From 933a5b379231414555560fb7ffe7a015eba66b9f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Fri, 21 Mar 2014 19:13:46 +0100 Subject: [PATCH] Add extractor for Engadget and 5min (closes #2465) engadget.com uses the generic 5min.com service. --- youtube_dl/extractor/__init__.py | 2 ++ youtube_dl/extractor/engadget.py | 43 ++++++++++++++++++++++++ youtube_dl/extractor/fivemin.py | 56 ++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+) create mode 100644 youtube_dl/extractor/engadget.py create mode 100644 youtube_dl/extractor/fivemin.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 9cf73272f..5138eb94b 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -64,6 +64,7 @@ from .ehow import EHowIE from .eighttracks import EightTracksIE from .eitb import EitbIE from .elpais import ElPaisIE +from .engadget import EngadgetIE from .escapist import EscapistIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE @@ -72,6 +73,7 @@ from .facebook import FacebookIE from .faz import FazIE from .firstpost import FirstpostIE from .firsttv import FirstTVIE +from .fivemin import FiveMinIE from .fktv import ( FKTVIE, FKTVPosteckeIE, diff --git a/youtube_dl/extractor/engadget.py b/youtube_dl/extractor/engadget.py new file mode 100644 index 000000000..92ada81d2 --- /dev/null +++ b/youtube_dl/extractor/engadget.py @@ -0,0 +1,43 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from .fivemin import FiveMinIE +from ..utils import ( + url_basename, +) + + +class EngadgetIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://www.engadget.com/ + (?:video/5min/(?P\d+)| + [\d/]+/.*?) + ''' + + _TEST = { + 'url': 'http://www.engadget.com/video/5min/518153925/', + 'md5': 'c6820d4828a5064447a4d9fc73f312c9', + 'info_dict': { + 'id': '518153925', + 'ext': 'mp4', + 'title': 'Samsung Galaxy Tab Pro 8.4 Review', + }, + 'add_ie': ['FiveMin'], + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + if video_id is not None: + return FiveMinIE._build_result(video_id) + else: + title = url_basename(url) + webpage = self._download_webpage(url, title) + ids = re.findall(r']+?playList=(\d+)', webpage) + return { + '_type': 'playlist', + 'title': title, + 'entries': [FiveMinIE._build_result(id) for id in ids] + } diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py new file mode 100644 index 000000000..215cc831e --- /dev/null +++ b/youtube_dl/extractor/fivemin.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_str, +) + + +class FiveMinIE(InfoExtractor): + IE_NAME = '5min' + _VALID_URL = r'''(?x) + (?:https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(.*?&)?playList=| + 5min:) + (?P\d+) + ''' + + _TEST = { + # From http://www.engadget.com/2013/11/15/ipad-mini-retina-display-review/ + 'url': 'http://pshared.5min.com/Scripts/PlayerSeed.js?sid=281&width=560&height=345&playList=518013791', + 'md5': '4f7b0b79bf1a470e5004f7112385941d', + 'info_dict': { + 'id': '518013791', + 'ext': 'mp4', + 'title': 'iPad Mini with Retina Display Review', + }, + } + + @classmethod + def _build_result(cls, video_id): + return cls.url_result('5min:%s' % video_id, cls.ie_key()) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + info = self._download_json( + 'https://syn.5min.com/handlers/SenseHandler.ashx?func=GetResults&' + 'playlist=%s&url=https' % video_id, + video_id)['binding'][0] + + second_id = compat_str(int(video_id[:-2]) + 1) + formats = [] + for quality, height in [(1, 320), (2, 480), (4, 720), (8, 1080)]: + if any(r['ID'] == quality for r in info['Renditions']): + formats.append({ + 'format_id': compat_str(quality), + 'url': 'http://avideos.5min.com/%s/%s/%s_%s.mp4' % (second_id[-3:], second_id, video_id, quality), + 'height': height, + }) + + return { + 'id': video_id, + 'title': info['Title'], + 'formats': formats, + }