From 366b1f3cfe9993dfdd80116fcf8a91b7a3eff75d Mon Sep 17 00:00:00 2001 From: Naglis Jonaitis Date: Sat, 26 Jul 2014 14:35:23 +0300 Subject: [PATCH 1/2] [izlesene] Add new extractor. Closes #3184 --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/izlesene.py | 94 ++++++++++++++++++++++++++++++++ 2 files changed, 95 insertions(+) create mode 100644 youtube_dl/extractor/izlesene.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index a8e593002..2bf8bc5e8 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -141,6 +141,7 @@ from .ivi import ( IviIE, IviCompilationIE ) +from .izlesene import IzleseneIE from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE from .jukebox import JukeboxIE diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py new file mode 100644 index 000000000..e51358595 --- /dev/null +++ b/youtube_dl/extractor/izlesene.py @@ -0,0 +1,94 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import get_element_by_id, parse_iso8601, determine_ext, int_or_none + + +class IzleseneIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.|m\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P[0-9]+)' + _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}' + _TEST = { + 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', + 'md5': '4384f9f0ea65086734b881085ee05ac2', + 'info_dict': { + 'id': '7599694', + 'title': u'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'upload_date': '20140702', + 'uploader_id': 'pelikzzle', + 'description': u'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', + 'timestamp': 1404298698, + 'duration': 95, + 'ext': 'mp4', + 'thumbnail': 're:^http://.*\.jpg', + 'age_limit': 0, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + url = 'http://www.izlesene.com/video/%s' % video_id + + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + duration = int( + self._html_search_regex( + r'"videoduration"\s?:\s?"([^"]+)"', webpage, 'duration', + fatal=False, default='0') + ) / 1000 + view_count = get_element_by_id('videoViewCount', + webpage).replace('.', '') + timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, + 'upload date', fatal=False)) + family_friendly = self._html_search_meta('isFamilyFriendly', webpage, + 'age limit', fatal=False) + uploader = self._html_search_regex(r"adduserUsername\s?=\s?'([^']+)';", + webpage, 'uploader', fatal=False, + default='') + comment_count = self._html_search_regex( + r'comment_count\s?=\s?\'([^\']+)\';', + webpage, 'uploader', fatal=False) + + content_url = self._html_search_meta('contentURL', webpage, + 'content URL', fatal=False) + ext = determine_ext(content_url) + + # Might be empty for some videos. + qualities = self._html_search_regex(r'"quality"\s?:\s?"([^"]+)"', + webpage, 'qualities', fatal=False, + default='') + + formats = [] + for quality in qualities.split('|'): + json = self._download_json( + self._STREAM_URL.format(id=video_id, format=quality), video_id, + note=u'Getting video URL for "%s" quality' % quality, + errnote=u'Failed to get video URL for "%s" quality' % quality + ) + video_format = '%sp' % quality if quality else 'sd' + formats.append({ + 'url': json.get('streamurl'), + 'ext': ext, + 'format': video_format, + 'format_id': video_format, + }) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'view_count': int_or_none(view_count), + 'timestamp': timestamp, + 'age_limit': 18 if family_friendly == 'False' else 0, + 'uploader_id': uploader, + 'comment_count': int_or_none(comment_count), + } From f4776371ae6e5472ec6dc96084461df621e99d37 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 1 Aug 2014 19:08:09 +0700 Subject: [PATCH 2/2] [izlesene] Minor changes --- youtube_dl/extractor/izlesene.py | 81 +++++++++++++++++--------------- youtube_dl/utils.py | 2 + 2 files changed, 44 insertions(+), 39 deletions(-) diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index e51358595..79e8430b5 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -4,25 +4,31 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import get_element_by_id, parse_iso8601, determine_ext, int_or_none +from ..utils import ( + get_element_by_id, + parse_iso8601, + determine_ext, + int_or_none, + str_to_int, +) class IzleseneIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|m\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P[0-9]+)' + _VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P[0-9]+)' _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}' _TEST = { 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', 'md5': '4384f9f0ea65086734b881085ee05ac2', 'info_dict': { 'id': '7599694', - 'title': u'Sevinçten Çıldırtan Doğum Günü Hediyesi', - 'upload_date': '20140702', - 'uploader_id': 'pelikzzle', - 'description': u'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', - 'timestamp': 1404298698, - 'duration': 95, 'ext': 'mp4', + 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', 'thumbnail': 're:^http://.*\.jpg', + 'uploader_id': 'pelikzzle', + 'timestamp': 1404298698, + 'upload_date': '20140702', + 'duration': 95.395, 'age_limit': 0, } } @@ -37,58 +43,55 @@ class IzleseneIE(InfoExtractor): title = self._og_search_title(webpage) description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage) - duration = int( - self._html_search_regex( - r'"videoduration"\s?:\s?"([^"]+)"', webpage, 'duration', - fatal=False, default='0') - ) / 1000 - view_count = get_element_by_id('videoViewCount', - webpage).replace('.', '') - timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, - 'upload date', fatal=False)) - family_friendly = self._html_search_meta('isFamilyFriendly', webpage, - 'age limit', fatal=False) - uploader = self._html_search_regex(r"adduserUsername\s?=\s?'([^']+)';", - webpage, 'uploader', fatal=False, - default='') + + uploader = self._html_search_regex( + r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='') + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date', fatal=False)) + + duration = int_or_none(self._html_search_regex( + r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False)) + if duration: + duration /= 1000.0 + + view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) comment_count = self._html_search_regex( - r'comment_count\s?=\s?\'([^\']+)\';', - webpage, 'uploader', fatal=False) + r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False) - content_url = self._html_search_meta('contentURL', webpage, - 'content URL', fatal=False) - ext = determine_ext(content_url) + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, 'age limit', fatal=False) + + content_url = self._html_search_meta( + 'contentURL', webpage, 'content URL', fatal=False) + ext = determine_ext(content_url, 'mp4') # Might be empty for some videos. - qualities = self._html_search_regex(r'"quality"\s?:\s?"([^"]+)"', - webpage, 'qualities', fatal=False, - default='') + qualities = self._html_search_regex( + r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='') formats = [] for quality in qualities.split('|'): json = self._download_json( self._STREAM_URL.format(id=video_id, format=quality), video_id, - note=u'Getting video URL for "%s" quality' % quality, - errnote=u'Failed to get video URL for "%s" quality' % quality + note='Getting video URL for "%s" quality' % quality, + errnote='Failed to get video URL for "%s" quality' % quality ) - video_format = '%sp' % quality if quality else 'sd' formats.append({ 'url': json.get('streamurl'), 'ext': ext, - 'format': video_format, - 'format_id': video_format, + 'format_id': '%sp' % quality if quality else 'sd', }) return { 'id': video_id, 'title': title, - 'formats': formats, 'description': description, 'thumbnail': thumbnail, + 'uploader_id': uploader, + 'timestamp': timestamp, 'duration': duration, 'view_count': int_or_none(view_count), - 'timestamp': timestamp, - 'age_limit': 18 if family_friendly == 'False' else 0, - 'uploader_id': uploader, 'comment_count': int_or_none(comment_count), + 'age_limit': 18 if family_friendly == 'False' else 0, + 'formats': formats, } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 0d0bbe8f6..e40b367c2 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -852,6 +852,8 @@ def unified_strdate(date_str): return upload_date def determine_ext(url, default_ext=u'unknown_video'): + if url is None: + return default_ext guess = url.partition(u'?')[0].rpartition(u'.')[2] if re.match(r'^[A-Za-z0-9]+$', guess): return guess