summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorSergey M․ <[email protected]>2018-03-04 17:46:36 +0700
committerSergey M․ <[email protected]>2018-03-04 17:46:36 +0700
commit62f49dd3b9d7f44537f70a31a0e37aa3dd9e91a9 (patch)
treef10256eccdbe5ec4e6affaa9be39370530751a9d
parentf9f10268c1816dcf1fc0db9d8128008f73a154c7 (diff)
downloadyoutube-dl-62f49dd3b9d7f44537f70a31a0e37aa3dd9e91a9.tar.gz
youtube-dl-62f49dd3b9d7f44537f70a31a0e37aa3dd9e91a9.zip
[hidive] Add extractor (closes #15494)
-rw-r--r--youtube_dl/extractor/extractors.py1
-rw-r--r--youtube_dl/extractor/hidive.py97
2 files changed, 98 insertions, 0 deletions
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index a0779e164..74ec899f4 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -429,6 +429,7 @@ from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
from .hgtv import HGTVComShowIE
+from .hidive import HiDiveIE
from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hitrecord import HitRecordIE
diff --git a/youtube_dl/extractor/hidive.py b/youtube_dl/extractor/hidive.py
new file mode 100644
index 000000000..1c70b6646
--- /dev/null
+++ b/youtube_dl/extractor/hidive.py
@@ -0,0 +1,97 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+ urlencode_postdata,
+)
+
+
+class HiDiveIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?hidive\.com/stream/(?P<title>[^/]+)/(?P<key>[^/?#&]+)'
+ # Using X-Forwarded-For results in 403 HTTP error for HLS fragments,
+ # so disabling geo bypass completely
+ _GEO_BYPASS = False
+
+ _TESTS = [{
+ 'url': 'https://www.hidive.com/stream/the-comic-artist-and-his-assistants/s01e001',
+ 'info_dict': {
+ 'id': 'the-comic-artist-and-his-assistants/s01e001',
+ 'ext': 'mp4',
+ 'title': 'the-comic-artist-and-his-assistants/s01e001',
+ 'series': 'the-comic-artist-and-his-assistants',
+ 'season_number': 1,
+ 'episode_number': 1,
+ },
+ 'params': {
+ 'skip_download': True,
+ 'proxy': '192.99.245.228:3128',
+ },
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ title, key = mobj.group('title', 'key')
+ video_id = '%s/%s' % (title, key)
+
+ settings = self._download_json(
+ 'https://www.hidive.com/play/settings', video_id,
+ data=urlencode_postdata({
+ 'Title': title,
+ 'Key': key,
+ }))
+
+ restriction = settings.get('restrictionReason')
+ if restriction == 'RegionRestricted':
+ self.raise_geo_restricted()
+
+ if restriction and restriction != 'None':
+ raise ExtractorError(
+ '%s said: %s' % (self.IE_NAME, restriction), expected=True)
+
+ formats = []
+ subtitles = {}
+ for rendition_id, rendition in settings['renditions'].items():
+ bitrates = rendition.get('bitrates')
+ if not isinstance(bitrates, dict):
+ continue
+ m3u8_url = bitrates.get('hls')
+ if not isinstance(m3u8_url, compat_str):
+ continue
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='%s-hls' % rendition_id, fatal=False))
+ cc_files = rendition.get('ccFiles')
+ if not isinstance(cc_files, list):
+ continue
+ for cc_file in cc_files:
+ if not isinstance(cc_file, list) or len(cc_file) < 3:
+ continue
+ cc_lang = cc_file[0]
+ cc_url = cc_file[2]
+ if not isinstance(cc_lang, compat_str) or not isinstance(
+ cc_url, compat_str):
+ continue
+ subtitles.setdefault(cc_lang, []).append({
+ 'url': cc_url,
+ })
+
+ season_number = int_or_none(self._search_regex(
+ r's(\d+)', key, 'season number', default=None))
+ episode_number = int_or_none(self._search_regex(
+ r'e(\d+)', key, 'episode number', default=None))
+
+ return {
+ 'id': video_id,
+ 'title': video_id,
+ 'subtitles': subtitles,
+ 'formats': formats,
+ 'series': title,
+ 'season_number': season_number,
+ 'episode_number': episode_number,
+ }