github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[izlesene] Adapt to website changes and improve

Browse source
This commit is contained in:
Naglis Jonaitis 2014-09-10 00:22:48 +03:00
parent c63b30901b
commit f1d15e6dbc
1 changed files with 60 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

90
youtube_dl/extractor/izlesene.py
View file

@ -14,24 +14,45 @@ from ..utils import (
class IzleseneIE(InfoExtractor): class IzleseneIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)' _VALID_URL = r'''(?x)
https?://(?:(?:www|m)\.)?izlesene\.com/
(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
'''
_STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}' _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
_TEST = { _TESTS = [
'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', {
'md5': '4384f9f0ea65086734b881085ee05ac2', 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
'info_dict': { 'md5': '4384f9f0ea65086734b881085ee05ac2',
'id': '7599694', 'info_dict': {
'ext': 'mp4', 'id': '7599694',
'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', 'ext': 'mp4',
'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
'thumbnail': 're:^http://.*\.jpg', 'description': 'md5:253753e2655dde93f59f74b572454f6d',
'uploader_id': 'pelikzzle', 'thumbnail': 're:^http://.*\.jpg',
'timestamp': 1404298698, 'uploader_id': 'pelikzzle',
'upload_date': '20140702', 'timestamp': 1404298698,
'duration': 95.395, 'upload_date': '20140702',
'age_limit': 0, 'duration': 95.395,
} 'age_limit': 0,
} }
},
{
'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
'md5': '97f09b6872bffa284cb7fa4f6910cb72',
'info_dict': {
'id': '17997',
'ext': 'mp4',
'title': 'Tarkan Dortmund 2006 Konseri',
'description': 'Tarkan Dortmund 2006 Konseri',
'thumbnail': 're:^http://.*\.jpg',
'uploader_id': 'parlayankiz',
'timestamp': 1163318593,
'upload_date': '20061112',
'duration': 253.666,
'age_limit': 0,
}
},
]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -45,18 +66,21 @@ class IzleseneIE(InfoExtractor):
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
uploader = self._html_search_regex( uploader = self._html_search_regex(
r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='') r"adduserUsername\s*=\s*'([^']+)';",
webpage, 'uploader', fatal=False, default='')
timestamp = parse_iso8601(self._html_search_meta( timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date', fatal=False)) 'uploadDate', webpage, 'upload date', fatal=False))
duration = int_or_none(self._html_search_regex( duration = int_or_none(self._html_search_regex(
r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False)) r'"videoduration"\s*:\s*"([^"]+)"',
webpage, 'duration', fatal=False))
if duration: if duration:
duration /= 1000.0 duration /= 1000.0
view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
comment_count = self._html_search_regex( comment_count = self._html_search_regex(
r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False) r'comment_count\s*=\s*\'([^\']+)\';',
webpage, 'comment_count', fatal=False)
family_friendly = self._html_search_meta( family_friendly = self._html_search_meta(
'isFamilyFriendly', webpage, 'age limit', fatal=False) 'isFamilyFriendly', webpage, 'age limit', fatal=False)
@ -66,20 +90,26 @@ class IzleseneIE(InfoExtractor):
ext = determine_ext(content_url, 'mp4') ext = determine_ext(content_url, 'mp4')
# Might be empty for some videos. # Might be empty for some videos.
qualities = self._html_search_regex( streams = self._html_search_regex(
r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='') r'"qualitylevel"\s*:\s*"([^"]+)"',
webpage, 'streams', fatal=False, default='')
formats = [] formats = []
for quality in qualities.split('|'): if streams:
json = self._download_json( for stream in streams.split('|'):
self._STREAM_URL.format(id=video_id, format=quality), video_id, quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
note='Getting video URL for "%s" quality' % quality, formats.append({
errnote='Failed to get video URL for "%s" quality' % quality 'format_id': '%sp' % quality if quality else 'sd',
) 'url': url,
'ext': ext,
})
else:
stream_url = self._search_regex(
r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
formats.append({ formats.append({
'url': json.get('streamurl'), 'format_id': 'sd',
'url': stream_url,
'ext': ext, 'ext': ext,
'format_id': '%sp' % quality if quality else 'sd',
}) })
return { return {