From 0d933b2ad57563b70d725ce03fe0e79c4d84c99e Mon Sep 17 00:00:00 2001 From: Ariset Llerena Date: Thu, 12 Jun 2014 03:27:23 -0400 Subject: [PATCH 1/3] Added vimple.ru support --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/vimple.py | 73 ++++++++++++++++++++++++++++++++ 2 files changed, 74 insertions(+) create mode 100644 youtube_dl/extractor/vimple.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 45cc479e2..4b7900b4f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -324,6 +324,7 @@ VimeoReviewIE, VimeoWatchLaterIE, ) +from .vimple import VimpleIE from .vine import ( VineIE, VineUserIE, diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py new file mode 100644 index 000000000..0f69e7126 --- /dev/null +++ b/youtube_dl/extractor/vimple.py @@ -0,0 +1,73 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re, zlib, base64 +import xml.etree.ElementTree + +from .common import InfoExtractor + +class VimpleIE(InfoExtractor): + IE_DESC = 'Vimple.ru' + _VALID_URL = r'https?://player.vimple.ru/iframe/(?P[a-f0-9]+)' + _TESTS = [ + { + # Quality: Large, from iframe + 'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c', + 'info_dict': { + 'id': 'b132bdfd71b546d3972f9ab9a25f201c', + 'title': 'great-escape-minecraft.flv', + 'ext':'mp4', + 'duration': 352, + 'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c', + }, + } + ] + + #http://jsunpack-n.googlecode.com/svn-history/r63/trunk/swf.py + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id + + iframe = self._download_webpage(iframe_url, video_id, note='Downloading iframe', errnote='unable to fetch iframe') + player_url = self._html_search_regex(r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url') + + player = self._request_webpage(player_url, video_id, note='Downloading swf player').read() + + #http://stackoverflow.com/a/6804758 + #http://stackoverflow.com/a/12073686 + player = zlib.decompress(player[8:]) + + + xml_pieces = re.findall(b'([a-zA-Z0-9 =\\+/]{500})', player) + xml_pieces = [piece[1:-1] for piece in xml_pieces] + + xml_data = b''.join(xml_pieces) + xml_data = base64.b64decode(xml_data) + + xml_data = xml.etree.ElementTree.fromstring(xml_data) + + video = xml_data.find('Video') + quality = video.get('quality') + q_tag = video.find(quality.capitalize()) + + formats = [ + { + 'url': q_tag.get('url'), + 'tbr': int(q_tag.get('bitrate')), + 'filesize': int(q_tag.get('filesize')), + 'format_id': quality, + }, + ] + + return { + 'id': video_id, + 'title': video.find('Title').text, + 'formats': formats, + 'thumbnail': video.find('Poster').get('url'), + 'duration': int(video.get('duration')), + 'webpage_url': video.find('Share').get('videoPageUrl'), + } + + From cb437dc2ad41122f1a08595a0829b4d929ddd580 Mon Sep 17 00:00:00 2001 From: Ariset Llerena Date: Thu, 12 Jun 2014 22:33:50 -0400 Subject: [PATCH 2/3] removed extra char in regexp --- youtube_dl/extractor/vimple.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py index 0f69e7126..a2f93afe3 100644 --- a/youtube_dl/extractor/vimple.py +++ b/youtube_dl/extractor/vimple.py @@ -40,7 +40,7 @@ def _real_extract(self, url): player = zlib.decompress(player[8:]) - xml_pieces = re.findall(b'([a-zA-Z0-9 =\\+/]{500})', player) + xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player) xml_pieces = [piece[1:-1] for piece in xml_pieces] xml_data = b''.join(xml_pieces) From e66ab17a3683bee57482ccce8f6b0a632f03d78e Mon Sep 17 00:00:00 2001 From: Ariset Llerena Date: Thu, 12 Jun 2014 23:08:06 -0400 Subject: [PATCH 3/3] Verified with pep8 and pyflakes --- youtube_dl/extractor/vimple.py | 49 +++++++++++++++++++++------------- 1 file changed, 30 insertions(+), 19 deletions(-) diff --git a/youtube_dl/extractor/vimple.py b/youtube_dl/extractor/vimple.py index a2f93afe3..f3a807cd3 100644 --- a/youtube_dl/extractor/vimple.py +++ b/youtube_dl/extractor/vimple.py @@ -1,53 +1,66 @@ # coding: utf-8 from __future__ import unicode_literals -import re, zlib, base64 -import xml.etree.ElementTree +import re +import zlib +import base64 +import xml.etree.ElementTree from .common import InfoExtractor + class VimpleIE(InfoExtractor): IE_DESC = 'Vimple.ru' - _VALID_URL = r'https?://player.vimple.ru/iframe/(?P[a-f0-9]+)' + _VALID_URL = r'https?://(player.vimple.ru/iframe|vimple.ru)/(?P[a-f0-9]{10,})' _TESTS = [ + # Quality: Large, from iframe { - # Quality: Large, from iframe 'url': 'http://player.vimple.ru/iframe/b132bdfd71b546d3972f9ab9a25f201c', 'info_dict': { 'id': 'b132bdfd71b546d3972f9ab9a25f201c', 'title': 'great-escape-minecraft.flv', - 'ext':'mp4', + 'ext': 'mp4', 'duration': 352, 'webpage_url': 'http://vimple.ru/b132bdfd71b546d3972f9ab9a25f201c', - }, - } + }, + }, + # Quality: Medium, from mainpage + { + 'url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', + 'info_dict': { + 'id': 'a15950562888453b8e6f9572dc8600cd', + 'title': 'DB 01', + 'ext': 'flv', + 'duration': 1484, + 'webpage_url': 'http://vimple.ru/a15950562888453b8e6f9572dc8600cd', + } + }, ] - - #http://jsunpack-n.googlecode.com/svn-history/r63/trunk/swf.py + + # http://jsunpack-n.googlecode.com/svn-history/r63/trunk/swf.py def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - + iframe_url = 'http://player.vimple.ru/iframe/%s' % video_id iframe = self._download_webpage(iframe_url, video_id, note='Downloading iframe', errnote='unable to fetch iframe') player_url = self._html_search_regex(r'"(http://player.vimple.ru/flash/.+?)"', iframe, 'player url') - + player = self._request_webpage(player_url, video_id, note='Downloading swf player').read() - #http://stackoverflow.com/a/6804758 - #http://stackoverflow.com/a/12073686 + # http://stackoverflow.com/a/6804758 + # http://stackoverflow.com/a/12073686 player = zlib.decompress(player[8:]) - xml_pieces = re.findall(b'([a-zA-Z0-9 =+/]{500})', player) xml_pieces = [piece[1:-1] for piece in xml_pieces] - + xml_data = b''.join(xml_pieces) xml_data = base64.b64decode(xml_data) - + xml_data = xml.etree.ElementTree.fromstring(xml_data) - + video = xml_data.find('Video') quality = video.get('quality') q_tag = video.find(quality.capitalize()) @@ -69,5 +82,3 @@ def _real_extract(self, url): 'duration': int(video.get('duration')), 'webpage_url': video.find('Share').get('videoPageUrl'), } - -