From 008af8660b7d0075882ac7d22c03dca67b5e64f1 Mon Sep 17 00:00:00 2001 From: Pornophage Date: Sat, 25 Jan 2014 01:46:52 +0100 Subject: [PATCH 1/4] Add cliphunter extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/cliphunter.py | 69 ++++++++++++++++++++++++++++++ 2 files changed, 70 insertions(+) create mode 100644 youtube_dl/extractor/cliphunter.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 118982ff8..80fc1f6ae 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -27,6 +27,7 @@ from .channel9 import Channel9IE from .cinemassacre import CinemassacreIE from .clipfish import ClipfishIE +from .cliphunter import CliphunterIE from .clipsyndicate import ClipsyndicateIE from .cmt import CMTIE from .cnn import CNNIE diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py new file mode 100644 index 000000000..9c90e2f98 --- /dev/null +++ b/youtube_dl/extractor/cliphunter.py @@ -0,0 +1,69 @@ +import re +import string + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + ExtractorError, +) + +translation_table = ( + '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12' + '\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#:%.\'=)*+,-./0123' + '456789:;?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]&_`hbcevofhdjknamoutsstupwrli{' + '|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f' + '\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1' + '\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3' + '\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5' + '\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7' + '\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9' + '\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb' + '\xfc\xfd\xfe\xff' +) + + +class CliphunterIE(InfoExtractor): + """Information Extractor for Cliphunter""" + IE_NAME = u'cliphunter' + + _VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/' + '(?P[0-9]+)/' + '(?P.+?)(?:\?.*)?') + _TESTS = [{ + u'url': u'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', + u'file': u'1012420.flv', + u'md5': u'49f72e2fd2977e6e518be9836dcf861e', + u'info_dict': { + u"title": u"Fun Jynx Maze solo", + } + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + raise ExtractorError(u'Unable to extract media URL') + + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id) + + pl_fiji = re.search(r'pl_fiji = \'([^\']+)\'', webpage).group(1) + pl_c_qual = re.search(r'pl_c_qual = "(.)"', webpage).group(1) + video_title = re.search(r'mediaTitle = "([^"]+)"', webpage).group(1) + + video_url = string.translate(pl_fiji.encode(), translation_table) + + formats = [{ + 'url': video_url, + 'ext': determine_ext(video_url), + 'format': pl_c_qual, + 'format_id': pl_c_qual, + }] + + return { + 'id': video_id, + 'title': video_title, + 'formats': formats, + 'description': '', + } From bacb5e4f440a7ac3997282c3603032e575bb518b Mon Sep 17 00:00:00 2001 From: Pornophage Date: Sat, 25 Jan 2014 02:34:08 +0100 Subject: [PATCH 2/4] Minor fixes Remove empty description Set correct md5 test --- youtube_dl/extractor/cliphunter.py | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 9c90e2f98..2d8c09630 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -32,12 +32,11 @@ class CliphunterIE(InfoExtractor): _TESTS = [{ u'url': u'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', u'file': u'1012420.flv', - u'md5': u'49f72e2fd2977e6e518be9836dcf861e', + u'md5': u'15e7740f30428abf70f4223478dc1225', u'info_dict': { - u"title": u"Fun Jynx Maze solo", + u'title': u'Fun Jynx Maze solo', } - }, - ] + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -65,5 +64,4 @@ def _real_extract(self, url): 'id': video_id, 'title': video_title, 'formats': formats, - 'description': '', } From efc867775e09f493cca95fc5cd2986db7b55a71b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 27 Jan 2014 07:55:30 +0100 Subject: [PATCH 3/4] [cliphunter] Simplify --- youtube_dl/extractor/cliphunter.py | 30 +++++++++++++----------------- 1 file changed, 13 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 2d8c09630..42d406820 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -1,9 +1,10 @@ +from __future__ import unicode_literals + import re import string from .common import InfoExtractor from ..utils import ( - determine_ext, ExtractorError, ) @@ -23,39 +24,34 @@ class CliphunterIE(InfoExtractor): - """Information Extractor for Cliphunter""" - IE_NAME = u'cliphunter' + IE_NAME = 'cliphunter' _VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/' '(?P[0-9]+)/' '(?P.+?)(?:\?.*)?') - _TESTS = [{ - u'url': u'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', - u'file': u'1012420.flv', - u'md5': u'15e7740f30428abf70f4223478dc1225', - u'info_dict': { - u'title': u'Fun Jynx Maze solo', + _TESTS = { + 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', + 'file': '1012420.flv', + 'md5': '15e7740f30428abf70f4223478dc1225', + 'info_dict': { + 'title': 'Fun Jynx Maze solo', } - }] + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Unable to extract media URL') - video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - pl_fiji = re.search(r'pl_fiji = \'([^\']+)\'', webpage).group(1) - pl_c_qual = re.search(r'pl_c_qual = "(.)"', webpage).group(1) - video_title = re.search(r'mediaTitle = "([^"]+)"', webpage).group(1) + pl_fiji = self._search_regex(r'pl_fiji = \'([^\']+)\'', webpage, 'video data') + pl_c_qual = self._search_regex(r'pl_c_qual = "(.)"', webpage, 'video quality') + video_title = self._search_regex(r'mediaTitle = "([^"]+)"', webpage, 'title') video_url = string.translate(pl_fiji.encode(), translation_table) formats = [{ 'url': video_url, - 'ext': determine_ext(video_url), 'format': pl_c_qual, 'format_id': pl_c_qual, }] From b6d3a99678052bb85a187268dbd50e35fbde109c Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 27 Jan 2014 12:39:39 +0100 Subject: [PATCH 4/4] [cliphunter] Simplify (#2233) --- youtube_dl/extractor/cliphunter.py | 40 ++++++++++++++---------------- 1 file changed, 18 insertions(+), 22 deletions(-) diff --git a/youtube_dl/extractor/cliphunter.py b/youtube_dl/extractor/cliphunter.py index 42d406820..d891fa301 100644 --- a/youtube_dl/extractor/cliphunter.py +++ b/youtube_dl/extractor/cliphunter.py @@ -8,28 +8,22 @@ ExtractorError, ) -translation_table = ( - '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12' - '\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#:%.\'=)*+,-./0123' - '456789:;?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]&_`hbcevofhdjknamoutsstupwrli{' - '|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f' - '\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1' - '\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3' - '\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5' - '\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7' - '\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9' - '\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb' - '\xfc\xfd\xfe\xff' -) +translation_table = { + 'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n', + 'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r', + 'y': 'l', 'z': 'i', + '$': ':', '&': '.', '(': '=', '^': '&', '=': '/', +} class CliphunterIE(InfoExtractor): IE_NAME = 'cliphunter' - _VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/' - '(?P[0-9]+)/' - '(?P.+?)(?:\?.*)?') - _TESTS = { + _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/ + (?P[0-9]+)/ + (?P.+?)(?:$|[#\?]) + ''' + _TEST = { 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', 'file': '1012420.flv', 'md5': '15e7740f30428abf70f4223478dc1225', @@ -44,15 +38,17 @@ def _real_extract(self, url): webpage = self._download_webpage(url, video_id) - pl_fiji = self._search_regex(r'pl_fiji = \'([^\']+)\'', webpage, 'video data') - pl_c_qual = self._search_regex(r'pl_c_qual = "(.)"', webpage, 'video quality') - video_title = self._search_regex(r'mediaTitle = "([^"]+)"', webpage, 'title') + pl_fiji = self._search_regex( + r'pl_fiji = \'([^\']+)\'', webpage, 'video data') + pl_c_qual = self._search_regex( + r'pl_c_qual = "(.)"', webpage, 'video quality') + video_title = self._search_regex( + r'mediaTitle = "([^"]+)"', webpage, 'title') - video_url = string.translate(pl_fiji.encode(), translation_table) + video_url = ''.join(translation_table.get(c, c) for c in pl_fiji) formats = [{ 'url': video_url, - 'format': pl_c_qual, 'format_id': pl_c_qual, }]