[ellentv] Simplify and correct tests

This commit is contained in:
Philipp Hagemeister 2014-08-21 11:57:03 +02:00
parent 266c71f971
commit 1d01f26ab1

View file

@ -4,10 +4,14 @@
import re import re
import json import json
from .common import InfoExtractor, ExtractorError from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_iso8601,
)
class EllenTVIE(InfoExtractor): class EllenTVIE(InfoExtractor):
IE_NAME = u'ellentv'
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)' _VALID_URL = r'https?://(?:www\.)?ellentv\.com/videos/(?P<id>[a-z0-9_-]+)'
_TEST = { _TEST = {
'url': 'http://www.ellentv.com/videos/0-7jqrsr18/', 'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
@ -15,43 +19,39 @@ class EllenTVIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '0-7jqrsr18', 'id': '0-7jqrsr18',
'ext': 'mp4', 'ext': 'mp4',
'title': u'What\'s Wrong with These Photos? A Whole Lot', 'title': 'What\'s Wrong with These Photos? A Whole Lot',
# TODO more properties, either as: 'timestamp': 1406876400,
# * A value 'upload_date': '20140801',
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, id) webpage = self._download_webpage(url, video_id)
timestamp = parse_iso8601(self._search_regex(
r'<span class="publish-date"><time datetime="([^"]+)">',
webpage, 'timestamp'))
return { return {
'id': id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'url': self._html_search_meta('VideoURL', webpage, 'url') 'url': self._html_search_meta('VideoURL', webpage, 'url'),
'timestamp': timestamp,
} }
class EllenTVClipsIE(InfoExtractor): class EllenTVClipsIE(InfoExtractor):
IE_NAME = u'ellentv:clips' IE_NAME = 'EllenTV:clips'
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)' _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
_TEST = { _TEST = {
'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
'md5': 'TODO: md5 sum of the first 10KiB of the video file',
'info_dict': { 'info_dict': {
'id': '0_wf6pizq7', 'id': 'meryl-streep-vanessa-hudgens',
'ext': 'mp4', 'title': 'Meryl Streep, Vanessa Hudgens',
'title': 'Video title goes here', },
# TODO more properties, either as: 'playlist_mincount': 9,
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
} }
def _real_extract(self, url): def _real_extract(self, url):
@ -76,4 +76,4 @@ def _extract_playlist(self, webpage):
raise ExtractorError('Failed to download JSON', cause=ve) raise ExtractorError('Failed to download JSON', cause=ve)
def _extract_entries(self, playlist): def _extract_entries(self, playlist):
return [self.url_result(item[u'url'], 'EllenTV') for item in playlist] return [self.url_result(item['url'], 'EllenTV') for item in playlist]