1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-04 13:45:17 +01:00
yt-dlp/youtube_dl/extractor/abc.py

153 lines
6.0 KiB
Python
Raw Normal View History

2014-07-26 00:05:37 +02:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
js_to_json,
2015-08-29 19:11:56 +02:00
int_or_none,
parse_iso8601,
)
2014-07-26 00:05:37 +02:00
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
2016-09-08 13:29:05 +02:00
_VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
2014-07-26 00:05:37 +02:00
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'cb3dd03b18455a661071ee1e28344d9f',
2014-07-26 00:05:37 +02:00
'info_dict': {
'id': '5868334',
2014-07-26 00:05:37 +02:00
'ext': 'mp4',
'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
2014-07-26 00:05:37 +02:00
},
'skip': 'this video has expired',
}, {
'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
'md5': 'db2a5369238b51f9811ad815b69dc086',
'info_dict': {
'id': 'NvqvPeNZsHU',
'ext': 'mp4',
'upload_date': '20150816',
'uploader': 'ABC News (Australia)',
'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef',
'uploader_id': 'NewsOnABC',
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
'skip': 'Not accessible from Travis CI server',
2015-10-23 08:09:41 +02:00
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
2015-10-24 12:31:42 +02:00
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}]
2014-07-26 00:05:37 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2014-07-26 00:05:37 +02:00
webpage = self._download_webpage(url, video_id)
mobj = re.search(
2015-10-23 08:09:41 +02:00
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
if expired:
raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
mobj.group('json_data'), video_id, transform_source=js_to_json)
if not isinstance(urls_info, list):
urls_info = [urls_info]
if mobj.group('type') == 'YouTube':
return self.playlist_result([
self.url_result(url_info['url']) for url_info in urls_info])
2014-07-26 00:05:37 +02:00
formats = [{
'url': url_info['url'],
2015-10-23 08:09:41 +02:00
'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
2015-08-29 19:11:56 +02:00
'width': int_or_none(url_info.get('width')),
'height': int_or_none(url_info.get('height')),
'tbr': int_or_none(url_info.get('bitrate')),
'filesize': int_or_none(url_info.get('filesize')),
2014-07-26 00:05:37 +02:00
} for url_info in urls_info]
2015-10-23 08:09:41 +02:00
2014-07-26 00:05:37 +02:00
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
'md5': '979d10b2939101f0d27a06b79edad536',
'info_dict': {
'id': 'FA1505V024S00',
'ext': 'mp4',
'title': 'Series 27 Ep 24',
'description': 'md5:b28baeae7504d1148e1d2f0e3ed3c15d',
'upload_date': '20160820',
'uploader_id': 'abc1',
'timestamp': 1471719600,
},
'skip': 'Video gone',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_params = self._parse_json(self._search_regex(
r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
title = video_params['title']
stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
self._sort_formats(formats)
subtitles = {}
src_vtt = stream.get('captions', {}).get('src-vtt')
if src_vtt:
subtitles['en'] = [{
'url': src_vtt,
'ext': 'vtt',
}]
return {
'id': video_id,
'title': title,
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': video_params.get('seriesTitle'),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage)),
'episode': self._html_search_meta('episode_title', webpage),
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
}