From e81a47460365738a0add4d4da52a712c0091704f Mon Sep 17 00:00:00 2001 From: snipem Date: Fri, 3 Apr 2015 15:34:49 +0200 Subject: [PATCH] [Gamersyde] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/gamersyde.py | 64 +++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) create mode 100644 youtube_dl/extractor/gamersyde.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index aae4aae4c..2935d5b33 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -177,6 +177,7 @@ from .gameone import ( GameOneIE, GameOnePlaylistIE, ) +from .gamersyde import GamersydeIE from .gamespot import GameSpotIE from .gamestar import GameStarIE from .gametrailers import GametrailersIE diff --git a/youtube_dl/extractor/gamersyde.py b/youtube_dl/extractor/gamersyde.py new file mode 100644 index 000000000..c40106216 --- /dev/null +++ b/youtube_dl/extractor/gamersyde.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals +import re +import json +import time +from .common import InfoExtractor + + +class GamersydeIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?gamersyde\.com/hqstream_' + _TEST = { + 'url': 'http://www.gamersyde.com/hqstream_bloodborne_birth_of_a_hero-34371_en.html', + 'md5': 'f38d400d32f19724570040d5ce3a505f', + 'info_dict': { + 'id': '34371', + 'ext': 'mp4', + 'title': 'Bloodborne - Birth of a hero', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _calculateDuration(self, durationString): + duration = time.strptime(durationString, "%M minutes %S seconds") + return duration.tm_min * 60 + duration.tm_sec + + def _fixJsonSyntax(self, json): + + json = re.sub(r"{\s*(\w)", r'{"\1', json) + json = re.sub(r",\s*(\w)", r',"\1', json) + json = re.sub(r"(\w): ", r'\1":', json) + json = re.sub(r",\s*}", "}", json, flags=re.DOTALL) + json = re.sub(r",\s*]", "]", json, flags=re.DOTALL) + + return json + + def _real_extract(self, url): + + video_id = self._search_regex(r'-(.*?)_[a-z]{2}.html$', url, 'video_id') + webpage = self._download_webpage(url, video_id) + + filesJson = self._search_regex(r'playlist: (.*?)\}\);', webpage, 'files', flags=re.DOTALL) + filesJson = self._fixJsonSyntax(filesJson) + + data = json.loads(filesJson) + playlist = data[0] + + formats = [] + + title = re.sub(r"[0-9]+ - ", "", playlist['title']) + + for playlistEntry in playlist['sources']: + format = { + 'url': playlistEntry['file'], + 'format_id': playlistEntry['label'] + } + + formats.append(format) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': playlist['image'] + }