[gamekings] Improve extraction

This commit is contained in:
Sergey M․ 2015-02-08 23:03:12 +06:00
parent 3bd4bffb1c
commit d87ec897e9

View File

@ -1,70 +1,64 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
xpath_text, xpath_text,
xpath_with_ns xpath_with_ns,
) )
class GamekingsIE(InfoExtractor): class GamekingsIE(InfoExtractor):
_VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<name>[0-9a-z\-]+)' _VALID_URL = r'http://www\.gamekings\.tv/videos/(?P<id>[^/]+)'
_TESTS = [ _TESTS = [{
{
'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/', 'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
# MD5 is flaky, seems to change regularly # MD5 is flaky, seems to change regularly
# 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3', # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3',
'info_dict': { 'info_dict': {
'id': '20130811', 'id': 'phoenix-wright-ace-attorney-dual-destinies-review',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review', 'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review',
'description': 'md5:36fd701e57e8c15ac8682a2374c99731', 'description': 'md5:36fd701e57e8c15ac8682a2374c99731',
} 'thumbnail': 're:^https?://.*\.jpg$',
}, },
{ }, {
# vimeo video
'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/', 'url': 'http://www.gamekings.tv/videos/the-legend-of-zelda-majoras-mask/',
'md5': '12bf04dfd238e70058046937657ea68d',
'info_dict': { 'info_dict': {
'id': '118933752', 'id': 'the-legend-of-zelda-majoras-mask',
'ext': 'mp4', 'ext': 'mp4',
'title': 'The Legend of Zelda: Majoras Mask', 'title': 'The Legend of Zelda: Majoras Mask',
'description': 'md5:9917825fe0e9f4057601fe1e38860de3' 'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
} 'thumbnail': 're:^https?://.*\.jpg$',
} },
] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url) webpage = self._download_webpage(url, video_id)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
playlist_id = re.search(r'(?:gogoVideo)\(\d+,"?(?P<playlist_id>.*)"', webpage, re.MULTILINE).group('playlist_id') playlist_id = self._search_regex(
playlist_url = 'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=' + playlist_id r'gogoVideo\(\s*\d+\s*,\s*"([^"]+)', webpage, 'playlist id')
playlist_rss = self._download_xml(playlist_url, playlist_id)
playlist = self._download_xml(
'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,
video_id)
NS_MAP = { NS_MAP = {
'jwplayer': 'http://rss.jwpcdn.com/' 'jwplayer': 'http://rss.jwpcdn.com/'
} }
item = playlist_rss.find('./channel/item') item = playlist.find('./channel/item')
image = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'image') thumbnail = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'thumbnail')
file_node = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)) video_url = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)).get('file')
video_url = file_node.get('file')
video = re.search(r'[0-9]+', video_url)
video_id = video.group(0)
# Todo: Add medium format
return { return {
'id': video_id, 'id': video_id,
'ext': 'mp4',
'url': video_url, 'url': video_url,
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
'thumbnail': image 'thumbnail': thumbnail,
} }