Merge remote-tracking branch 'upstream/master'
This commit is contained in:
Marco Ferragina
commit
5ba6537e03
@ -35,10 +35,14 @@ class TestInfoExtractor(unittest.TestCase):
|
||||
<meta name="og:title" content='Foo'/>
|
||||
<meta content="Some video's description " name="og:description"/>
|
||||
<meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&key2=val2'/>
|
||||
<meta content='application/x-shockwave-flash' property='og:video:type'>
|
||||
<meta content='Foo' property=og:foobar>
|
||||
'''
|
||||
self.assertEqual(ie._og_search_title(html), 'Foo')
|
||||
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
|
||||
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
|
||||
self.assertEqual(ie._og_search_video_url(html, default=None), None)
|
||||
self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
|
||||
|
||||
def test_html_search_meta(self):
|
||||
ie = self.ie
|
||||
|
||||
@ -319,7 +319,6 @@ from .macgamestore import MacGameStoreIE
|
||||
from .mailru import MailRuIE
|
||||
from .malemotion import MalemotionIE
|
||||
from .mdr import MDRIE
|
||||
from .megavideoz import MegaVideozIE
|
||||
from .metacafe import MetacafeIE
|
||||
from .metacritic import MetacriticIE
|
||||
from .mgoon import MgoonIE
|
||||
|
||||
@ -3,7 +3,11 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
parse_filesize,
|
||||
qualities,
|
||||
)
|
||||
|
||||
|
||||
class Channel9IE(InfoExtractor):
|
||||
@ -28,7 +32,7 @@ class Channel9IE(InfoExtractor):
|
||||
'title': 'Developer Kick-Off Session: Stuff We Love',
|
||||
'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
|
||||
'duration': 4576,
|
||||
'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
|
||||
'thumbnail': 're:http://.*\.jpg',
|
||||
'session_code': 'KOS002',
|
||||
'session_day': 'Day 1',
|
||||
'session_room': 'Arena 1A',
|
||||
@ -44,31 +48,29 @@ class Channel9IE(InfoExtractor):
|
||||
'title': 'Self-service BI with Power BI - nuclear testing',
|
||||
'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
|
||||
'duration': 1540,
|
||||
'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
|
||||
'thumbnail': 're:http://.*\.jpg',
|
||||
'authors': ['Mike Wilmot'],
|
||||
},
|
||||
},
|
||||
{
|
||||
# low quality mp4 is best
|
||||
'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
|
||||
'info_dict': {
|
||||
'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ranges for the Standard Library',
|
||||
'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
|
||||
'duration': 5646,
|
||||
'thumbnail': 're:http://.*\.jpg',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
]
|
||||
|
||||
_RSS_URL = 'http://channel9.msdn.com/%s/RSS'
|
||||
|
||||
# Sorted by quality
|
||||
_known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
|
||||
|
||||
def _restore_bytes(self, formatted_size):
|
||||
if not formatted_size:
|
||||
return 0
|
||||
m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
|
||||
if not m:
|
||||
return 0
|
||||
units = m.group('units')
|
||||
try:
|
||||
exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
|
||||
except ValueError:
|
||||
return 0
|
||||
size = float(m.group('size'))
|
||||
return int(size * (1024 ** exponent))
|
||||
|
||||
def _formats_from_html(self, html):
|
||||
FORMAT_REGEX = r'''
|
||||
(?x)
|
||||
@ -78,16 +80,20 @@ class Channel9IE(InfoExtractor):
|
||||
<h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
|
||||
</div>)? # File size part may be missing
|
||||
'''
|
||||
# Extract known formats
|
||||
quality = qualities((
|
||||
'MP3', 'MP4',
|
||||
'Low Quality WMV', 'Low Quality MP4',
|
||||
'Mid Quality WMV', 'Mid Quality MP4',
|
||||
'High Quality WMV', 'High Quality MP4'))
|
||||
formats = [{
|
||||
'url': x.group('url'),
|
||||
'format_id': x.group('quality'),
|
||||
'format_note': x.group('note'),
|
||||
'format': '%s (%s)' % (x.group('quality'), x.group('note')),
|
||||
'filesize': self._restore_bytes(x.group('filesize')), # File size is approximate
|
||||
'preference': self._known_formats.index(x.group('quality')),
|
||||
'filesize_approx': parse_filesize(x.group('filesize')),
|
||||
'quality': quality(x.group('quality')),
|
||||
'vcodec': 'none' if x.group('note') == 'Audio only' else None,
|
||||
} for x in list(re.finditer(FORMAT_REGEX, html)) if x.group('quality') in self._known_formats]
|
||||
} for x in list(re.finditer(FORMAT_REGEX, html))]
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
||||
@ -646,7 +646,8 @@ class InfoExtractor(object):
|
||||
@staticmethod
|
||||
def _og_regexes(prop):
|
||||
content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\'|\s*([^\s"\'=<>`]+?))'
|
||||
property_re = r'(?:name|property)=[\'"]?og:%s[\'"]?' % re.escape(prop)
|
||||
property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
|
||||
% {'prop': re.escape(prop)})
|
||||
template = r'<meta[^>]+?%s[^>]+?%s'
|
||||
return [
|
||||
template % (property_re, content_re),
|
||||
|
||||
@ -27,9 +27,7 @@ class CriterionIE(InfoExtractor):
|
||||
final_url = self._search_regex(
|
||||
r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
|
||||
title = self._og_search_title(webpage)
|
||||
description = self._html_search_regex(
|
||||
r'<meta name="description" content="(.+?)" />',
|
||||
webpage, 'video description')
|
||||
description = self._html_search_meta('description', webpage)
|
||||
thumbnail = self._search_regex(
|
||||
r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
|
||||
webpage, 'thumbnail url')
|
||||
|
||||
@ -2,11 +2,15 @@ from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_str,
|
||||
compat_urllib_parse,
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_urlparse,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
parse_duration,
|
||||
replace_extension,
|
||||
)
|
||||
|
||||
|
||||
@ -28,6 +32,7 @@ class FiveMinIE(InfoExtractor):
|
||||
'id': '518013791',
|
||||
'ext': 'mp4',
|
||||
'title': 'iPad Mini with Retina Display Review',
|
||||
'duration': 177,
|
||||
},
|
||||
},
|
||||
{
|
||||
@ -38,9 +43,52 @@ class FiveMinIE(InfoExtractor):
|
||||
'id': '518086247',
|
||||
'ext': 'mp4',
|
||||
'title': 'How to Make a Next-Level Fruit Salad',
|
||||
'duration': 184,
|
||||
},
|
||||
},
|
||||
]
|
||||
_ERRORS = {
|
||||
'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
|
||||
'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
|
||||
'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
|
||||
'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
|
||||
'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
|
||||
'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
|
||||
}
|
||||
_QUALITIES = {
|
||||
1: {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
},
|
||||
2: {
|
||||
'width': 854,
|
||||
'height': 480,
|
||||
},
|
||||
4: {
|
||||
'width': 1280,
|
||||
'height': 720,
|
||||
},
|
||||
8: {
|
||||
'width': 1920,
|
||||
'height': 1080,
|
||||
},
|
||||
16: {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
},
|
||||
32: {
|
||||
'width': 854,
|
||||
'height': 480,
|
||||
},
|
||||
64: {
|
||||
'width': 1280,
|
||||
'height': 720,
|
||||
},
|
||||
128: {
|
||||
'width': 640,
|
||||
'height': 360,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -59,26 +107,36 @@ class FiveMinIE(InfoExtractor):
|
||||
'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
|
||||
video_id)
|
||||
if not response['success']:
|
||||
err_msg = response['errorMessage']
|
||||
if err_msg == 'ErrorVideoUserNotGeo':
|
||||
msg = 'Video not available from your location'
|
||||
else:
|
||||
msg = 'Aol said: %s' % err_msg
|
||||
raise ExtractorError(msg, expected=True, video_id=video_id)
|
||||
raise ExtractorError(
|
||||
'%s said: %s' % (
|
||||
self.IE_NAME,
|
||||
self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
|
||||
expected=True)
|
||||
info = response['binding'][0]
|
||||
|
||||
second_id = compat_str(int(video_id[:-2]) + 1)
|
||||
formats = []
|
||||
for quality, height in [(1, 320), (2, 480), (4, 720), (8, 1080)]:
|
||||
if any(r['ID'] == quality for r in info['Renditions']):
|
||||
parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
|
||||
compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
|
||||
for rendition in info['Renditions']:
|
||||
if rendition['RenditionType'] == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls'))
|
||||
elif rendition['RenditionType'] == 'aac':
|
||||
continue
|
||||
else:
|
||||
rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
|
||||
quality = self._QUALITIES.get(rendition['ID'], {})
|
||||
formats.append({
|
||||
'format_id': compat_str(quality),
|
||||
'url': 'http://avideos.5min.com/%s/%s/%s_%s.mp4' % (second_id[-3:], second_id, video_id, quality),
|
||||
'height': height,
|
||||
'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
|
||||
'url': rendition_url,
|
||||
'width': quality.get('width'),
|
||||
'height': quality.get('height'),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': info['Title'],
|
||||
'thumbnail': info.get('ThumbURL'),
|
||||
'duration': parse_duration(info.get('Duration')),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -28,7 +28,7 @@ class JeuxVideoIE(InfoExtractor):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
title = mobj.group(1)
|
||||
webpage = self._download_webpage(url, title)
|
||||
title = self._html_search_meta('name', webpage)
|
||||
title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
|
||||
config_url = self._html_search_regex(
|
||||
r'data-src="(/contenu/medias/video.php.*?)"',
|
||||
webpage, 'config URL')
|
||||
|
||||
@ -1,56 +0,0 @@
|
||||
# encoding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
||||
class MegaVideozIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>[^/]+)(?:/(?P<display_id>[^/]+))?'
|
||||
_TEST = {
|
||||
'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader',
|
||||
'info_dict': {
|
||||
'id': '48723',
|
||||
'display_id': 'SMPTE-Universal-Film-Leader',
|
||||
'ext': 'mp4',
|
||||
'title': 'SMPTE Universal Film Leader',
|
||||
'thumbnail': 're:https?://.*?\.jpg',
|
||||
'duration': 10.93,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
display_id = mobj.group('display_id') or video_id
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
if any(p in webpage for p in ('>Video Not Found<', '>404 Error<')):
|
||||
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
|
||||
|
||||
config = self._download_xml(
|
||||
self._search_regex(
|
||||
r"var\s+cnf\s*=\s*'([^']+)'", webpage, 'cnf url'),
|
||||
display_id)
|
||||
|
||||
video_url = xpath_text(config, './file', 'video url', fatal=True)
|
||||
title = xpath_text(config, './title', 'title', fatal=True)
|
||||
thumbnail = xpath_text(config, './image', 'thumbnail')
|
||||
duration = float_or_none(xpath_text(config, './duration', 'duration'))
|
||||
video_id = xpath_text(config, './mediaid', 'video id') or video_id
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration
|
||||
}
|
||||
@ -212,7 +212,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
url = url.replace('http://', 'https://')
|
||||
password_request = compat_urllib_request.Request(url + '/password', data)
|
||||
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
||||
password_request.add_header('Cookie', 'clip_v=1; vuid=%s' % vuid)
|
||||
password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid)
|
||||
password_request.add_header('Referer', url)
|
||||
return self._download_webpage(
|
||||
password_request, video_id,
|
||||
|
||||
@ -46,6 +46,12 @@ class YandexMusicTrackIE(InfoExtractor):
|
||||
% (data['host'], key, data['ts'] + data['path'], storage[1]))
|
||||
|
||||
def _get_track_info(self, track):
|
||||
thumbnail = None
|
||||
cover_uri = track.get('albums', [{}])[0].get('coverUri')
|
||||
if cover_uri:
|
||||
thumbnail = cover_uri.replace('%%', 'orig')
|
||||
if not thumbnail.startswith('http'):
|
||||
thumbnail = 'http://' + thumbnail
|
||||
return {
|
||||
'id': track['id'],
|
||||
'ext': 'mp3',
|
||||
@ -53,6 +59,7 @@ class YandexMusicTrackIE(InfoExtractor):
|
||||
'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
|
||||
'filesize': int_or_none(track.get('fileSize')),
|
||||
'duration': float_or_none(track.get('durationMs'), 1000),
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -1371,7 +1371,12 @@ def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
|
||||
v = getattr(v, get_attr, None)
|
||||
if v == '':
|
||||
v = None
|
||||
return default if v is None else (int(v) * invscale // scale)
|
||||
if v is None:
|
||||
return default
|
||||
try:
|
||||
return int(v) * invscale // scale
|
||||
except ValueError:
|
||||
return default
|
||||
|
||||
|
||||
def str_or_none(v, default=None):
|
||||
@ -1387,7 +1392,12 @@ def str_to_int(int_str):
|
||||
|
||||
|
||||
def float_or_none(v, scale=1, invscale=1, default=None):
|
||||
return default if v is None else (float(v) * invscale / scale)
|
||||
if v is None:
|
||||
return default
|
||||
try:
|
||||
return float(v) * invscale / scale
|
||||
except ValueError:
|
||||
return default
|
||||
|
||||
|
||||
def parse_duration(s):
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user