Add extractor for Engadget and 5min (closes #2465)

engadget.com uses the generic 5min.com service.
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-03-21 19:13:46 +01:00
parent aa488e1385
commit 933a5b3792
3 changed files with 101 additions and 0 deletions

View File

@ -64,6 +64,7 @@
from .eighttracks import EightTracksIE from .eighttracks import EightTracksIE
from .eitb import EitbIE from .eitb import EitbIE
from .elpais import ElPaisIE from .elpais import ElPaisIE
from .engadget import EngadgetIE
from .escapist import EscapistIE from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE from .exfm import ExfmIE
@ -72,6 +73,7 @@
from .faz import FazIE from .faz import FazIE
from .firstpost import FirstpostIE from .firstpost import FirstpostIE
from .firsttv import FirstTVIE from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
from .fktv import ( from .fktv import (
FKTVIE, FKTVIE,
FKTVPosteckeIE, FKTVPosteckeIE,

View File

@ -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<id>\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'<iframe[^>]+?playList=(\d+)', webpage)
return {
'_type': 'playlist',
'title': title,
'entries': [FiveMinIE._build_result(id) for id in ids]
}

View File

@ -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<id>\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,
}