github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[Gamekings] Use xpath

Browse source 
XPath is used for extracting the video url and the thumbnail
This commit is contained in:
robin 2015-02-08 16:44:25 +01:00
parent 5d678df64a
commit 955c5505e7
1 changed files with 15 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/gamekings.py
View file

@ -3,7 +3,11 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import xpath_text from ..utils import (
xpath_text,
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<name>[0-9a-z\-]+)'
@ -39,23 +43,22 @@ class GamekingsIE(InfoExtractor):
playlist_id = re.search(r'(?:gogoVideo)\(\d+,"?(?P<playlist_id>.*)"', webpage, re.MULTILINE).group('playlist_id') playlist_id = re.search(r'(?:gogoVideo)\(\d+,"?(?P<playlist_id>.*)"', webpage, re.MULTILINE).group('playlist_id')
playlist_url = 'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=' + playlist_id playlist_url = 'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=' + playlist_id
playlist_rss = self._download_xml(playlist_url, playlist_id) playlist_rss = self._download_xml(playlist_url, playlist_id)
NS_MAP { NS_MAP = {
'rss': 'http://rss.jwpcdn.com/' 'jwplayer': 'http://rss.jwpcdn.com/'
} }
# Todo: Implement Xpath for searching the video link item = playlist_rss.find('./channel/item')
video_url = self._og_search_video_url(webpage) image = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'image')
file_node = item.find(xpath_with_ns('./jwplayer:source', NS_MAP))
video_url = file_node.get('file')
video = re.search(r'[0-9]+', video_url) video = re.search(r'[0-9]+', video_url)
video_id = video.group(0) video_id = video.group(0)
# Todo: add medium format # Todo: Add medium format
video_url = video_url.replace(video_id, 'large/' + video_id)
if "vimeo" in video_url:
video_url = video_url.replace('large/' + video_id, video_id)
video_url = video_url.replace('http://stream.gamekings.tv/', '')
return { return {
'id': video_id, 'id': video_id,