X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Frai.py;h=207a6c247f3c78ff260bd8a326af1b1fb59c550c;hb=HEAD;hp=b77b0a08e61f7969e182ffe41a749767c0a1d0bf;hpb=b8d8cced9b55c57f3b09e83972be9d6318a459ee;p=youtube-dl diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index b77b0a08e..207a6c247 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -17,6 +17,7 @@ from ..utils import ( parse_duration, strip_or_none, try_get, + unescapeHTML, unified_strdate, unified_timestamp, update_url_query, @@ -31,6 +32,9 @@ class RaiBaseIE(InfoExtractor): _GEO_BYPASS = False def _extract_relinker_info(self, relinker_url, video_id): + if not re.match(r'https?://', relinker_url): + return {'formats': [{'url': relinker_url}]} + formats = [] geoprotection = None is_live = None @@ -70,11 +74,11 @@ class RaiBaseIE(InfoExtractor): if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'): continue - if ext == 'm3u8': + if ext == 'm3u8' or 'format=m3u8' in media_url or platform == 'mon': formats.extend(self._extract_m3u8_formats( media_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) - elif ext == 'f4m': + elif ext == 'f4m' or platform == 'flash': manifest_url = update_url_query( media_url.replace('manifest#live_hds.f4m', 'manifest.f4m'), {'hdcore': '3.7.0', 'plugin': 'aasp-3.7.0.39.44'}) @@ -97,6 +101,25 @@ class RaiBaseIE(InfoExtractor): 'formats': formats, }.items() if v is not None) + @staticmethod + def _extract_subtitles(url, subtitle_url): + subtitles = {} + if subtitle_url and isinstance(subtitle_url, compat_str): + subtitle_url = urljoin(url, subtitle_url) + STL_EXT = '.stl' + SRT_EXT = '.srt' + subtitles['it'] = [{ + 'ext': 'stl', + 'url': subtitle_url, + }] + if subtitle_url.endswith(STL_EXT): + srt_url = subtitle_url[:-len(STL_EXT)] + SRT_EXT + subtitles['it'].append({ + 'ext': 'srt', + 'url': srt_url, + }) + return subtitles + class RaiPlayIE(RaiBaseIE): _VALID_URL = r'(?Phttps?://(?:www\.)?raiplay\.it/.+?-(?P%s)\.html)' % RaiBaseIE._UUID_RE @@ -168,13 +191,16 @@ class RaiPlayIE(RaiBaseIE): timestamp = unified_timestamp(try_get( media, lambda x: x['availabilities'][0]['start'], compat_str)) + subtitles = self._extract_subtitles(url, video.get('subtitles')) + info = { 'id': video_id, - 'title': title, + 'title': self._live_title(title) if relinker_info.get( + 'is_live') else title, 'alt_title': media.get('subtitle'), 'description': media.get('description'), - 'uploader': media.get('channel'), - 'creator': media.get('editor'), + 'uploader': strip_or_none(media.get('channel')), + 'creator': strip_or_none(media.get('editor')), 'duration': parse_duration(video.get('duration')), 'timestamp': timestamp, 'thumbnails': thumbnails, @@ -183,15 +209,86 @@ class RaiPlayIE(RaiBaseIE): 'season_number': int_or_none(try_get( media, lambda x: x['isPartOf']['numeroStagioni'])), 'season': media.get('stagione') or None, + 'subtitles': subtitles, } info.update(relinker_info) - return info +class RaiPlayLiveIE(RaiBaseIE): + _VALID_URL = r'https?://(?:www\.)?raiplay\.it/dirette/(?P[^/?#&]+)' + _TEST = { + 'url': 'http://www.raiplay.it/dirette/rainews24', + 'info_dict': { + 'id': 'd784ad40-e0ae-4a69-aa76-37519d238a9c', + 'display_id': 'rainews24', + 'ext': 'mp4', + 'title': 're:^Diretta di Rai News 24 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:6eca31500550f9376819f174e5644754', + 'uploader': 'Rai News 24', + 'creator': 'Rai News 24', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'data-uniquename=["\']ContentItem-(%s)' % RaiBaseIE._UUID_RE, + webpage, 'content id') + + return { + '_type': 'url_transparent', + 'ie_key': RaiPlayIE.ie_key(), + 'url': 'http://www.raiplay.it/dirette/ContentItem-%s.html' % video_id, + 'id': video_id, + 'display_id': display_id, + } + + +class RaiPlayPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', + 'info_dict': { + 'id': 'nondirloalmiocapo', + 'title': 'Non dirlo al mio capo', + 'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86', + }, + 'playlist_mincount': 12, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + title = self._html_search_meta( + ('programma', 'nomeProgramma'), webpage, 'title') + description = unescapeHTML(self._html_search_meta( + ('description', 'og:description'), webpage, 'description')) + + entries = [] + for mobj in re.finditer( + r']+\bhref=(["\'])(?P/raiplay/video/.+?)\1', + webpage): + video_url = urljoin(url, mobj.group('path')) + 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) + + class RaiIE(RaiBaseIE): - _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE + _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/.+?-(?P%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE _TESTS = [{ # var uniquename = "ContentItem-..." # data-id="ContentItem-..." @@ -274,6 +371,13 @@ class RaiIE(RaiBaseIE): 'params': { 'skip_download': True, }, + }, { + # Direct MMS URL + 'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-b63a4089-ac28-48cf-bca5-9f5b5bc46df5.html', + 'only_matching': True, + }, { + 'url': 'https://www.rainews.it/tgr/marche/notiziari/video/2019/02/ContentItem-6ba945a2-889c-4a80-bdeb-8489c70a8db9.html', + 'only_matching': True, }] def _extract_from_content_id(self, content_id, url): @@ -286,11 +390,11 @@ class RaiIE(RaiBaseIE): media_type = media['type'] if 'Audio' in media_type: relinker_info = { - 'formats': { + 'formats': [{ 'format_id': media.get('formatoAudio'), 'url': media['audioUrl'], 'ext': media.get('formatoAudio'), - } + }] } elif 'Video' in media_type: relinker_info = self._extract_relinker_info(media['mediaUri'], content_id) @@ -307,17 +411,7 @@ class RaiIE(RaiBaseIE): 'url': compat_urlparse.urljoin(url, thumbnail_url), }) - subtitles = {} - captions = media.get('subtitlesUrl') - if captions: - STL_EXT = '.stl' - SRT_EXT = '.srt' - if captions.endswith(STL_EXT): - captions = captions[:-len(STL_EXT)] + SRT_EXT - subtitles['it'] = [{ - 'ext': 'srt', - 'url': captions, - }] + subtitles = self._extract_subtitles(url, media.get('subtitlesUrl')) info = { 'id': content_id, @@ -362,7 +456,8 @@ class RaiIE(RaiBaseIE): webpage, 'content item id', default=None, group='id') content_item_ids = set() - content_item_ids.add(content_item_id) + if content_item_id: + content_item_ids.add(content_item_id) if video_id not in content_item_ids: content_item_ids.add(video_id)