X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a070911bf98c751e4425008f1335cc57c86d30fc..4121346dfbb2b660ded98e98069857c7a50e381f:/youtube_dl/extractor/vier.py diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py index 619039e..dbd5ba9 100644 --- a/youtube_dl/extractor/vier.py +++ b/youtube_dl/extractor/vier.py @@ -2,54 +2,193 @@ from __future__ import unicode_literals import re +import itertools from .common import InfoExtractor +from ..utils import ( + urlencode_postdata, + int_or_none, + unified_strdate, +) class VierIE(InfoExtractor): IE_NAME = 'vier' - _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P[^/]+)(?:/(?P\d+))?|video/v3/embed/(?P\d+))' + IE_DESC = 'vier.be and vijf.be' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?(?Pvier|vijf)\.be/ + (?: + (?: + [^/]+/videos| + video(?:/[^/]+)* + )/ + (?P[^/]+)(?:/(?P\d+))?| + (?: + video/v3/embed| + embed/video/public + )/(?P\d+) + ) + ''' + _NETRC_MACHINE = 'vier' _TESTS = [{ 'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129', + 'md5': 'e4ae2054a6b040ef1e289e20d111b46e', 'info_dict': { 'id': '16129', 'display_id': 'het-wordt-warm-de-moestuin', 'ext': 'mp4', 'title': 'Het wordt warm in De Moestuin', 'description': 'De vele uren werk eisen hun tol. Wim droomt van assistentie...', + 'upload_date': '20121025', + 'series': 'Plan B', + 'tags': ['De Moestuin', 'Moestuin', 'meisjes', 'Tomaat', 'Wim', 'Droom'], + }, + }, { + 'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614', + 'info_dict': { + 'id': '2561614', + 'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas', + 'ext': 'mp4', + 'title': 'md5:84f45fe48b8c1fa296a7f6d208d080a7', + 'description': 'md5:0356d4981e58b8cbee19355cbd51a8fe', + 'upload_date': '20170228', + 'series': 'Temptation Island', + 'tags': list, }, 'params': { - # m3u8 download 'skip_download': True, }, }, { - 'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen', + 'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839', + 'info_dict': { + 'id': '2674839', + 'display_id': 'jani-gaat-naar-tokio-aflevering-4', + 'ext': 'mp4', + 'title': 'Jani gaat naar Tokio - Aflevering 4', + 'description': 'md5:aa8d611541db6ae9e863125704511f88', + 'upload_date': '20170501', + 'series': 'Jani gaat', + 'episode_number': 4, + 'tags': ['Jani Gaat', 'Volledige Aflevering'], + }, + 'params': { + 'skip_download': True, + }, + 'skip': 'Requires account credentials', + }, { + # Requires account credentials but bypassed extraction via v3/embed page + # without metadata + 'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839', + 'info_dict': { + 'id': '2674839', + 'display_id': 'jani-gaat-naar-tokio-aflevering-4', + 'ext': 'mp4', + 'title': 'jani-gaat-naar-tokio-aflevering-4', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Log in to extract metadata'], + }, { + # Without video id in URL + 'url': 'http://www.vier.be/planb/videos/dit-najaar-plan-b', 'only_matching': True, }, { 'url': 'http://www.vier.be/video/v3/embed/16129', 'only_matching': True, + }, { + 'url': 'https://www.vijf.be/embed/video/public/4093', + 'only_matching': True, + }, { + 'url': 'https://www.vier.be/video/blockbusters/in-juli-en-augustus-summer-classics', + 'only_matching': True, + }, { + 'url': 'https://www.vier.be/video/achter-de-rug/2017/achter-de-rug-seizoen-1-aflevering-6', + 'only_matching': True, }] + def _real_initialize(self): + self._logged_in = False + + def _login(self, site): + username, password = self._get_login_info() + if username is None or password is None: + return + + login_page = self._download_webpage( + 'http://www.%s.be/user/login' % site, + None, note='Logging in', errnote='Unable to log in', + data=urlencode_postdata({ + 'form_id': 'user_login', + 'name': username, + 'pass': password, + }), + headers={'Content-Type': 'application/x-www-form-urlencoded'}) + + login_error = self._html_search_regex( + r'(?s)
\s*
\s*(.+?)<', + login_page, 'login error', default=None) + if login_error: + self.report_warning('Unable to log in: %s' % login_error) + else: + self._logged_in = True + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) embed_id = mobj.group('embed_id') display_id = mobj.group('display_id') or embed_id + video_id = mobj.group('id') or embed_id + site = mobj.group('site') + + if not self._logged_in: + self._login(site) webpage = self._download_webpage(url, display_id) + if r'id="user-login"' in webpage: + self.report_warning( + 'Log in to extract metadata', video_id=display_id) + webpage = self._download_webpage( + 'http://www.%s.be/video/v3/embed/%s' % (site, video_id), + display_id) + video_id = self._search_regex( - r'"nid"\s*:\s*"(\d+)"', webpage, 'video id') - application = self._search_regex( - r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod') - filename = self._search_regex( - r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename') + [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'], + webpage, 'video id', default=video_id or display_id) + + playlist_url = self._search_regex( + r'data-file=(["\'])(?P(?:https?:)?//[^/]+/.+?\.m3u8.*?)\1', + webpage, 'm3u8 url', default=None, group='url') - playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename) - formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4') + if not playlist_url: + application = self._search_regex( + [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'], + webpage, 'application', default=site + '_vod') + filename = self._search_regex( + [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'], + webpage, 'filename') + playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename) + + formats = self._extract_wowza_formats( + playlist_url, display_id, skip_protocols=['dash']) + self._sort_formats(formats) title = self._og_search_title(webpage, default=display_id) - description = self._og_search_description(webpage, default=None) + description = self._html_search_regex( + r'(?s)]+\bclass=(["\'])[^>]*?\bfield-type-text-with-summary\b[^>]*?\1[^>]*>.*?

(?P.+?)

', + webpage, 'description', default=None, group='value') thumbnail = self._og_search_thumbnail(webpage, default=None) + upload_date = unified_strdate(self._html_search_regex( + r'(?s)]+\bclass=(["\'])[^>]*?\bfield-name-post-date\b[^>]*?\1[^>]*>.*?(?P\d{2}/\d{2}/\d{4})', + webpage, 'upload date', default=None, group='value')) + + series = self._search_regex( + r'data-program=(["\'])(?P(?:(?!\1).)+)\1', webpage, + 'series', default=None, group='value') + episode_number = int_or_none(self._search_regex( + r'(?i)aflevering (\d+)', title, 'episode number', default=None)) + tags = re.findall(r']+\bhref=["\']/tags/[^>]+>([^<]+)<', webpage) return { 'id': video_id, @@ -57,19 +196,29 @@ class VierIE(InfoExtractor): 'title': title, 'description': description, 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'series': series, + 'episode_number': episode_number, + 'tags': tags, 'formats': formats, } class VierVideosIE(InfoExtractor): IE_NAME = 'vier:videos' - _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P[^/]+)/videos(?:\?.*\bpage=(?P\d+)|$)' + _VALID_URL = r'https?://(?:www\.)?(?Pvier|vijf)\.be/(?P[^/]+)/videos(?:\?.*\bpage=(?P\d+)|$)' _TESTS = [{ 'url': 'http://www.vier.be/demoestuin/videos', 'info_dict': { 'id': 'demoestuin', }, 'playlist_mincount': 153, + }, { + 'url': 'http://www.vijf.be/temptationisland/videos', + 'info_dict': { + 'id': 'temptationisland', + }, + 'playlist_mincount': 159, }, { 'url': 'http://www.vier.be/demoestuin/videos?page=6', 'info_dict': { @@ -87,32 +236,29 @@ class VierVideosIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) program = mobj.group('program') - - webpage = self._download_webpage(url, program) + site = mobj.group('site') page_id = mobj.group('page') if page_id: page_id = int(page_id) start_page = page_id - last_page = start_page + 1 playlist_id = '%s-page%d' % (program, page_id) else: start_page = 0 - last_page = int(self._search_regex( - r'videos\?page=(\d+)">laatste', - webpage, 'last page', default=0)) + 1 playlist_id = program entries = [] - for current_page_id in range(start_page, last_page): + for current_page_id in itertools.count(start_page): current_page = self._download_webpage( - 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id), + 'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id), program, - 'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage + 'Downloading page %d' % (current_page_id + 1)) page_entries = [ - self.url_result('http://www.vier.be' + video_url, 'Vier') + self.url_result('http://www.' + site + '.be' + video_url, 'Vier') for video_url in re.findall( - r'

', current_page)] + r'', current_page)] entries.extend(page_entries) + if page_id or '>Meer<' not in current_page: + break return self.playlist_result(entries, playlist_id)