# coding: utf-8\r
from __future__ import unicode_literals\r
\r
-from .common import InfoExtractor\r
import re\r
\r
+from .common import InfoExtractor\r
+from ..compat import compat_str\r
+from ..utils import (\r
+ int_or_none,\r
+ js_to_json,\r
+ try_get,\r
+)\r
+\r
\r
class JojIE(InfoExtractor):\r
- _VALID_URL = r'https?://[a-z0-9]+\.joj\.sk/([^/]+/)*(?P<title_query>(?P<release_date>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa\r
+ _VALID_URL = r'''(?x)\r
+ (?:\r
+ joj:|\r
+ https?://media\.joj\.sk/embed/\r
+ )\r
+ (?P<id>[^/?#^]+)\r
+ '''\r
_TESTS = [{\r
- 'url': 'https://www.joj.sk/nove-byvanie/archiv/2017-05-28-nove-byvanie', # noqa\r
+ 'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932',\r
'info_dict': {\r
'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',\r
'ext': 'mp4',\r
- 'title': 'Nové Bývanie',\r
- 'release_date': '20170528'\r
+ 'title': 'NOVÉ BÝVANIE',\r
+ 'thumbnail': r're:^https?://.*\.jpg$',\r
+ 'duration': 3118,\r
}\r
}, {\r
- 'url': 'http://nasi.joj.sk/epizody/2016-09-06-stari-rodicia',\r
- 'info_dict': {\r
- 'id': 'f18b2c5f-9ea8-4941-a164-a814c53306ad',\r
- 'ext': 'mp4',\r
- 'title': 'Starí Rodičia',\r
- 'release_date': '20160906'\r
- }\r
+ 'url': 'https://media.joj.sk/embed/9i1cxv',\r
+ 'only_matching': True,\r
+ }, {\r
+ 'url': 'joj:a388ec4c-6019-4a4a-9312-b1bee194e932',\r
+ 'only_matching': True,\r
+ }, {\r
+ 'url': 'joj:9i1cxv',\r
+ 'only_matching': True,\r
}]\r
\r
- media_src_url = 'http://n16.joj.sk/storage/'\r
- xml_source_url = 'https://media.joj.sk/services/Video.php?clip='\r
+ @staticmethod\r
+ def _extract_urls(webpage):\r
+ return [\r
+ mobj.group('url')\r
+ for mobj in re.finditer(\r
+ r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//media\.joj\.sk/embed/(?:(?!\1).)+)\1',\r
+ webpage)]\r
\r
def _real_extract(self, url):\r
- mobj = re.match(self._VALID_URL, url)\r
- release_date = mobj.group('release_date').replace('-', '')\r
- webpage = self._download_webpage(url, 'id')\r
- video_id = self._html_search_regex(\r
- r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P<video_id>[a-f0-9\-]+)',\r
- webpage, 'id', group='video_id')\r
- xml_playlist_url = self.xml_source_url + video_id\r
- xml_playlist_et = self._download_xml(xml_playlist_url, 'XML playlist')\r
+ video_id = self._match_id(url)\r
+\r
+ webpage = self._download_webpage(\r
+ 'https://media.joj.sk/embed/%s' % video_id, video_id)\r
+\r
+ title = self._search_regex(\r
+ (r'videoTitle\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',\r
+ r'<title>(?P<title>[^<]+)'), webpage, 'title',\r
+ default=None, group='title') or self._og_search_title(webpage)\r
+\r
+ bitrates = self._parse_json(\r
+ self._search_regex(\r
+ r'(?s)(?:src|bitrates)\s*=\s*({.+?});', webpage, 'bitrates',\r
+ default='{}'),\r
+ video_id, transform_source=js_to_json, fatal=False)\r
+\r
formats = []\r
- for file_el in xml_playlist_et.findall('files/file'):\r
- try:\r
- height = int(file_el.attrib['id'].replace('p', ''))\r
- except ValueError:\r
- height = 0\r
- formats.append({'height': height,\r
- 'url': self.media_src_url + file_el.attrib['path'].replace( # noqa\r
- 'dat/', '', 1)})\r
+ for format_url in try_get(bitrates, lambda x: x['mp4'], list) or []:\r
+ if isinstance(format_url, compat_str):\r
+ height = self._search_regex(\r
+ r'(\d+)[pP]\.', format_url, 'height', default=None)\r
+ formats.append({\r
+ 'url': format_url,\r
+ 'format_id': '%sp' % height if height else None,\r
+ 'height': int(height),\r
+ })\r
+ if not formats:\r
+ playlist = self._download_xml(\r
+ 'https://media.joj.sk/services/Video.php?clip=%s' % video_id,\r
+ video_id)\r
+ for file_el in playlist.findall('./files/file'):\r
+ path = file_el.get('path')\r
+ if not path:\r
+ continue\r
+ format_id = file_el.get('id') or file_el.get('label')\r
+ formats.append({\r
+ 'url': 'http://n16.joj.sk/storage/%s' % path.replace(\r
+ 'dat/', '', 1),\r
+ 'format_id': format_id,\r
+ 'height': int_or_none(self._search_regex(\r
+ r'(\d+)[pP]', format_id or path, 'height',\r
+ default=None)),\r
+ })\r
self._sort_formats(formats)\r
\r
+ thumbnail = self._og_search_thumbnail(webpage)\r
+\r
+ duration = int_or_none(self._search_regex(\r
+ r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))\r
+\r
return {\r
'id': video_id,\r
- 'title': self._og_search_title(webpage).title(),\r
+ 'title': title,\r
+ 'thumbnail': thumbnail,\r
+ 'duration': duration,\r
'formats': formats,\r
- 'release_date': release_date\r
}\r
projects / youtube-dl / blobdiff