mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-06-26 00:27:57 +00:00
Compare commits
18 Commits
8f31d4934e
...
660832b79e
Author | SHA1 | Date | |
---|---|---|---|
|
660832b79e | ||
|
0153b387e5 | ||
|
a48fe7491d | ||
|
e20ca543f0 | ||
|
e39466051f | ||
|
d95c0d203f | ||
|
3bde6a5752 | ||
|
50f6c5668a | ||
|
b4ff08bd2d | ||
|
88bd8b9f87 | ||
|
5aee29b7ca | ||
|
df617513cc | ||
|
e1b7640587 | ||
|
6d1af4e2cf | ||
|
f5e01562b1 | ||
|
2fcb8b8c20 | ||
|
7def329f19 | ||
|
d59b83f04b |
|
@ -5,9 +5,9 @@ import hashlib
|
|||
import json
|
||||
import os.path
|
||||
import re
|
||||
import types
|
||||
import ssl
|
||||
import sys
|
||||
import types
|
||||
import unittest
|
||||
|
||||
import youtube_dl.extractor
|
||||
|
@ -181,18 +181,18 @@ def expect_value(self, got, expected, field):
|
|||
op, _, expected_num = expected.partition(':')
|
||||
expected_num = int(expected_num)
|
||||
if op == 'mincount':
|
||||
assert_func = assertGreaterEqual
|
||||
assert_func = self.assertGreaterEqual
|
||||
msg_tmpl = 'Expected %d items in field %s, but only got %d'
|
||||
elif op == 'maxcount':
|
||||
assert_func = assertLessEqual
|
||||
assert_func = self.assertLessEqual
|
||||
msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
|
||||
elif op == 'count':
|
||||
assert_func = assertEqual
|
||||
assert_func = self.assertEqual
|
||||
msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
|
||||
else:
|
||||
assert False
|
||||
assert_func(
|
||||
self, len(got), expected_num,
|
||||
len(got), expected_num,
|
||||
msg_tmpl % (expected_num, field, len(got)))
|
||||
return
|
||||
self.assertEqual(
|
||||
|
@ -262,27 +262,6 @@ def assertRegexpMatches(self, text, regexp, msg=None):
|
|||
self.assertTrue(m, msg)
|
||||
|
||||
|
||||
def assertGreaterEqual(self, got, expected, msg=None):
|
||||
if not (got >= expected):
|
||||
if msg is None:
|
||||
msg = '%r not greater than or equal to %r' % (got, expected)
|
||||
self.assertTrue(got >= expected, msg)
|
||||
|
||||
|
||||
def assertLessEqual(self, got, expected, msg=None):
|
||||
if not (got <= expected):
|
||||
if msg is None:
|
||||
msg = '%r not less than or equal to %r' % (got, expected)
|
||||
self.assertTrue(got <= expected, msg)
|
||||
|
||||
|
||||
def assertEqual(self, got, expected, msg=None):
|
||||
if not (got == expected):
|
||||
if msg is None:
|
||||
msg = '%r not equal to %r' % (got, expected)
|
||||
self.assertTrue(got == expected, msg)
|
||||
|
||||
|
||||
def expect_warnings(ydl, warnings_re):
|
||||
real_warning = ydl.report_warning
|
||||
|
||||
|
|
|
@ -9,8 +9,6 @@ import unittest
|
|||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import (
|
||||
assertGreaterEqual,
|
||||
assertLessEqual,
|
||||
expect_warnings,
|
||||
get_params,
|
||||
gettestcases,
|
||||
|
@ -36,12 +34,20 @@ from youtube_dl.utils import (
|
|||
ExtractorError,
|
||||
error_to_compat_str,
|
||||
format_bytes,
|
||||
IDENTITY,
|
||||
preferredencoding,
|
||||
UnavailableVideoError,
|
||||
)
|
||||
from youtube_dl.extractor import get_info_extractor
|
||||
|
||||
RETRIES = 3
|
||||
|
||||
# Some unittest APIs require actual str
|
||||
if not isinstance('TEST', str):
|
||||
_encode_str = lambda s: s.encode(preferredencoding())
|
||||
else:
|
||||
_encode_str = IDENTITY
|
||||
|
||||
|
||||
class YoutubeDL(youtube_dl.YoutubeDL):
|
||||
def __init__(self, *args, **kwargs):
|
||||
|
@ -102,7 +108,7 @@ def generator(test_case, tname):
|
|||
|
||||
def print_skipping(reason):
|
||||
print('Skipping %s: %s' % (test_case['name'], reason))
|
||||
self.skipTest(reason)
|
||||
self.skipTest(_encode_str(reason))
|
||||
|
||||
if not ie.working():
|
||||
print_skipping('IE marked as not _WORKING')
|
||||
|
@ -187,16 +193,14 @@ def generator(test_case, tname):
|
|||
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
|
||||
|
||||
if 'playlist_mincount' in test_case:
|
||||
assertGreaterEqual(
|
||||
self,
|
||||
self.assertGreaterEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_mincount'],
|
||||
'Expected at least %d in playlist %s, but got only %d' % (
|
||||
test_case['playlist_mincount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_maxcount' in test_case:
|
||||
assertLessEqual(
|
||||
self,
|
||||
self.assertLessEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_maxcount'],
|
||||
'Expected at most %d in playlist %s, but got %d' % (
|
||||
|
@ -243,8 +247,8 @@ def generator(test_case, tname):
|
|||
if params.get('test'):
|
||||
expected_minsize = max(expected_minsize, 10000)
|
||||
got_fsize = os.path.getsize(tc_filename)
|
||||
assertGreaterEqual(
|
||||
self, got_fsize, expected_minsize,
|
||||
self.assertGreaterEqual(
|
||||
got_fsize, expected_minsize,
|
||||
'Expected %s to be at least %s, but it\'s only %s ' %
|
||||
(tc_filename, format_bytes(expected_minsize),
|
||||
format_bytes(got_fsize)))
|
||||
|
|
|
@ -1039,8 +1039,8 @@ class YoutubeDL(object):
|
|||
elif result_type in ('playlist', 'multi_video'):
|
||||
# Protect from infinite recursion due to recursively nested playlists
|
||||
# (see https://github.com/ytdl-org/youtube-dl/issues/27833)
|
||||
webpage_url = ie_result['webpage_url']
|
||||
if webpage_url in self._playlist_urls:
|
||||
webpage_url = ie_result.get('webpage_url') # not all pl/mv have this
|
||||
if webpage_url and webpage_url in self._playlist_urls:
|
||||
self.to_screen(
|
||||
'[download] Skipping already downloaded playlist: %s'
|
||||
% ie_result.get('title') or ie_result.get('id'))
|
||||
|
@ -1048,6 +1048,10 @@ class YoutubeDL(object):
|
|||
|
||||
self._playlist_level += 1
|
||||
self._playlist_urls.add(webpage_url)
|
||||
new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
|
||||
if new_result:
|
||||
new_result.update(ie_result)
|
||||
ie_result = new_result
|
||||
try:
|
||||
return self.__process_playlist(ie_result, download)
|
||||
finally:
|
||||
|
@ -1593,6 +1597,28 @@ class YoutubeDL(object):
|
|||
self.cookiejar.add_cookie_header(pr)
|
||||
return pr.get_header('Cookie')
|
||||
|
||||
def _fill_common_fields(self, info_dict, final=True):
|
||||
|
||||
for ts_key, date_key in (
|
||||
('timestamp', 'upload_date'),
|
||||
('release_timestamp', 'release_date'),
|
||||
):
|
||||
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
|
||||
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
|
||||
# see http://bugs.python.org/issue1646728)
|
||||
try:
|
||||
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
|
||||
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
|
||||
except (ValueError, OverflowError, OSError):
|
||||
pass
|
||||
|
||||
# Auto generate title fields corresponding to the *_number fields when missing
|
||||
# in order to always have clean titles. This is very common for TV series.
|
||||
if final:
|
||||
for field in ('chapter', 'season', 'episode'):
|
||||
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
|
||||
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
|
||||
|
||||
def process_video_result(self, info_dict, download=True):
|
||||
assert info_dict.get('_type', 'video') == 'video'
|
||||
|
||||
|
@ -1660,24 +1686,7 @@ class YoutubeDL(object):
|
|||
if 'display_id' not in info_dict and 'id' in info_dict:
|
||||
info_dict['display_id'] = info_dict['id']
|
||||
|
||||
for ts_key, date_key in (
|
||||
('timestamp', 'upload_date'),
|
||||
('release_timestamp', 'release_date'),
|
||||
):
|
||||
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
|
||||
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
|
||||
# see http://bugs.python.org/issue1646728)
|
||||
try:
|
||||
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
|
||||
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
|
||||
except (ValueError, OverflowError, OSError):
|
||||
pass
|
||||
|
||||
# Auto generate title fields corresponding to the *_number fields when missing
|
||||
# in order to always have clean titles. This is very common for TV series.
|
||||
for field in ('chapter', 'season', 'episode'):
|
||||
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
|
||||
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
|
||||
self._fill_common_fields(info_dict)
|
||||
|
||||
for cc_kind in ('subtitles', 'automatic_captions'):
|
||||
cc = info_dict.get(cc_kind)
|
||||
|
|
|
@ -898,21 +898,13 @@ from .ooyala import (
|
|||
)
|
||||
from .ora import OraTVIE
|
||||
from .orf import (
|
||||
ORFTVthekIE,
|
||||
ORFFM4IE,
|
||||
ORFONIE,
|
||||
ORFONLiveIE,
|
||||
ORFFM4StoryIE,
|
||||
ORFOE1IE,
|
||||
ORFOE3IE,
|
||||
ORFNOEIE,
|
||||
ORFWIEIE,
|
||||
ORFBGLIE,
|
||||
ORFOOEIE,
|
||||
ORFSTMIE,
|
||||
ORFKTNIE,
|
||||
ORFSBGIE,
|
||||
ORFTIRIE,
|
||||
ORFVBGIE,
|
||||
ORFIPTVIE,
|
||||
ORFPodcastIE,
|
||||
ORFRadioIE,
|
||||
ORFRadioCollectionIE,
|
||||
)
|
||||
from .outsidetv import OutsideTVIE
|
||||
from .packtpub import (
|
||||
|
|
|
@ -1,3 +1,4 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
|
@ -10,7 +11,7 @@ from ..compat import (
|
|||
compat_ord,
|
||||
compat_str,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_zip
|
||||
compat_zip as zip,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
|
@ -24,7 +25,7 @@ class MixcloudBaseIE(InfoExtractor):
|
|||
def _call_api(self, object_type, object_fields, display_id, username, slug=None):
|
||||
lookup_key = object_type + 'Lookup'
|
||||
return self._download_json(
|
||||
'https://www.mixcloud.com/graphql', display_id, query={
|
||||
'https://app.mixcloud.com/graphql', display_id, query={
|
||||
'query': '''{
|
||||
%s(lookup: {username: "%s"%s}) {
|
||||
%s
|
||||
|
@ -44,7 +45,7 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'ext': 'm4a',
|
||||
'title': 'Cryptkeeper',
|
||||
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
|
||||
'uploader': 'Daniel Holbach',
|
||||
'uploader': 'dholbach', # was: 'Daniel Holbach',
|
||||
'uploader_id': 'dholbach',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'view_count': int,
|
||||
|
@ -57,7 +58,7 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
|
||||
'ext': 'mp3',
|
||||
'title': 'Caribou 7 inch Vinyl Mix & Chat',
|
||||
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
|
||||
'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
|
||||
'uploader': 'Gilles Peterson Worldwide',
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
|
@ -65,6 +66,23 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'timestamp': 1422987057,
|
||||
'upload_date': '20150203',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': '404 not found',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
|
||||
'info_dict': {
|
||||
'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
|
||||
'ext': 'm4a',
|
||||
'title': 'Carnival Música Popular Brasileira Mix',
|
||||
'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
|
||||
'timestamp': 1454347174,
|
||||
'upload_date': '20160201',
|
||||
'uploader': 'Gilles Peterson Worldwide',
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
'view_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
|
||||
'only_matching': True,
|
||||
|
@ -76,10 +94,10 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
|
||||
return ''.join([
|
||||
compat_chr(compat_ord(ch) ^ compat_ord(k))
|
||||
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
|
||||
for ch, k in zip(ciphertext, itertools.cycle(key))])
|
||||
|
||||
def _real_extract(self, url):
|
||||
username, slug = re.match(self._VALID_URL, url).groups()
|
||||
username, slug = self._match_valid_url(url).groups()
|
||||
username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
|
||||
track_id = '%s_%s' % (username, slug)
|
||||
|
||||
|
|
File diff suppressed because it is too large
Load Diff
|
@ -5,48 +5,52 @@ import re
|
|||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
parse_duration,
|
||||
unsmuggle_url,
|
||||
url_or_none,
|
||||
)
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..compat import compat_parse_qs
|
||||
|
||||
|
||||
class SenateISVPIE(InfoExtractor):
|
||||
|
||||
# [committee, stream_number, stream_domain, stream_id, msl3]
|
||||
_COMM_MAP = [
|
||||
['ag', '76440', 'http://ag-f.akamaihd.net'],
|
||||
['aging', '76442', 'http://aging-f.akamaihd.net'],
|
||||
['approps', '76441', 'http://approps-f.akamaihd.net'],
|
||||
['armed', '76445', 'http://armed-f.akamaihd.net'],
|
||||
['banking', '76446', 'http://banking-f.akamaihd.net'],
|
||||
['budget', '76447', 'http://budget-f.akamaihd.net'],
|
||||
['cecc', '76486', 'http://srs-f.akamaihd.net'],
|
||||
['commerce', '80177', 'http://commerce1-f.akamaihd.net'],
|
||||
['csce', '75229', 'http://srs-f.akamaihd.net'],
|
||||
['dpc', '76590', 'http://dpc-f.akamaihd.net'],
|
||||
['energy', '76448', 'http://energy-f.akamaihd.net'],
|
||||
['epw', '76478', 'http://epw-f.akamaihd.net'],
|
||||
['ethics', '76449', 'http://ethics-f.akamaihd.net'],
|
||||
['finance', '76450', 'http://finance-f.akamaihd.net'],
|
||||
['foreign', '76451', 'http://foreign-f.akamaihd.net'],
|
||||
['govtaff', '76453', 'http://govtaff-f.akamaihd.net'],
|
||||
['help', '76452', 'http://help-f.akamaihd.net'],
|
||||
['indian', '76455', 'http://indian-f.akamaihd.net'],
|
||||
['intel', '76456', 'http://intel-f.akamaihd.net'],
|
||||
['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net'],
|
||||
['jccic', '85180', 'http://jccic-f.akamaihd.net'],
|
||||
['jec', '76458', 'http://jec-f.akamaihd.net'],
|
||||
['judiciary', '76459', 'http://judiciary-f.akamaihd.net'],
|
||||
['rpc', '76591', 'http://rpc-f.akamaihd.net'],
|
||||
['rules', '76460', 'http://rules-f.akamaihd.net'],
|
||||
['saa', '76489', 'http://srs-f.akamaihd.net'],
|
||||
['smbiz', '76461', 'http://smbiz-f.akamaihd.net'],
|
||||
['srs', '75229', 'http://srs-f.akamaihd.net'],
|
||||
['uscc', '76487', 'http://srs-f.akamaihd.net'],
|
||||
['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
|
||||
['arch', '', 'http://ussenate-f.akamaihd.net/']
|
||||
['ag', '76440', 'http://ag-f.akamaihd.net', '2036803', 'agriculture'],
|
||||
['aging', '76442', 'http://aging-f.akamaihd.net', '2036801', 'aging'],
|
||||
['approps', '76441', 'http://approps-f.akamaihd.net', '2036802', 'appropriations'],
|
||||
['armed', '76445', 'http://armed-f.akamaihd.net', '2036800', 'armedservices'],
|
||||
['banking', '76446', 'http://banking-f.akamaihd.net', '2036799', 'banking'],
|
||||
['budget', '76447', 'http://budget-f.akamaihd.net', '2036798', 'budget'],
|
||||
['cecc', '76486', 'http://srs-f.akamaihd.net', '2036782', 'srs_cecc'],
|
||||
['commerce', '80177', 'http://commerce1-f.akamaihd.net', '2036779', 'commerce'],
|
||||
['csce', '75229', 'http://srs-f.akamaihd.net', '2036777', 'srs_srs'],
|
||||
['dpc', '76590', 'http://dpc-f.akamaihd.net', None, 'dpc'],
|
||||
['energy', '76448', 'http://energy-f.akamaihd.net', '2036797', 'energy'],
|
||||
['epw', '76478', 'http://epw-f.akamaihd.net', '2036783', 'environment'],
|
||||
['ethics', '76449', 'http://ethics-f.akamaihd.net', '2036796', 'ethics'],
|
||||
['finance', '76450', 'http://finance-f.akamaihd.net', '2036795', 'finance_finance'],
|
||||
['foreign', '76451', 'http://foreign-f.akamaihd.net', '2036794', 'foreignrelations'],
|
||||
['govtaff', '76453', 'http://govtaff-f.akamaihd.net', '2036792', 'hsgac'],
|
||||
['help', '76452', 'http://help-f.akamaihd.net', '2036793', 'help'],
|
||||
['indian', '76455', 'http://indian-f.akamaihd.net', '2036791', 'indianaffairs'],
|
||||
['intel', '76456', 'http://intel-f.akamaihd.net', '2036790', 'intelligence'],
|
||||
['intlnarc', '76457', 'http://intlnarc-f.akamaihd.net', None, 'internationalnarcoticscaucus'],
|
||||
['jccic', '85180', 'http://jccic-f.akamaihd.net', '2036778', 'jccic'],
|
||||
['jec', '76458', 'http://jec-f.akamaihd.net', '2036789', 'jointeconomic'],
|
||||
['judiciary', '76459', 'http://judiciary-f.akamaihd.net', '2036788', 'judiciary'],
|
||||
['rpc', '76591', 'http://rpc-f.akamaihd.net', None, 'rpc'],
|
||||
['rules', '76460', 'http://rules-f.akamaihd.net', '2036787', 'rules'],
|
||||
['saa', '76489', 'http://srs-f.akamaihd.net', '2036780', 'srs_saa'],
|
||||
['smbiz', '76461', 'http://smbiz-f.akamaihd.net', '2036786', 'smallbusiness'],
|
||||
['srs', '75229', 'http://srs-f.akamaihd.net', '2031966', 'srs_srs'],
|
||||
['uscc', '76487', 'http://srs-f.akamaihd.net', '2036781', 'srs_uscc'],
|
||||
['vetaff', '76462', 'http://vetaff-f.akamaihd.net', '2036785', 'veteransaffairs'],
|
||||
['arch', '', 'http://ussenate-f.akamaihd.net/', None, None],
|
||||
['uscp', None, '', '2043685', 'uscp'],
|
||||
['cio', None, '', '2043686', 'cio']
|
||||
]
|
||||
|
||||
_IE_NAME = 'senate.gov'
|
||||
_VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
|
||||
_TESTS = [{
|
||||
|
@ -54,100 +58,120 @@ class SenateISVPIE(InfoExtractor):
|
|||
'info_dict': {
|
||||
'id': 'judiciary031715',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player',
|
||||
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
|
||||
'info_dict': {
|
||||
'id': 'commerce011514',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player'
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
'title': 'judiciary031715',
|
||||
'thumbnail': 'http://www.judiciary.senate.gov/themes/judiciary/images/video-poster-flash-fit.png',
|
||||
},
|
||||
'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'],
|
||||
}, {
|
||||
'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
|
||||
# checksum differs each time
|
||||
'info_dict': {
|
||||
'id': 'intel090613',
|
||||
'ext': 'mp4',
|
||||
'title': 'Integrated Senate Video Player'
|
||||
}
|
||||
'title': 'intel090613',
|
||||
},
|
||||
'expected_warnings': ['Failed to download m3u8 information: HTTP Error 404: Not Found'],
|
||||
}, {
|
||||
# From http://www.c-span.org/video/?96791-1
|
||||
'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715',
|
||||
'only_matching': True,
|
||||
'url': 'https://www.senate.gov/isvp/?comm=govtaff&type=archv&stt=975&filename=govtaff111722&auto_play=false&poster=https%3A%2F%2Fwww%2Ehsgac%2Esenate%2Egov%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
|
||||
'info_dict': {
|
||||
'id': 'govtaff111722',
|
||||
'ext': 'mp4',
|
||||
'title': 'govtaff111722',
|
||||
'thumbnail': 'https://www.hsgac.senate.gov/images/video-poster-flash-fit.png',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.senate.gov/isvp/?type=arch&comm=energy&filename=energy111722&stt=00:22:30&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eenergy%2Esenate%2Egov%2Fthemes%2Fenergy%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
|
||||
'info_dict': {
|
||||
'id': 'energy111722',
|
||||
'ext': 'mp4',
|
||||
'title': 'energy111722',
|
||||
'thumbnail': 'https://www.energy.senate.gov/themes/energy/images/video-poster-flash-fit.png',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.senate.gov/isvp/?comm=foreign&type=archv&stt=0&filename=foreign080322&auto_play=false&wmode=transparent&poster=https%3A%2F%2Fwww%2Eforeign%2Esenate%2Egov%2Fthemes%2Fforeign%2Fimages%2Fvideo%2Dposter%2Dflash%2Dfit%2Epng',
|
||||
'info_dict': {
|
||||
'id': 'foreign080322',
|
||||
'ext': 'mp4',
|
||||
'title': 'foreign080322',
|
||||
'thumbnail': 'https://www.foreign.senate.gov/themes/foreign/images/video-poster-flash-fit.png',
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
# returns url from an iframe
|
||||
def _search_iframe_url(webpage):
|
||||
mobj = re.search(
|
||||
r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
|
||||
r'''<iframe\b[^>]+\bsrc\s*=\s*(['"])(?P<url>https?://www\.senate\.gov/isvp/?\?(?:(?!\1)\S)+)''',
|
||||
webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
|
||||
@staticmethod
|
||||
def __dictify(cm):
|
||||
return dict((row[0], (row[1:] + ['', ''])[:4]) for row in cm)
|
||||
|
||||
# returns stream_number, stream_domain, stream_id, msl3
|
||||
def _get_info_for_comm(self, committee):
|
||||
for entry in self._COMM_MAP:
|
||||
if entry[0] == committee:
|
||||
return entry[1:]
|
||||
dict = self.__dictify(self._COMM_MAP)
|
||||
return dict[committee][0:]
|
||||
|
||||
def _real_extract(self, url):
|
||||
# smuggled data may contain a forced title that should be used
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
|
||||
qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
|
||||
if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
|
||||
raise ExtractorError('Invalid URL', expected=True)
|
||||
|
||||
video_id = re.sub(r'.mp4$', '', qs['filename'][0])
|
||||
# error handling for invalid URL - specify which error
|
||||
if not qs.get('filename'):
|
||||
raise ExtractorError('Invalid URL. Missing filename in query parameters', expected=True)
|
||||
if not qs.get('comm'):
|
||||
raise ExtractorError('Invalid URL. Missing committee in query parameters', expected=True)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
committee = qs.get('comm')[0]
|
||||
filename = qs.get('filename')[0]
|
||||
video_id = re.sub(r'\.mp4$', '', filename)
|
||||
|
||||
if smuggled_data.get('force_title'):
|
||||
title = smuggled_data['force_title']
|
||||
else:
|
||||
title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
|
||||
poster = qs.get('poster')
|
||||
thumbnail = poster[0] if poster else None
|
||||
# there is no point in pulling the title from the webpage since it always defaults to 'Integrated Senate Player'
|
||||
title = smuggled_data.get('force_title') or filename
|
||||
|
||||
video_type = qs['type'][0]
|
||||
committee = video_type if video_type == 'arch' else qs['comm'][0]
|
||||
stream_num, domain = self._get_info_for_comm(committee)
|
||||
stream_number, stream_domain, stream_id, msl3 = self._get_info_for_comm(committee)
|
||||
stream_number = int(stream_number)
|
||||
stream_id = int(stream_id)
|
||||
|
||||
# the possible locations for the video: only the first has been seen in use
|
||||
possible_manifest_urls = [
|
||||
'https://www-senate-gov-media-srs.akamaized.net/hls/live/%d/%s/%s/master.m3u8' % (stream_id, committee, filename),
|
||||
'https://www-senate-gov-msl3archive.akamaized.net/%s/%s_1/master.m3u8' % (msl3, filename),
|
||||
'%s/i/%s_1@%d/master.m3u8' % (stream_domain, filename, stream_number),
|
||||
'https://ussenate-f.akamaihd.net/i/%s.mp4/master.m3u8' % video_id,
|
||||
]
|
||||
|
||||
# we iterate through the possible locations until we find formats
|
||||
formats = []
|
||||
if video_type == 'arch':
|
||||
filename = video_id if '.' in video_id else video_id + '.mp4'
|
||||
formats = [{
|
||||
# All parameters in the query string are necessary to prevent a 403 error
|
||||
'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
|
||||
}]
|
||||
else:
|
||||
hdcore_sign = 'hdcore=3.1.0'
|
||||
url_params = (domain, video_id, stream_num)
|
||||
f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
|
||||
m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
|
||||
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
|
||||
# URLs without the extra param induce an 404 error
|
||||
entry.update({'extra_param_to_segment_url': hdcore_sign})
|
||||
formats.append(entry)
|
||||
for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
|
||||
mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
|
||||
for url in possible_manifest_urls:
|
||||
entries = self._extract_m3u8_formats(
|
||||
url, video_id, ext='mp4', m3u8_id='hls',
|
||||
entry_protocol='m3u8_native', fatal=False)
|
||||
|
||||
for entry in entries:
|
||||
mobj = re.search(r'(?P<tag>-[pb]).m3u8', entry['url'])
|
||||
if mobj:
|
||||
entry['format_id'] += mobj.group('tag')
|
||||
formats.append(entry)
|
||||
|
||||
self._sort_formats(formats)
|
||||
if formats:
|
||||
break
|
||||
|
||||
self._sort_formats(formats)
|
||||
thumbnail = url_or_none(qs.get('poster', [None])[-1])
|
||||
start_time = parse_duration(qs.get('stt', [None])[-1])
|
||||
stop_time = parse_duration(qs.get('dur', [None])[-1])
|
||||
if stop_time is not None:
|
||||
stop_time += start_time or 0
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'start_time': start_time,
|
||||
'stop_time': stop_time,
|
||||
}
|
||||
|
|
|
@ -4,6 +4,7 @@ from __future__ import unicode_literals
|
|||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
get_element_by_id,
|
||||
|
@ -11,6 +12,7 @@ from ..utils import (
|
|||
strip_or_none,
|
||||
unified_strdate,
|
||||
urljoin,
|
||||
str_to_int,
|
||||
)
|
||||
|
||||
|
||||
|
@ -35,6 +37,26 @@ class VidLiiIE(InfoExtractor):
|
|||
'categories': ['News & Politics'],
|
||||
'tags': ['Vidlii', 'Jan', 'Videogames'],
|
||||
}
|
||||
}, {
|
||||
# HD
|
||||
'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
|
||||
'md5': '450e7da379c884788c3a4fa02a3ce1a4',
|
||||
'info_dict': {
|
||||
'id': '2Ng8Abj2Fkl',
|
||||
'ext': 'mp4',
|
||||
'title': 'test',
|
||||
'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
|
||||
'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
|
||||
'uploader': 'VidLii',
|
||||
'uploader_url': 'https://www.vidlii.com/user/VidLii',
|
||||
'upload_date': '20200927',
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'average_rating': float,
|
||||
'categories': ['Film & Animation'],
|
||||
'tags': list,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
|
||||
'only_matching': True,
|
||||
|
@ -46,11 +68,32 @@ class VidLiiIE(InfoExtractor):
|
|||
webpage = self._download_webpage(
|
||||
'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
|
||||
|
||||
video_url = self._search_regex(
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
|
||||
'video url', group='url')
|
||||
formats = []
|
||||
|
||||
title = self._search_regex(
|
||||
def add_format(format_url, height=None):
|
||||
height = int(self._search_regex(r'(\d+)\.mp4',
|
||||
format_url, 'height', default=360))
|
||||
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': '%dp' % height if height else None,
|
||||
'height': height,
|
||||
})
|
||||
|
||||
sources = re.findall(
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
|
||||
webpage)
|
||||
|
||||
formats = []
|
||||
if len(sources) > 1:
|
||||
add_format(sources[1][1])
|
||||
self._check_formats(formats, video_id)
|
||||
if len(sources) > 0:
|
||||
add_format(sources[0][1])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._html_search_regex(
|
||||
(r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
|
||||
'title')
|
||||
|
||||
|
@ -82,9 +125,9 @@ class VidLiiIE(InfoExtractor):
|
|||
default=None) or self._search_regex(
|
||||
r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
|
||||
|
||||
view_count = int_or_none(self._search_regex(
|
||||
(r'<strong>(\d+)</strong> views',
|
||||
r'Views\s*:\s*<strong>(\d+)</strong>'),
|
||||
view_count = str_to_int(self._html_search_regex(
|
||||
(r'<strong>([\d,.]+)</strong> views',
|
||||
r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
|
||||
webpage, 'view count', fatal=False))
|
||||
|
||||
comment_count = int_or_none(self._search_regex(
|
||||
|
@ -109,7 +152,7 @@ class VidLiiIE(InfoExtractor):
|
|||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
|
|
Loading…
Reference in New Issue
Block a user