depau/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-25 10:17:41 +00:00
Code Issues Releases Wiki Activity

[arte] clean extractor(closes #15583)(closes #21614)

Browse source
This commit is contained in:
Remita Amine 2019-07-02 22:07:01 +01:00
parent 1335bf10f6
commit ff0f4cfeba
2 changed files with 29 additions and 310 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

330
youtube_dl/extractor/arte.py
View file

@ -4,17 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
find_xpath_attr,
get_element_by_attribute,
int_or_none,
NO_DEFAULT,
qualities,
try_get,
unified_strdate,
@ -25,59 +18,7 @@ from ..utils import (
# add tests.
class ArteTvIE(InfoExtractor):
_VALID_URL = r'https?://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
IE_NAME = 'arte.tv'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
lang = mobj.group('lang')
video_id = mobj.group('id')
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
ref_xml_doc = self._download_xml(
ref_xml_url, video_id, note='Downloading metadata')
config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config = self._download_xml(
config_xml_url, video_id, note='Downloading configuration')
formats = [{
'format_id': q.attrib['quality'],
# The playpath starts at 'mp4:', if we don't manually
# split the url, rtmpdump will incorrectly parse them
'url': q.text.split('mp4:', 1)[0],
'play_path': 'mp4:' + q.text.split('mp4:', 1)[1],
'ext': 'flv',
'quality': 2 if q.attrib['quality'] == 'hd' else 1,
} for q in config.findall('./urls/url')]
self._sort_formats(formats)
title = config.find('.//name').text
thumbnail = config.find('.//firstThumbnailUrl').text
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}
class ArteTVBaseIE(InfoExtractor):
@classmethod
def _extract_url_info(cls, url):
mobj = re.match(cls._VALID_URL, url)
lang = mobj.group('lang')
query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
if 'vid' in query:
video_id = query['vid'][0]
else:
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id')
return video_id, lang
def _extract_from_json_url(self, json_url, video_id, lang, title=None):
info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer']
@ -108,13 +49,15 @@ class ArteTVBaseIE(InfoExtractor):
'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])
LANGS = {
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
'it': 'E[ITA]',
'pl': 'E[POL]',
}
langcode = LANGS.get(lang, lang)
@ -126,8 +69,8 @@ class ArteTVBaseIE(InfoExtractor):
l = re.escape(langcode)
# Language preference from most to least priority
# Reference: section 5.6.3 of
# http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
# Reference: section 6.8 of
# https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
PREFERENCES = (
# original version in requested language, without subtitles
r'VO{0}$'.format(l),
@ -193,274 +136,59 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVPlus7IE(ArteTVBaseIE):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>\d{6}-\d{3}-[AF])'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
'only_matching': True,
}, {
'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
'only_matching': True,
}, {
'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
'only_matching': True,
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'info_dict': {
'id': '088501-000-A',
'ext': 'mp4',
'title': 'Mexico: Stealing Petrol to Survive',
'upload_date': '20190628',
},
}]
@classmethod
def suitable(cls, url):
return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, video_id)
return self._extract_from_webpage(webpage, video_id, lang)
def _extract_from_webpage(self, webpage, video_id, lang):
patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
ids = (video_id, '')
# some pages contain multiple videos (like
# http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
# so we first try to look for json URLs that contain the video id from
# the 'vid' parameter.
patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
json_url = self._html_search_regex(
patterns, webpage, 'json vp url', default=None)
if not json_url:
def find_iframe_url(webpage, default=NO_DEFAULT):
return self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url', default=default)
iframe_url = find_iframe_url(webpage, None)
if not iframe_url:
embed_url = self._html_search_regex(
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
if embed_url:
player = self._download_json(
embed_url, video_id, 'Downloading player page')
iframe_url = find_iframe_url(player['html'])
# en and es URLs produce react-based pages with different layout (e.g.
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
if not iframe_url:
program = self._search_regex(
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
webpage, 'program', default=None)
if program:
embed_html = self._parse_json(program, video_id)
if embed_html:
iframe_url = find_iframe_url(embed_html['embed_html'])
if iframe_url:
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
if json_url:
title = self._search_regex(
r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
webpage, 'title', default=None, group='title')
return self._extract_from_json_url(json_url, video_id, lang, title=title)
# Different kind of embed URL (e.g.
# http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
entries = [
self.url_result(url)
for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
return self.playlist_result(entries)
# It also uses the arte_vp_url url from the webpage to extract the information
class ArteTVCreativeIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:creative'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
'info_dict': {
'id': '057405-001-A',
'ext': 'mp4',
'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
'upload_date': '20150716',
},
}, {
'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
'playlist_count': 11,
'add_ie': ['Youtube'],
}, {
'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
'only_matching': True,
}]
class ArteTVInfoIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:info'
_VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
'info_dict': {
'id': '067528-000-A',
'ext': 'mp4',
'title': 'Service civique, un cache misère ?',
'upload_date': '20160403',
},
}]
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
'info_dict': {
'id': '050940-028-A',
'ext': 'mp4',
'title': 'Les écrevisses aussi peuvent être anxieuses',
'upload_date': '20140902',
},
}, {
'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
'only_matching': True,
}]
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:ddc'
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
_TESTS = []
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
if lang == 'folge':
lang = 'de'
elif lang == 'emission':
lang = 'fr'
webpage = self._download_webpage(url, video_id)
scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)
class ArteTVConcertIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:concert'
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
'md5': '9ea035b7bd69696b67aa2ccaaa218161',
'info_dict': {
'id': '186',
'ext': 'mp4',
'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
'upload_date': '20140128',
'description': 'md5:486eb08f991552ade77439fe6d82c305',
},
}]
class ArteTVCinemaIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:cinema'
_VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
_TESTS = [{
'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck',
'md5': 'a5b9dd5575a11d93daf0e3f404f45438',
'info_dict': {
'id': '062494-000-A',
'ext': 'mp4',
'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck',
'upload_date': '20150807',
},
}]
class ArteTVMagazineIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:magazine'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
# Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..."
'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium',
'md5': '2a9369bcccf847d1c741e51416299f25',
'info_dict': {
'id': '065965-000-A',
'ext': 'mp4',
'title': 'Trepalium - Extrait Ep.01',
'upload_date': '20160121',
},
}, {
# Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium"
'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium',
'md5': 'fedc64fc7a946110fe311634e79782ca',
'info_dict': {
'id': '054813-004_PLUS7-F',
'ext': 'mp4',
'title': 'Trepalium (4/6)',
'description': 'md5:10057003c34d54e95350be4f9b05cb40',
'upload_date': '20160218',
},
}, {
'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis',
'only_matching': True,
}]
lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(
'https://api.arte.tv/api/player/v1/config/%s/%s' % (lang, video_id),
video_id, lang)
class ArteTVEmbedIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:embed'
_VALID_URL = r'''(?x)
http://www\.arte\.tv
/(?:playerv2/embed|arte_vp/index)\.php\?json_url=
https://www\.arte\.tv
/player/v3/index\.php\?json_url=
(?P<json_url>
http://arte\.tv/papi/tvguide/videos/stream/player/
(?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
https?://api\.arte\.tv/api/player/v1/config/
(?P<lang>[^/]+)/(?P<id>\d{6}-\d{3}-[AF])
)
'''
_TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
lang = mobj.group('lang')
json_url = mobj.group('json_url')
json_url, lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(json_url, video_id, lang)
class TheOperaPlatformIE(ArteTVPlus7IE):
IE_NAME = 'theoperaplatform'
_VALID_URL = r'https?://(?:www\.)?theoperaplatform\.eu/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.theoperaplatform.eu/de/opera/verdi-otello',
'md5': '970655901fa2e82e04c00b955e9afe7b',
'info_dict': {
'id': '060338-009-A',
'ext': 'mp4',
'title': 'Verdi - OTELLO',
'upload_date': '20160927',
},
}]
class ArteTVPlaylistIE(ArteTVBaseIE):
IE_NAME = 'arte.tv:playlist'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>RC-\d{6})'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV',
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'info_dict': {
'id': 'PL-013263',
'title': 'Areva & Uramin',
'description': 'md5:a1dc0312ce357c262259139cfd48c9bf',
'id': 'RC-016954',
'title': 'Earn a Living',
'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
},
'playlist_mincount': 6,
}, {
'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id, lang = self._extract_url_info(url)
lang, playlist_id = re.match(self._VALID_URL, url).groups()
collection = self._download_json(
'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
% (lang, playlist_id), playlist_id)

9
youtube_dl/extractor/extractors.py
View file

@ -58,17 +58,8 @@ from .ard import (
ARDMediathekIE,
)
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVConcertIE,
ArteTVInfoIE,
ArteTVFutureIE,
ArteTVCinemaIE,
ArteTVDDCIE,
ArteTVMagazineIE,
ArteTVEmbedIE,
TheOperaPlatformIE,
ArteTVPlaylistIE,
)
from .asiancrush import (