refactoring - bug fixes

This commit is contained in:
David Development 2015-01-25 11:53:53 +01:00
parent 6695916045
commit fe41ddbb28

View file

@ -2,7 +2,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
@ -14,55 +13,58 @@ from ..utils import (
class RTL2IE(InfoExtractor): class RTL2IE(InfoExtractor):
"""Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" """Information Extractor for RTL2"""
_VALID_URL = r'http?://(?P<url>(?P<domain>(www\.)?rtl2\.de)/.*/(?P<video_id>.*))' _VALID_URL = r'http?://(?P<url>(?P<domain>(www\.)?rtl2\.de)/.*/(?P<video_id>.*))/'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0', 'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
'info_dict': { 'info_dict': {
'id': 'folge-203-0', 'id': 'folge-203-0',
'ext': 'f4v', 'ext': 'f4v',
'title': 'GRIP sucht den Sommerk\xf6nig', 'title': 'GRIP sucht den Sommerkönig',
'description' : 'Matthias, Det und Helge treten gegeneinander an.' 'description' : 'Matthias, Det und Helge treten gegeneinander an.'
}, },
'params': { 'params': {
# rtmp download # rtmp download
#'skip_download': True, 'skip_download': True,
}, },
}, },
{ {
'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/', 'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
'info_dict': { 'info_dict': {
'id': '21040-anna-erwischt-alex', 'id': '21040-anna-erwischt-alex',
'ext': 'f4v', 'ext': 'mp4',
'title': 'GRIP sucht den Sommerk\xf6nig', 'title': 'Anna erwischt Alex!',
'description' : 'Matthias, Det und Helge treten gegeneinander an.' 'description' : 'Anna ist Alex\' Tochter bei Köln 50667.'
}, },
'params': { 'params': {
# rtmp download # rtmp download
#'skip_download': True, 'skip_download': True,
}, },
}, },
] ]
def _real_extract(self, url): def _real_extract(self, url):
#Some rtl2 urls have no slash at the end, so append it.
if not url.endswith("/"):
url += '/'
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_page_url = 'http://%s/' % mobj.group('domain')
video_id = mobj.group('video_id') video_id = mobj.group('video_id')
webpage = self._download_webpage('http://' + mobj.group('url'), video_id) webpage = self._download_webpage(url, video_id)
vico_id = self._html_search_regex(r'vico_id\s*:\s*([0-9]+)', webpage, '%s'); vico_id = self._html_search_regex(r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id not found');
vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, '%s'); vivi_id = self._html_search_regex(r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id not found');
info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
webpage = self._download_webpage(info_url, '') webpage = self._download_webpage(info_url, '')
video_info = json.loads(webpage) video_info = self._download_json(info_url, video_id)
download_url = video_info["video"]["streamurl"] # self._html_search_regex(r'streamurl\":\"(.*?)\"', webpage, '%s'); download_url = video_info["video"]["streamurl"]
title = video_info["video"]["titel"] # self._html_search_regex(r'titel\":\"(.*?)\"', webpage, '%s'); title = video_info["video"]["titel"]
description = video_info["video"]["beschreibung"] # self._html_search_regex(r'beschreibung\":\"(.*?)\"', webpage, '%s'); description = video_info["video"]["beschreibung"]
#ext = self._html_search_regex(r'streamurl\":\".*?(\..{2,4})\"', webpage, '%s');
thumbnail = video_info["video"]["image"] thumbnail = video_info["video"]["image"]
@ -70,15 +72,15 @@ class RTL2IE(InfoExtractor):
stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s') stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, '%s')
#print(download_url) #Debug output
#print(stream_url) #print('URL: ' + url)
#print(title) #print('DL URL: ' + download_url)
#print(description) #print('Stream URL: ' + stream_url)
#print(video_id) #print('Title: ' + title)
#print('Description: '+ description)
#print('Video ID: ' + video_id)
formats = [] formats = [{
fmt = {
'url' : download_url, 'url' : download_url,
#'app': 'ondemand?_fcs_vhost=cp108781.edgefcs.net', #'app': 'ondemand?_fcs_vhost=cp108781.edgefcs.net',
'play_path': stream_url, 'play_path': stream_url,
@ -86,10 +88,8 @@ class RTL2IE(InfoExtractor):
'page_url': url, 'page_url': url,
'flash_version' : "LNX 11,2,202,429", 'flash_version' : "LNX 11,2,202,429",
'rtmp_conn' : ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"], 'rtmp_conn' : ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"],
'no_resume' : 1, 'no_resume' : True,
} }]
formats.append(fmt)
return { return {
'id': video_id, 'id': video_id,