[yt-dlp.git] / youtube_dl / extractor / wdr.py

# -*- coding: utf-8 -*-
from __future__ import unicode_literals

import itertools
import re

from .common import InfoExtractor
from ..compat import (
    compat_parse_qs,
    compat_urlparse,
)
from ..utils import (
    determine_ext,
    unified_strdate,
)


class WDRIE(InfoExtractor):
    _PLAYER_REGEX = '-(?:video|audio)player(?:_size-[LMS])?'
    _VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX

    _TESTS = [
        {
            'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
            'info_dict': {
                'id': 'mdb-362427',
                'ext': 'flv',
                'title': 'Servicezeit',
                'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
                'upload_date': '20140310',
                'is_live': False
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
            'info_dict': {
                'id': 'mdb-363194',
                'ext': 'flv',
                'title': 'Marga Spiegel ist tot',
                'description': 'md5:2309992a6716c347891c045be50992e4',
                'upload_date': '20140311',
                'is_live': False
            },
            'params': {
                'skip_download': True,
            },
        },
        {
            'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
            'md5': '83e9e8fefad36f357278759870805898',
            'info_dict': {
                'id': 'mdb-194332',
                'ext': 'mp3',
                'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
                'description': 'md5:2309992a6716c347891c045be50992e4',
                'upload_date': '20091129',
                'is_live': False
            },
        },
        {
            'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
            'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
            'info_dict': {
                'id': 'mdb-478135',
                'ext': 'mp3',
                'title': 'Flavia Coelho: Amar é Amar',
                'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
                'upload_date': '20140717',
                'is_live': False
            },
        },
        {
            'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
            'playlist_mincount': 146,
            'info_dict': {
                'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
            }
        },
        {
            'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
            'info_dict': {
                'id': 'mdb-103364',
                'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
                'ext': 'flv',
                'upload_date': '20150212',
                'is_live': True
            },
            'params': {
                'skip_download': True,
            },
        }
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        page_url = mobj.group('url')
        page_id = mobj.group('id')

        webpage = self._download_webpage(url, page_id)

        if mobj.group('player') is None:
            entries = [
                self.url_result(page_url + href, 'WDR')
                for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
            ]

            if entries:  # Playlist page
                return self.playlist_result(entries, page_id)

            # Overview page
            entries = []
            for page_num in itertools.count(2):
                hrefs = re.findall(
                    r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
                    webpage)
                entries.extend(
                    self.url_result(page_url + href, 'WDR')
                    for href in hrefs)
                next_url_m = re.search(
                    r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
                if not next_url_m:
                    break
                next_url = page_url + next_url_m.group(1)
                webpage = self._download_webpage(
                    next_url, page_id,
                    note='Downloading playlist page %d' % page_num)
            return self.playlist_result(entries, page_id)

        flashvars = compat_parse_qs(
            self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))

        page_id = flashvars['trackerClipId'][0]
        video_url = flashvars['dslSrc'][0]
        title = flashvars['trackerClipTitle'][0]
        thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
        is_live = flashvars.get('isLive', ['0'])[0] == '1'

        if is_live:
            title = self._live_title(title)

        if 'trackerClipAirTime' in flashvars:
            upload_date = flashvars['trackerClipAirTime'][0]
        else:
            upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')

        if upload_date:
            upload_date = unified_strdate(upload_date)

        if video_url.endswith('.f4m'):
            video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
            ext = 'flv'
        elif video_url.endswith('.smil'):
            fmt = self._extract_smil_formats(video_url, page_id)[0]
            video_url = fmt['url']
            sep = '&' if '?' in video_url else '?'
            video_url += sep
            video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43'
            ext = fmt['ext']
        else:
            ext = determine_ext(video_url)

        description = self._html_search_meta('Description', webpage, 'description')

        return {
            'id': page_id,
            'url': video_url,
            'ext': ext,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'upload_date': upload_date,
            'is_live': is_live
        }


class WDRMobileIE(InfoExtractor):
    _VALID_URL = r'''(?x)
        https?://mobile-ondemand\.wdr\.de/
        .*?/fsk(?P<age_limit>[0-9]+)
        /[0-9]+/[0-9]+/
        (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
    IE_NAME = 'wdr:mobile'
    _TEST = {
        'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
        'info_dict': {
            'title': '4283021',
            'id': '421735',
            'ext': 'mp4',
            'age_limit': 0,
        },
        'skip': 'Problems with loading data.'
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        return {
            'id': mobj.group('id'),
            'title': mobj.group('title'),
            'age_limit': int(mobj.group('age_limit')),
            'url': url,
            'http_headers': {
                'User-Agent': 'mobile',
            },
        }


class WDRMausIE(InfoExtractor):
    _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
    IE_DESC = 'Sendung mit der Maus'
    _TESTS = [{
        'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
        'info_dict': {
            'id': 'aktuelle-sendung',
            'ext': 'mp4',
            'thumbnail': 're:^http://.+\.jpg',
            'upload_date': 're:^[0-9]{8}$',
            'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
        }
    }, {
        'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
        'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
        'info_dict': {
            'id': '40_jahre_maus',
            'ext': 'mp4',
            'thumbnail': 're:^http://.+\.jpg',
            'upload_date': '20131007',
            'title': '12.03.2011 - 40 Jahre Maus',
        }
    }]

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)
        param_code = self._html_search_regex(
            r'<a href="\?startVideo=1&amp;([^"]+)"', webpage, 'parameters')

        title_date = self._search_regex(
            r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
            webpage, 'air date')
        title_str = self._html_search_regex(
            r'<h1>(.*?)</h1>', webpage, 'title')
        title = '%s - %s' % (title_date, title_str)
        upload_date = unified_strdate(
            self._html_search_meta('dc.date', webpage))

        fields = compat_parse_qs(param_code)
        video_url = fields['firstVideo'][0]
        thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])

        formats = [{
            'format_id': 'rtmp',
            'url': video_url,
        }]

        jscode = self._download_webpage(
            'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
            video_id, fatal=False,
            note='Downloading URL translation table',
            errnote='Could not download URL translation table')
        if jscode:
            for m in re.finditer(
                    r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
                    jscode):
                if video_url.startswith(m.group('stream')):
                    http_url = video_url.replace(
                        m.group('stream'), m.group('dl'))
                    formats.append({
                        'format_id': 'http',
                        'url': http_url,
                    })
                    break

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': title,
            'formats': formats,
            'thumbnail': thumbnail,
            'upload_date': upload_date,
        }
Commit	Line	Data
7807ee66	1	# -- coding: utf-8 --
b461641f S	2	from __future__ import unicode_literals
b461641f S	3
176cf9e0	4	import itertools
b461641f S	5	import re
	6
	7	from .common import InfoExtractor
1cc79574	8	from ..compat import (
cd7481a3	9	compat_parse_qs,
becafcbf	10	compat_urlparse,
1cc79574 PH	11	)
1cc79574 PH	12	from ..utils import (
b461641f	13	determine_ext,
cd7481a3	14	unified_strdate,
b461641f S	15	)
	16
	17
	18	class WDRIE(InfoExtractor):
	19	_PLAYER_REGEX = '-(?:video\|audio)player(?:_size-[LMS])?'
	20	_VALID_URL = r'(?P<url>https?://www\d?\.(?:wdr\d?\|funkhauseuropa)\.de/)(?P<id>.+?)(?P<player>%s)?\.html' % _PLAYER_REGEX
	21
	22	_TESTS = [
	23	{
	24	'url': 'http://www1.wdr.de/mediathek/video/sendungen/servicezeit/videoservicezeit560-videoplayer_size-L.html',
	25	'info_dict': {
	26	'id': 'mdb-362427',
	27	'ext': 'flv',
	28	'title': 'Servicezeit',
	29	'description': 'md5:c8f43e5e815eeb54d0b96df2fba906cb',
	30	'upload_date': '20140310',
b8988b63	31	'is_live': False
b461641f S	32	},
	33	'params': {
	34	'skip_download': True,
	35	},
	36	},
	37	{
	38	'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
	39	'info_dict': {
	40	'id': 'mdb-363194',
	41	'ext': 'flv',
	42	'title': 'Marga Spiegel ist tot',
87a29e6f	43	'description': 'md5:2309992a6716c347891c045be50992e4',
b461641f	44	'upload_date': '20140311',
b8988b63	45	'is_live': False
b461641f S	46	},
	47	'params': {
	48	'skip_download': True,
	49	},
	50	},
	51	{
	52	'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
	53	'md5': '83e9e8fefad36f357278759870805898',
	54	'info_dict': {
	55	'id': 'mdb-194332',
	56	'ext': 'mp3',
	57	'title': 'Erlebte Geschichten: Marga Spiegel (29.11.2009)',
87a29e6f	58	'description': 'md5:2309992a6716c347891c045be50992e4',
b461641f	59	'upload_date': '20091129',
b8988b63	60	'is_live': False
b461641f S	61	},
	62	},
	63	{
ff1956e0 PH	64	'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
ff1956e0 PH	65	'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
b461641f	66	'info_dict': {
ff1956e0	67	'id': 'mdb-478135',
b461641f	68	'ext': 'mp3',
ff1956e0	69	'title': 'Flavia Coelho: Amar é Amar',
87a29e6f	70	'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
ff1956e0	71	'upload_date': '20140717',
b8988b63	72	'is_live': False
b461641f S	73	},
b461641f S	74	},
176cf9e0 PH	75	{
	76	'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
	77	'playlist_mincount': 146,
dd8982f1 PH	78	'info_dict': {
	79	'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
	80	}
b8988b63 AA	81	},
	82	{
	83	'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
	84	'info_dict': {
	85	'id': 'mdb-103364',
	86	'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	87	'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
	88	'ext': 'flv',
	89	'upload_date': '20150212',
	90	'is_live': True
	91	},
	92	'params': {
	93	'skip_download': True,
	94	},
176cf9e0	95	}
b461641f S	96	]
	97
	98	def _real_extract(self, url):
	99	mobj = re.match(self._VALID_URL, url)
	100	page_url = mobj.group('url')
	101	page_id = mobj.group('id')
	102
	103	webpage = self._download_webpage(url, page_id)
	104
	105	if mobj.group('player') is None:
	106	entries = [
	107	self.url_result(page_url + href, 'WDR')
	108	for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
	109	]
176cf9e0 PH	110
	111	if entries: # Playlist page
	112	return self.playlist_result(entries, page_id)
	113
	114	# Overview page
	115	entries = []
	116	for page_num in itertools.count(2):
	117	hrefs = re.findall(
	118	r'<li class="mediathekvideo"\s>\s<img[^>]>\s<a href="(/mediathek/video/[^"]+)"',
	119	webpage)
	120	entries.extend(
	121	self.url_result(page_url + href, 'WDR')
	122	for href in hrefs)
	123	next_url_m = re.search(
	124	r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
	125	if not next_url_m:
	126	break
	127	next_url = page_url + next_url_m.group(1)
	128	webpage = self._download_webpage(
	129	next_url, page_id,
	130	note='Downloading playlist page %d' % page_num)
b461641f S	131	return self.playlist_result(entries, page_id)
b461641f S	132
94e8df3a	133	flashvars = compat_parse_qs(
b461641f S	134	self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
	135
	136	page_id = flashvars['trackerClipId'][0]
	137	video_url = flashvars['dslSrc'][0]
	138	title = flashvars['trackerClipTitle'][0]
	139	thumbnail = flashvars['startPicture'][0] if 'startPicture' in flashvars else None
b8988b63 AA	140	is_live = flashvars.get('isLive', ['0'])[0] == '1'
	141
	142	if is_live:
	143	title = self._live_title(title)
b461641f S	144
	145	if 'trackerClipAirTime' in flashvars:
	146	upload_date = flashvars['trackerClipAirTime'][0]
	147	else:
	148	upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
	149
	150	if upload_date:
	151	upload_date = unified_strdate(upload_date)
	152
	153	if video_url.endswith('.f4m'):
	154	video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
	155	ext = 'flv'
b8988b63 AA	156	elif video_url.endswith('.smil'):
	157	fmt = self._extract_smil_formats(video_url, page_id)[0]
	158	video_url = fmt['url']
	159	sep = '&' if '?' in video_url else '?'
	160	video_url += sep
	161	video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43'
	162	ext = fmt['ext']
b461641f S	163	else:
	164	ext = determine_ext(video_url)
	165
	166	description = self._html_search_meta('Description', webpage, 'description')
	167
	168	return {
	169	'id': page_id,
	170	'url': video_url,
	171	'ext': ext,
	172	'title': title,
	173	'description': description,
	174	'thumbnail': thumbnail,
	175	'upload_date': upload_date,
b8988b63	176	'is_live': is_live
cd7481a3 PH	177	}
	178
	179
e4cbb5f3 PH	180	class WDRMobileIE(InfoExtractor):
	181	_VALID_URL = r'''(?x)
	182	https?://mobile-ondemand\.wdr\.de/
	183	.*?/fsk(?P<age_limit>[0-9]+)
	184	/[0-9]+/[0-9]+/
	185	(?P<id>[0-9]+)_(?P<title>[0-9]+)'''
	186	IE_NAME = 'wdr:mobile'
	187	_TEST = {
	188	'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
	189	'info_dict': {
	190	'title': '4283021',
	191	'id': '421735',
7807ee66	192	'ext': 'mp4',
e4cbb5f3 PH	193	'age_limit': 0,
e4cbb5f3 PH	194	},
7807ee66	195	'skip': 'Problems with loading data.'
e4cbb5f3 PH	196	}
	197
	198	def _real_extract(self, url):
	199	mobj = re.match(self._VALID_URL, url)
	200	return {
	201	'id': mobj.group('id'),
	202	'title': mobj.group('title'),
	203	'age_limit': int(mobj.group('age_limit')),
	204	'url': url,
e1554a40 JMF	205	'http_headers': {
	206	'User-Agent': 'mobile',
	207	},
e4cbb5f3 PH	208	}
	209
	210
cd7481a3	211	class WDRMausIE(InfoExtractor):
9a7b072e	212	_VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5\|(?<!index)\.php5\|/(?:$\|[?#]))'
cd7481a3 PH	213	IE_DESC = 'Sendung mit der Maus'
	214	_TESTS = [{
	215	'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
	216	'info_dict': {
	217	'id': 'aktuelle-sendung',
	218	'ext': 'mp4',
	219	'thumbnail': 're:^http://.+\.jpg',
	220	'upload_date': 're:^[0-9]{8}$',
	221	'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
	222	}
	223	}, {
	224	'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
	225	'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
	226	'info_dict': {
	227	'id': '40_jahre_maus',
	228	'ext': 'mp4',
	229	'thumbnail': 're:^http://.+\.jpg',
	230	'upload_date': '20131007',
	231	'title': '12.03.2011 - 40 Jahre Maus',
	232	}
	233	}]
	234
	235	def _real_extract(self, url):
7b6faddf	236	video_id = self._match_id(url)
cd7481a3 PH	237
	238	webpage = self._download_webpage(url, video_id)
	239	param_code = self._html_search_regex(
	240	r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters')
	241
	242	title_date = self._search_regex(
	243	r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
	244	webpage, 'air date')
	245	title_str = self._html_search_regex(
	246	r'<h1>(.*?)</h1>', webpage, 'title')
	247	title = '%s - %s' % (title_date, title_str)
	248	upload_date = unified_strdate(
	249	self._html_search_meta('dc.date', webpage))
	250
	251	fields = compat_parse_qs(param_code)
	252	video_url = fields['firstVideo'][0]
	253	thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
	254
	255	formats = [{
	256	'format_id': 'rtmp',
	257	'url': video_url,
	258	}]
	259
	260	jscode = self._download_webpage(
	261	'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
	262	video_id, fatal=False,
	263	note='Downloading URL translation table',
	264	errnote='Could not download URL translation table')
	265	if jscode:
	266	for m in re.finditer(
	267	r"stream:\s'dslSrc=(?P<stream>[^']+)',\sdownload:\s'(?P<dl>[^']+)'\s\}",
	268	jscode):
	269	if video_url.startswith(m.group('stream')):
	270	http_url = video_url.replace(
	271	m.group('stream'), m.group('dl'))
	272	formats.append({
	273	'format_id': 'http',
	274	'url': http_url,
	275	})
	276	break
	277
	278	self._sort_formats(formats)
	279
	280	return {
	281	'id': video_id,
	282	'title': title,
	283	'formats': formats,
	284	'thumbnail': thumbnail,
	285	'upload_date': upload_date,
	286	}