aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--test/test_YoutubeDL.py4
-rw-r--r--test/test_playlists.py10
-rw-r--r--youtube_dl/extractor/__init__.py6
-rw-r--r--youtube_dl/extractor/empflix.py22
-rw-r--r--youtube_dl/extractor/ndr.py15
-rw-r--r--youtube_dl/extractor/nrk.py80
-rw-r--r--youtube_dl/extractor/nuvid.py2
-rw-r--r--youtube_dl/extractor/pornhub.py2
-rw-r--r--youtube_dl/extractor/streamcz.py22
-rw-r--r--youtube_dl/extractor/swrmediathek.py104
10 files changed, 237 insertions, 30 deletions
diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py
index 8735013f7..e794cc97f 100644
--- a/test/test_YoutubeDL.py
+++ b/test/test_YoutubeDL.py
@@ -67,7 +67,7 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'mp4')
- # No prefer_free_formats => prefer mp4 and flv for greater compatibilty
+ # No prefer_free_formats => prefer mp4 and flv for greater compatibility
ydl = YDL()
ydl.params['prefer_free_formats'] = False
formats = [
@@ -279,7 +279,7 @@ class TestFormatSelection(unittest.TestCase):
self.assertEqual(ydl._format_note({}), '')
assertRegexpMatches(self, ydl._format_note({
'vbr': 10,
- }), '^x\s*10k$')
+ }), '^\s*10k$')
if __name__ == '__main__':
unittest.main()
diff --git a/test/test_playlists.py b/test/test_playlists.py
index cc871698a..63d31db8c 100644
--- a/test/test_playlists.py
+++ b/test/test_playlists.py
@@ -213,16 +213,16 @@ class TestPlaylists(unittest.TestCase):
self.assertIsPlaylist(result)
self.assertEqual(result['id'], 'dezhurnyi_angel')
self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012)')
- self.assertTrue(len(result['entries']) >= 23)
+ self.assertTrue(len(result['entries']) >= 16)
def test_ivi_compilation_season(self):
dl = FakeYDL()
ie = IviCompilationIE(dl)
- result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season2')
+ result = ie.extract('http://www.ivi.ru/watch/dezhurnyi_angel/season1')
self.assertIsPlaylist(result)
- self.assertEqual(result['id'], 'dezhurnyi_angel/season2')
- self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 2 сезон')
- self.assertTrue(len(result['entries']) >= 7)
+ self.assertEqual(result['id'], 'dezhurnyi_angel/season1')
+ self.assertEqual(result['title'], 'Дежурный ангел (2010 - 2012) 1 сезон')
+ self.assertTrue(len(result['entries']) >= 16)
def test_imdb_list(self):
dl = FakeYDL()
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 3503c76b7..def58f1d6 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -194,7 +194,10 @@ from .normalboots import NormalbootsIE
from .novamov import NovaMovIE
from .nowness import NownessIE
from .nowvideo import NowVideoIE
-from .nrk import NRKIE
+from .nrk import (
+ NRKIE,
+ NRKTVIE,
+)
from .ntv import NTVIE
from .nytimes import NYTimesIE
from .nuvid import NuvidIE
@@ -260,6 +263,7 @@ from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
+from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE
from .sztvhu import SztvHuIE
from .teamcoco import TeamcocoIE
diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
index eaeee5a51..e6952588f 100644
--- a/youtube_dl/extractor/empflix.py
+++ b/youtube_dl/extractor/empflix.py
@@ -3,20 +3,18 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
-)
class EmpflixIE(InfoExtractor):
_VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
_TEST = {
'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
- 'md5': '5e5cc160f38ca9857f318eb97146e13e',
+ 'md5': 'b1bc15b6412d33902d6e5952035fcabc',
'info_dict': {
'id': '33051',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Amateur Finger Fuck',
+ 'description': 'Amateur solo finger fucking.',
'age_limit': 18,
}
}
@@ -30,6 +28,8 @@ class EmpflixIE(InfoExtractor):
video_title = self._html_search_regex(
r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
+ video_description = self._html_search_regex(
+ r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
cfg_url = self._html_search_regex(
r'flashvars\.config = escape\("([^"]+)"',
@@ -37,12 +37,18 @@ class EmpflixIE(InfoExtractor):
cfg_xml = self._download_xml(
cfg_url, video_id, note='Downloading metadata')
- video_url = cfg_xml.find('videoLink').text
+
+ formats = [
+ {
+ 'url': item.find('videoLink').text,
+ 'format_id': item.find('res').text,
+ } for item in cfg_xml.findall('./quality/item')
+ ]
return {
'id': video_id,
- 'url': video_url,
- 'ext': 'flv',
'title': video_title,
+ 'description': video_description,
+ 'formats': formats,
'age_limit': age_limit,
}
diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py
index 53b34f5e6..3d6096e46 100644
--- a/youtube_dl/extractor/ndr.py
+++ b/youtube_dl/extractor/ndr.py
@@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
+ qualities,
)
@@ -57,7 +58,7 @@ class NDRIE(InfoExtractor):
formats = []
- mp3_url = re.search(r'''{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
+ mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page)
if mp3_url:
formats.append({
'url': mp3_url.group('audio'),
@@ -66,15 +67,15 @@ class NDRIE(InfoExtractor):
thumbnail = None
- video_url = re.search(r'''3: {src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
+ video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.hi\.mp4', type:"video/mp4"},''', page)
if video_url:
- thumbnails = re.findall(r'''\d+: {src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
+ thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page)
if thumbnails:
- QUALITIES = ['xs', 's', 'm', 'l', 'xl']
- thumbnails.sort(key=lambda thumb: QUALITIES.index(thumb[1]) if thumb[1] in QUALITIES else -1)
- thumbnail = 'http://www.ndr.de' + thumbnails[-1][0]
+ quality_key = qualities(['xs', 's', 'm', 'l', 'xl'])
+ largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1]))
+ thumbnail = 'http://www.ndr.de' + largest[0]
- for format_id in ['lo', 'hi', 'hq']:
+ for format_id in 'lo', 'hi', 'hq':
formats.append({
'url': '%s.%s.mp4' % (video_url.group('video'), format_id),
'format_id': format_id,
diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py
index e6d68b836..f5117d7b3 100644
--- a/youtube_dl/extractor/nrk.py
+++ b/youtube_dl/extractor/nrk.py
@@ -4,7 +4,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+ unified_strdate,
+)
class NRKIE(InfoExtractor):
@@ -64,4 +68,78 @@ class NRKIE(InfoExtractor):
'title': data['title'],
'description': data['description'],
'thumbnail': thumbnail,
+ }
+
+
+class NRKTVIE(InfoExtractor):
+ _VALID_URL = r'http://tv\.nrk\.no/(?:serie/[^/]+|program)/(?P<id>[a-z]{4}\d{8})'
+
+ _TESTS = [
+ {
+ 'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/muhh48000314/23-05-2014',
+ 'md5': '7b96112fbae1faf09a6f9ae1aff6cb84',
+ 'info_dict': {
+ 'id': 'muhh48000314',
+ 'ext': 'flv',
+ 'title': '20 spørsmål',
+ 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
+ 'upload_date': '20140523',
+ 'duration': 1741.52,
+ }
+ },
+ {
+ 'url': 'http://tv.nrk.no/program/mdfp15000514',
+ 'md5': '383650ece2b25ecec996ad7b5bb2a384',
+ 'info_dict': {
+ 'id': 'mdfp15000514',
+ 'ext': 'flv',
+ 'title': 'Kunnskapskanalen: Grunnlovsjubiléet - Stor ståhei for ingenting',
+ 'description': 'md5:654c12511f035aed1e42bdf5db3b206a',
+ 'upload_date': '20140524',
+ 'duration': 4605.0,
+ }
+ },
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ page = self._download_webpage(url, video_id)
+
+ title = self._html_search_meta('title', page, 'title')
+ description = self._html_search_meta('description', page, 'description')
+ thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
+ upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
+ duration = self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False)
+ if duration:
+ duration = float(duration)
+
+ formats = []
+
+ f4m_url = re.search(r'data-media="([^"]+)"', page)
+ if f4m_url:
+ formats.append({
+ 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
+ 'format_id': 'f4m',
+ 'ext': 'flv',
+ })
+
+ m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
+ if m3u8_url:
+ formats.append({
+ 'url': m3u8_url.group(1),
+ 'format_id': 'm3u8',
+ })
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ 'duration': duration,
+ 'formats': formats,
} \ No newline at end of file
diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py
index f0befa116..e3db9fe8c 100644
--- a/youtube_dl/extractor/nuvid.py
+++ b/youtube_dl/extractor/nuvid.py
@@ -30,7 +30,7 @@ class NuvidIE(InfoExtractor):
webpage, 'title').strip()
url_end = self._html_search_regex(
- r'href="(/mp4/[^"]+)"[^>]*data-link_type="mp4"',
+ r'href="(/[^"]+)"[^>]*data-link_type="mp4"',
webpage, 'video_url')
video_url = 'http://m.nuvid.com' + url_end
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 7dd3dca0d..4118ee956 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -45,7 +45,7 @@ class PornHubIE(InfoExtractor):
video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
- r'(?s)<div class="video-info-row">\s*From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
+ r'(?s)From:&nbsp;.+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
webpage, 'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
if thumbnail:
diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py
index 7362904db..73efe9542 100644
--- a/youtube_dl/extractor/streamcz.py
+++ b/youtube_dl/extractor/streamcz.py
@@ -5,13 +5,16 @@ import re
import json
from .common import InfoExtractor
-from ..utils import int_or_none
+from ..utils import (
+ int_or_none,
+ compat_str,
+)
class StreamCZIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)'
- _TEST = {
+ _TESTS = [{
'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti',
'md5': '6d3ca61a8d0633c9c542b92fcb936b0c',
'info_dict': {
@@ -22,7 +25,18 @@ class StreamCZIE(InfoExtractor):
'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100',
'duration': 256,
},
- }
+ }, {
+ 'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka',
+ 'md5': '246272e753e26bbace7fcd9deca0650c',
+ 'info_dict': {
+ 'id': '10002447',
+ 'ext': 'mp4',
+ 'title': 'Kancelář Blaník: Tři roky pro Mazánka',
+ 'description': 'md5:9177695a8b756a0a8ab160de4043b392',
+ 'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000',
+ 'duration': 368,
+ },
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -57,7 +71,7 @@ class StreamCZIE(InfoExtractor):
self._sort_formats(formats)
return {
- 'id': str(jsonData['id']),
+ 'id': compat_str(jsonData['episode_id']),
'title': self._og_search_title(webpage),
'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'),
'formats': formats,
diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py
new file mode 100644
index 000000000..6c688c520
--- /dev/null
+++ b/youtube_dl/extractor/swrmediathek.py
@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class SWRMediathekIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+
+ _TESTS = [{
+ 'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6',
+ 'md5': '8c5f6f0172753368547ca8413a7768ac',
+ 'info_dict': {
+ 'id': '849790d0-dab8-11e3-a953-0026b975f2e6',
+ 'ext': 'mp4',
+ 'title': 'SWR odysso',
+ 'description': 'md5:2012e31baad36162e97ce9eb3f157b8a',
+ 'thumbnail': 're:^http:.*\.jpg$',
+ 'duration': 2602,
+ 'upload_date': '20140515',
+ 'uploader': 'SWR Fernsehen',
+ 'uploader_id': '990030',
+ },
+ }, {
+ 'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
+ 'md5': 'b10ab854f912eecc5a6b55cd6fc1f545',
+ 'info_dict': {
+ 'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6',
+ 'ext': 'mp4',
+ 'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen',
+ 'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2',
+ 'thumbnail': 're:http://.*\.jpg',
+ 'duration': 5305,
+ 'upload_date': '20140516',
+ 'uploader': 'SWR Fernsehen',
+ 'uploader_id': '990030',
+ },
+ }, {
+ 'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6',
+ 'md5': '4382e4ef2c9d7ce6852535fa867a0dd3',
+ 'info_dict': {
+ 'id': 'bba23e10-cb93-11e3-bf7f-0026b975f2e6',
+ 'ext': 'mp3',
+ 'title': 'Saša Stanišic: Vor dem Fest',
+ 'description': 'md5:5b792387dc3fbb171eb709060654e8c9',
+ 'thumbnail': 're:http://.*\.jpg',
+ 'duration': 3366,
+ 'upload_date': '20140520',
+ 'uploader': 'SWR 2',
+ 'uploader_id': '284670',
+ }
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
+ video = self._download_json(
+ 'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id, video_id, 'Downloading video JSON')
+
+ attr = video['attr']
+ media_type = attr['entry_etype']
+
+ formats = []
+ for entry in video['sub']:
+ if entry['name'] != 'entry_media':
+ continue
+
+ entry_attr = entry['attr']
+ codec = entry_attr['val0']
+ quality = int(entry_attr['val1'])
+
+ fmt = {
+ 'url': entry_attr['val2'],
+ 'quality': quality,
+ }
+
+ if media_type == 'Video':
+ fmt.update({
+ 'format_note': ['144p', '288p', '544p'][quality-1],
+ 'vcodec': codec,
+ })
+ elif media_type == 'Audio':
+ fmt.update({
+ 'acodec': codec,
+ })
+ formats.append(fmt)
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': attr['entry_title'],
+ 'description': attr['entry_descl'],
+ 'thumbnail': attr['entry_image_16_9'],
+ 'duration': parse_duration(attr['entry_durat']),
+ 'upload_date': attr['entry_pdatet'][:-4],
+ 'uploader': attr['channel_title'],
+ 'uploader_id': attr['channel_idkey'],
+ 'formats': formats,
+ } \ No newline at end of file
generated by cgit v1.2.3 (git 2.26.2) at 2024-07-02 17:01:51 +0000