Browse Source

Move Escapist into its own file

rtmp_test
Philipp Hagemeister 12 years ago
parent
commit
153697660d
2 changed files with 69 additions and 56 deletions
  1. +1
    -56
      youtube_dl/InfoExtractors.py
  2. +68
    -0
      youtube_dl/extractor/escapist.py

+ 1
- 56
youtube_dl/InfoExtractors.py View File

@ -24,6 +24,7 @@ from .extractor.bliptv import BlipTVIE, BlipTVUserIE
from .extractor.comedycentral import ComedyCentralIE from .extractor.comedycentral import ComedyCentralIE
from .extractor.dailymotion import DailymotionIE from .extractor.dailymotion import DailymotionIE
from .extractor.depositfiles import DepositFilesIE from .extractor.depositfiles import DepositFilesIE
from .extractor.escapist import EscapistIE
from .extractor.facebook import FacebookIE from .extractor.facebook import FacebookIE
from .extractor.gametrailers import GametrailersIE from .extractor.gametrailers import GametrailersIE
from .extractor.generic import GenericIE from .extractor.generic import GenericIE
@ -66,62 +67,6 @@ from .extractor.zdf import ZDFIE
class EscapistIE(InfoExtractor):
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
self.report_extraction(videoId)
webpage = self._download_webpage(url, videoId)
videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
webpage, u'description', fatal=False)
imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
webpage, u'thumbnail', fatal=False)
playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
webpage, u'player url')
title = self._html_search_regex('<meta name="title" content="([^"]*)"',
webpage, u'player url').split(' : ')[-1]
configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
configUrl = compat_urllib_parse.unquote(configUrl)
configJSON = self._download_webpage(configUrl, videoId,
u'Downloading configuration',
u'unable to download configuration')
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
try:
config = json.loads(configJSON)
except (ValueError,) as err:
raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
videoUrl = playlist[1]['url']
info = {
'id': videoId,
'url': videoUrl,
'uploader': showName,
'upload_date': None,
'title': title,
'ext': 'mp4',
'thumbnail': imgUrl,
'description': videoDesc,
'player_url': playerUrl,
}
return [info]
class CollegeHumorIE(InfoExtractor): class CollegeHumorIE(InfoExtractor):
"""Information extractor for collegehumor.com""" """Information extractor for collegehumor.com"""


+ 68
- 0
youtube_dl/extractor/escapist.py View File

@ -0,0 +1,68 @@
import json
import re
from .common import InfoExtractor
from ..utils import (
compat_str,
compat_urllib_parse,
ExtractorError,
)
class EscapistIE(InfoExtractor):
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
showName = mobj.group('showname')
videoId = mobj.group('episode')
self.report_extraction(videoId)
webpage = self._download_webpage(url, videoId)
videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
webpage, u'description', fatal=False)
imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
webpage, u'thumbnail', fatal=False)
playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
webpage, u'player url')
title = self._html_search_regex('<meta name="title" content="([^"]*)"',
webpage, u'player url').split(' : ')[-1]
configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
configUrl = compat_urllib_parse.unquote(configUrl)
configJSON = self._download_webpage(configUrl, videoId,
u'Downloading configuration',
u'unable to download configuration')
# Technically, it's JavaScript, not JSON
configJSON = configJSON.replace("'", '"')
try:
config = json.loads(configJSON)
except (ValueError,) as err:
raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
playlist = config['playlist']
videoUrl = playlist[1]['url']
info = {
'id': videoId,
'url': videoUrl,
'uploader': showName,
'upload_date': None,
'title': title,
'ext': 'mp4',
'thumbnail': imgUrl,
'description': videoDesc,
'player_url': playerUrl,
}
return [info]

Loading…
Cancel
Save