diff options
Diffstat (limited to 'youtube_dl/extractor/vier.py')
| -rw-r--r-- | youtube_dl/extractor/vier.py | 117 |
1 files changed, 106 insertions, 11 deletions
diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py index 5086f59..3e67eb8 100644 --- a/youtube_dl/extractor/vier.py +++ b/youtube_dl/extractor/vier.py @@ -5,23 +5,30 @@ import re import itertools from .common import InfoExtractor +from ..utils import ( + urlencode_postdata, + int_or_none, + unified_strdate, +) class VierIE(InfoExtractor): IE_NAME = 'vier' + IE_DESC = 'vier.be and vijf.be' _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\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...', - }, - 'params': { - # m3u8 download - 'skip_download': True, + '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', @@ -29,32 +36,103 @@ class VierIE(InfoExtractor): 'id': '2561614', 'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas', 'ext': 'mp4', - 'title': 'ZO grappig: Temptation Island hosts moeten kiezen tussen onmogelijke dilemma\'s', - 'description': 'Het spel is simpel: Annelien Coorevits en Rick Brandsteder krijgen telkens 2 dilemma\'s voorgeschoteld en ze MOETEN een keuze maken.', + 'title': 'md5:84f45fe48b8c1fa296a7f6d208d080a7', + 'description': 'md5:0356d4981e58b8cbee19355cbd51a8fe', + 'upload_date': '20170228', + 'series': 'Temptation Island', + 'tags': list, + }, + 'params': { + 'skip_download': True, + }, + }, { + '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': { - # m3u8 download 'skip_download': True, }, + 'expected_warnings': ['Log in to extract metadata'], }, { - 'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen', + # 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, }] + 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)<div class="messages error">\s*<div>\s*<h2.+?</h2>(.+?)<', + 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'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'], - webpage, 'video id') + webpage, 'video id', default=video_id or display_id) application = self._search_regex( [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'], webpage, 'application', default=site + '_vod') @@ -63,12 +141,25 @@ class VierIE(InfoExtractor): 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']) + 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)<div\b[^>]+\bclass=(["\'])[^>]*?\bfield-type-text-with-summary\b[^>]*?\1[^>]*>.*?<p>(?P<value>.+?)</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)<div\b[^>]+\bclass=(["\'])[^>]*?\bfield-name-post-date\b[^>]*?\1[^>]*>.*?(?P<value>\d{2}/\d{2}/\d{4})', + webpage, 'upload date', default=None, group='value')) + + series = self._search_regex( + r'data-program=(["\'])(?P<value>(?:(?!\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'<a\b[^>]+\bhref=["\']/tags/[^>]+>([^<]+)<', webpage) return { 'id': video_id, @@ -76,6 +167,10 @@ class VierIE(InfoExtractor): 'title': title, 'description': description, 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'series': series, + 'episode_number': episode_number, + 'tags': tags, 'formats': formats, } |