1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 18:02:53 +08:00

[apa] Add extractor (closes #15041, closes #15672)

This commit is contained in:
Sergey M․ 2018-05-27 18:24:37 +07:00
parent 9c65c4a6cd
commit cfd7f2a636
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
3 changed files with 118 additions and 0 deletions

View File

@ -0,0 +1,94 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
js_to_json,
)
class APAIE(InfoExtractor):
_VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': 'jjv85FdZ',
'ext': 'mp4',
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 254,
'timestamp': 1519211149,
'upload_date': '20180221',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
'only_matching': True,
}, {
'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
'only_matching': True,
}, {
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1',
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
'jwplatform id', default=None)
if jwplatform_id:
return self.url_result(
'jwplatform:' + jwplatform_id, ie='JWPlatform',
video_id=video_id)
sources = self._parse_json(
self._search_regex(
r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'),
video_id, transform_source=js_to_json)
formats = []
for source in sources:
if not isinstance(source, dict):
continue
source_url = source.get('file')
if not source_url or not isinstance(source_url, compat_str):
continue
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': source_url,
})
self._sort_formats(formats)
thumbnail = self._search_regex(
r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', fatal=False, group='url')
return {
'id': video_id,
'title': video_id,
'thumbnail': thumbnail,
'formats': formats,
}

View File

@ -44,6 +44,7 @@ from .anysex import AnySexIE
from .aol import AolIE
from .allocine import AllocineIE
from .aliexpress import AliExpressLiveIE
from .apa import APAIE
from .aparat import AparatIE
from .appleconnect import AppleConnectIE
from .appletrailers import (

View File

@ -110,6 +110,7 @@ from .xfileshare import XFileShareIE
from .cloudflarestream import CloudflareStreamIE
from .peertube import PeerTubeIE
from .indavideo import IndavideoEmbedIE
from .apa import APAIE
class GenericIE(InfoExtractor):
@ -2041,6 +2042,23 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
{
# APA embed via JWPlatform embed
'url': 'http://www.vol.at/blue-man-group/5593454',
'info_dict': {
'id': 'jjv85FdZ',
'ext': 'mp4',
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 254,
'timestamp': 1519211149,
'upload_date': '20180221',
},
'params': {
'skip_download': True,
},
},
{
'url': 'http://share-videos.se/auto/video/83645793?uid=13',
'md5': 'b68d276de422ab07ee1d49388103f457',
@ -3068,6 +3086,11 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
apa_urls = APAIE._extract_urls(webpage)
if apa_urls:
return self.playlist_from_matches(
apa_urls, video_id, video_title, ie=APAIE.ie_key())
sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
webpage)]