aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dlc/extractor/rai.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dlc/extractor/rai.py')
-rw-r--r--youtube_dlc/extractor/rai.py145
1 files changed, 64 insertions, 81 deletions
diff --git a/youtube_dlc/extractor/rai.py b/youtube_dlc/extractor/rai.py
index 51a310f5c..5eef7c633 100644
--- a/youtube_dlc/extractor/rai.py
+++ b/youtube_dlc/extractor/rai.py
@@ -16,6 +16,7 @@ from ..utils import (
GeoRestrictedError,
int_or_none,
parse_duration,
+ remove_start,
strip_or_none,
try_get,
unified_strdate,
@@ -30,7 +31,6 @@ class RaiBaseIE(InfoExtractor):
_UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_GEO_COUNTRIES = ['IT']
_GEO_BYPASS = False
- _BASE_URL = 'https://www.raiplay.it'
def _extract_relinker_info(self, relinker_url, video_id):
if not re.match(r'https?://', relinker_url):
@@ -68,7 +68,7 @@ class RaiBaseIE(InfoExtractor):
# This does not imply geo restriction (e.g.
# http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
- if media_url == 'http://download.rai.it/video_no_available.mp4':
+ if '/video_no_available.mp4' in media_url:
continue
ext = determine_ext(media_url)
@@ -123,7 +123,7 @@ class RaiBaseIE(InfoExtractor):
class RaiPlayIE(RaiBaseIE):
- _VALID_URL = r'(?P<url>(?P<base>https?://(?:www\.)?raiplay\.it/.+?-)(?P<id>%s)(?P<ext>\.(?:html|json)))' % RaiBaseIE._UUID_RE
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s))\.(?:html|json)' % RaiBaseIE._UUID_RE
_TESTS = [{
'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
'md5': '8970abf8caf8aef4696e7b1f2adfc696',
@@ -131,11 +131,13 @@ class RaiPlayIE(RaiBaseIE):
'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
'ext': 'mp4',
'title': 'Report del 07/04/2014',
- 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014 ',
+ 'alt_title': 'St 2013/14 - Espresso nel caffè - 07/04/2014',
'description': 'md5:d730c168a58f4bb35600fc2f881ec04e',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai Gulp',
'duration': 6160,
+ 'series': 'Report',
+ 'season': '2013/14',
},
'params': {
'skip_download': True,
@@ -146,11 +148,10 @@ class RaiPlayIE(RaiBaseIE):
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- url, base, video_id, ext = mobj.group('url', 'base', 'id', 'ext')
+ base, video_id = re.match(self._VALID_URL, url).groups()
media = self._download_json(
- '%s%s.json' % (base, video_id), video_id, 'Downloading video JSON')
+ base + '.json', video_id, 'Downloading video JSON')
title = media['name']
video = media['video']
@@ -159,34 +160,39 @@ class RaiPlayIE(RaiBaseIE):
self._sort_formats(relinker_info['formats'])
thumbnails = []
- if 'images' in media:
- for _, value in media.get('images').items():
- if value:
- thumbnails.append({
- 'url': urljoin(RaiBaseIE._BASE_URL, value.replace('[RESOLUTION]', '600x400'))
- })
+ for _, value in media.get('images', {}).items():
+ if value:
+ thumbnails.append({
+ 'url': urljoin(url, value),
+ })
- timestamp = unified_timestamp(try_get(
- media, lambda x: x['availabilities'][0]['start'], compat_str))
+ date_published = media.get('date_published')
+ time_published = media.get('time_published')
+ if date_published and time_published:
+ date_published += ' ' + time_published
subtitles = self._extract_subtitles(url, video.get('subtitles'))
+ program_info = media.get('program_info') or {}
+ season = media.get('season')
+
info = {
- 'id': video_id,
+ 'id': remove_start(media.get('id'), 'ContentItem-') or video_id,
+ 'display_id': video_id,
'title': self._live_title(title) if relinker_info.get(
'is_live') else title,
- 'alt_title': media.get('subtitle'),
+ 'alt_title': strip_or_none(media.get('subtitle')),
'description': media.get('description'),
'uploader': strip_or_none(media.get('channel')),
- 'creator': strip_or_none(media.get('editor')),
+ 'creator': strip_or_none(media.get('editor') or None),
'duration': parse_duration(video.get('duration')),
- 'timestamp': timestamp,
+ 'timestamp': unified_timestamp(date_published),
'thumbnails': thumbnails,
- 'series': try_get(
- media, lambda x: x['isPartOf']['name'], compat_str),
- 'season_number': int_or_none(try_get(
- media, lambda x: x['isPartOf']['numeroStagioni'])),
- 'season': media.get('stagione') or None,
+ 'series': program_info.get('name'),
+ 'season_number': int_or_none(season),
+ 'season': season if (season and not season.isdigit()) else None,
+ 'episode': media.get('episode_title'),
+ 'episode_number': int_or_none(media.get('episode')),
'subtitles': subtitles,
}
@@ -194,9 +200,9 @@ class RaiPlayIE(RaiBaseIE):
return info
-class RaiPlayLiveIE(RaiBaseIE):
- _VALID_URL = r'https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+)'
- _TEST = {
+class RaiPlayLiveIE(RaiPlayIE):
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/dirette/(?P<id>[^/?#&]+))'
+ _TESTS = [{
'url': 'http://www.raiplay.it/dirette/rainews24',
'info_dict': {
'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c',
@@ -211,40 +217,11 @@ class RaiPlayLiveIE(RaiBaseIE):
'params': {
'skip_download': True,
},
- }
-
- def _real_extract(self, url):
- display_id = self._match_id(url)
-
- media = self._download_json(
- '%s.json' % urljoin(RaiBaseIE._BASE_URL, 'dirette/' + display_id),
- display_id, 'Downloading channel JSON')
-
- title = media['name']
- video = media['video']
- video_id = media['id'].replace('ContentItem-', '')
-
- relinker_info = self._extract_relinker_info(video['content_url'], video_id)
- self._sort_formats(relinker_info['formats'])
-
- info = {
- 'id': video_id,
- 'display_id': display_id,
- 'title': self._live_title(title) if relinker_info.get(
- 'is_live') else title,
- 'alt_title': media.get('subtitle'),
- 'description': media.get('description'),
- 'uploader': strip_or_none(media.get('channel')),
- 'creator': strip_or_none(media.get('editor')),
- 'duration': parse_duration(video.get('duration')),
- }
-
- info.update(relinker_info)
- return info
+ }]
class RaiPlayPlaylistIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)'
+ _VALID_URL = r'(?P<base>https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/',
'info_dict': {
@@ -256,29 +233,34 @@ class RaiPlayPlaylistIE(InfoExtractor):
}]
def _real_extract(self, url):
- playlist_id = self._match_id(url)
-
- media = self._download_json(
- '%s.json' % urljoin(RaiBaseIE._BASE_URL, 'programmi/' + playlist_id),
- playlist_id, 'Downloading program JSON')
-
- title = media['name']
- description = media['program_info']['description']
+ base, playlist_id = re.match(self._VALID_URL, url).groups()
- content_sets = [s['id'] for b in media['blocks'] for s in b['sets']]
+ program = self._download_json(
+ base + '.json', playlist_id, 'Downloading program JSON')
entries = []
- for cs in content_sets:
- medias = self._download_json(
- '%s/%s.json' % (urljoin(RaiBaseIE._BASE_URL, 'programmi/' + playlist_id), cs),
- cs, 'Downloading content set JSON')
- for m in medias['items']:
- video_url = urljoin(url, m['path_id'])
- entries.append(self.url_result(
- video_url, ie=RaiPlayIE.ie_key(),
- video_id=RaiPlayIE._match_id(video_url)))
-
- return self.playlist_result(entries, playlist_id, title, description)
+ for b in (program.get('blocks') or []):
+ for s in (b.get('sets') or []):
+ s_id = s.get('id')
+ if not s_id:
+ continue
+ medias = self._download_json(
+ '%s/%s.json' % (base, s_id), s_id,
+ 'Downloading content set JSON', fatal=False)
+ if not medias:
+ continue
+ for m in (medias.get('items') or []):
+ path_id = m.get('path_id')
+ if not path_id:
+ continue
+ video_url = urljoin(url, path_id)
+ entries.append(self.url_result(
+ video_url, ie=RaiPlayIE.ie_key(),
+ video_id=RaiPlayIE._match_id(video_url)))
+
+ return self.playlist_result(
+ entries, playlist_id, program.get('name'),
+ try_get(program, lambda x: x['program_info']['description']))
class RaiIE(RaiBaseIE):
@@ -294,7 +276,8 @@ class RaiIE(RaiBaseIE):
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1758,
'upload_date': '20140612',
- }
+ },
+ 'skip': 'This content is available only in Italy',
}, {
# with ContentItem in many metas
'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
@@ -440,7 +423,7 @@ class RaiIE(RaiBaseIE):
except ExtractorError:
pass
- relinker_url = self._search_regex(
+ relinker_url = self._proto_relative_url(self._search_regex(
r'''(?x)
(?:
var\s+videoURL|
@@ -452,7 +435,7 @@ class RaiIE(RaiBaseIE):
//mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
(?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
''',
- webpage, 'relinker URL', group='url')
+ webpage, 'relinker URL', group='url'))
relinker_info = self._extract_relinker_info(
urljoin(url, relinker_url), video_id)