'lr': {'vcodec': 'h264', 'acodec': 'aac', 'height': 480},
'hdmp4': {'vcodec': 'h264', 'acodec': 'aac', 'height': 1080},
'mp3': {'vcodec': 'none', 'acodec': 'mp3', 'abr': 128},
}
_TESTS = [{ _TESTS = [{
'url': 'http://ec.europa.eu/avservices/video/player.cfm?ref=I107758', 'url': 'https://audiovisual.ec.europa.eu/en/video/I-107758',
'md5': '574f080699ddd1e19a675b0ddf010371', 'md5': '728cca2fd41d5aa7350cec1141fbe620',
'info_dict': { 'info_dict': {
'id': 'I107758', 'id': 'I-107758',
'ext': 'mp4', 'ext': 'mp4',
'title': 'TRADE - Wikileaks on TTIP', 'title': 'TRADE - Wikileaks on TTIP:- Q&A',
'description': 'NEW LIVE EC Midday press briefing of 11/08/2015', 'description': 'LIVE EC Midday press briefing of 11/08/2015',
'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'beluga',
'duration': 34.92,
'thumbnail': 'https://vod.prd.commavservices.eu/18/107758/THUMB_M_I107758INT1W.jpg',
'timestamp': 1439288640,
'upload_date': '20150811', 'upload_date': '20150811',
'duration': 34, 'modified_timestamp': 1731858348,
'view_count': int, 'modified_date': '20241117',
'formats': 'mincount:3',
}, },
}, { }, {
'url': 'http://ec.europa.eu/avservices/video/player.cfm?sitelang=en&ref=I107786', 'url': 'https://audiovisual.ec.europa.eu/en/video/I-107786',
'only_matching': True, 'md5': '5ecf1eb72800573ed75a53fc06511967',
'info_dict': {
'id': 'I-107786',
'ext': 'mp4',
'title': 'Midday press briefing from 14/08/2015',
'description': 'md5:e56082f090a0ad1da6b76f453dd9d155',
'uploader': 'beluga',
'thumbnail': 'https://vod.prd.commavservices.eu/06/107786/THUMB_M_I107786INT1W.jpg',
'timestamp': 1439503200,
'upload_date': '20150813',
'modified_timestamp': 1731858616,
'modified_date': '20241117',
},
}, { }, {
'url': 'http://ec.europa.eu/avservices/audio/audioDetails.cfm?ref=I-109295&sitelang=en', 'url': 'https://audiovisual.ec.europa.eu/en/video/I-109295',
'only_matching': True, 'md5': '3a6d560e0aff5633de4bb7cdc368ab72',
'info_dict': {
'id': 'I-109295',
'ext': 'mp4',
'title': 'md5:dfc882adaabf388999e20d3079ee5277',
'description': 'md5:67374bddab3fd2a8a319a92e1a286ad2',
'uploader': 'beluga',
'thumbnail': 'https://vod.prd.commavservices.eu/15/109295/THUMB_M_I109295INT1W_03.jpg',
'timestamp': 1443762000,
'upload_date': '20151002',
'modified_timestamp': 1731845416,
'modified_date': '20241117',
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) language, video_id = self._match_valid_url(url).group('language', 'id')
constants = self._download_webpage('https://audiovisual.ec.europa.eu/js/constants.js', video_id, 'Downloading constants')
playlist = self._download_xml( api = self._search_regex(r'"urlJellyfishApi":\s*"([^"]+)"', constants, 'urlJellyfishApi', 'https://yy2iyrkool.execute-api.eu-west-1.amazonaws.com/jellyfish/')
f'http://ec.europa.eu/avservices/video/player/playlist.cfm?ID={video_id}', video_id) media = self._download_json(urljoin(api, f'medias/{video_id}'), video_id, 'Downloading media JSON')
info = traverse_obj(media, ('latest', {
def get_item(type_, preference): 'modified_timestamp': ('timestamp', {parse_iso8601}),
items = {} 'uploader': ('user', {str_or_none}),
for item in playlist.findall(f'./info/{type_}/item'): 'id': ('data', 'reference', {str_or_none}),
lang, label = xpath_text(item, 'lg', default=None), xpath_text(item, 'label', default=None) 'duration': ('data', 'duration', {lambda d: None if d == 1 else d}),
if lang and label: 'timestamp': ('data', 'productionDatetime', {parse_iso8601}),
items[lang] = label.strip() 'title': ('data', 'titles', ..., ..., {lambda t: t and t.strip()}, any),
for p in preference: 'description': ('data', 'summaries', ..., ..., {lambda t: t and t.strip()}, any),
if items.get(p): 'thumbnails': ('data', 'files', ..., ('image', 'thumb'), {'url': ('url', {url_or_none})}),
return items[p] }))
query = parse_qs(url)
preferred_lang = query.get('sitelang', ('en', ))[0]
preferred_langs = orderedSet((preferred_lang, 'en', 'int'))
title = get_item('title', preferred_langs) or video_id
description = get_item('description', preferred_langs)
thumbnail = xpath_text(playlist, './info/thumburl', 'thumbnail')
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'))
language_preference = qualities(preferred_langs[::-1])
formats = [] formats = []
for file_ in playlist.findall('./files/file'):
video_url = xpath_text(file_, './url') for file in traverse_obj(media, ('latest', 'data', 'files', ...)):
if not video_url: l = traverse_obj(file, ('language', {lambda l: l and l.lower()}))
continue for k in ('mp3', 'lr', 'hdmp4'):
lang = xpath_text(file_, './lg') if f_url := traverse_obj(file, (k, 'url')):
formats.append({ formats.append({
'url': video_url, 'url': f_url,
'format_id': lang, 'language': l,
'format_note': xpath_text(file_, './lglabel'), 'language_preference': 10 if (l and l.lower() == language) or l == 'int' else -10,
'language_preference': language_preference(lang), 'format_id': f'{k}-{l}',
**self._FORMATS[k],
}) })
return {**info, 'formats': formats}
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'formats': formats,
}
class EuroParlWebstreamIE(InfoExtractor): class EuroParlWebstreamIE(InfoExtractor):

Write Preview
Loading…
Cancel
Save