From a20575e8aeafeb1aaf70243cce96505b661449e9 Mon Sep 17 00:00:00 2001
From: Elias Probst <mail@eliasprobst.eu>
Date: Sat, 21 Jun 2014 00:35:12 +0200
Subject: Make debug message useful and also report, which URL failed to
download.
---
youtube_dl/extractor/spiegel.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index 9156d7faf..94346daf6 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -36,7 +36,7 @@ class SpiegelIE(InfoExtractor):
xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml'
idoc = self._download_xml(
xml_url, video_id,
- note='Downloading XML', errnote='Failed to download XML')
+ note='Downloading XML', errnote='Failed to download XML from "{0}"'.format(xml_url))
formats = [
{
--
cgit v1.2.3
From 8bfb6723cb5bd9cb7a4c843e12688b26ab14d17a Mon Sep 17 00:00:00 2001
From: Elias Probst <mail@eliasprobst.eu>
Date: Sat, 21 Jun 2014 01:00:48 +0200
Subject: Extract the base_url for the XML download from the JS snippet's
'server' variable.
---
youtube_dl/extractor/spiegel.py | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index 94346daf6..87f1ee694 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -33,7 +33,13 @@ class SpiegelIE(InfoExtractor):
video_title = self._html_search_regex(
r'<div class="module-title">(.*?)</div>', webpage, 'title')
- xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml'
+ base_url = self._search_regex(
+ r'var\s+server\s+=\s+\"(http://video\d*\.spiegel\.de/flash/\d+/\d+/)\";',
+ webpage,
+ 'base_url',
+ )
+
+ xml_url = base_url + video_id + '.xml'
idoc = self._download_xml(
xml_url, video_id,
note='Downloading XML', errnote='Failed to download XML from "{0}"'.format(xml_url))
--
cgit v1.2.3
From 98aeac6ea9c6f554fa81f19cfa2a7b67b2d424f2 Mon Sep 17 00:00:00 2001
From: Elias Probst <mail@eliasprobst.eu>
Date: Sat, 21 Jun 2014 01:10:10 +0200
Subject: Use the 'base_url' for building the resulting 'url' as well.
---
youtube_dl/extractor/spiegel.py | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index 87f1ee694..bf5a5e2a4 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -47,7 +47,7 @@ class SpiegelIE(InfoExtractor):
formats = [
{
'format_id': n.tag.rpartition('type')[2],
- 'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text,
+ 'url': base_url + n.find('./filename').text,
'width': int(n.find('./width').text),
'height': int(n.find('./height').text),
'abr': int(n.find('./audiobitrate').text),
--
cgit v1.2.3
From 55c97a03e133012f92ffd9b2070f72234924ae7b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sat, 21 Jun 2014 16:31:18 +0700
Subject: [spiegel] Add description and modernize
---
youtube_dl/extractor/spiegel.py | 39 ++++++++++++++++++++++++++-------------
1 file changed, 26 insertions(+), 13 deletions(-)
diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py
index bf5a5e2a4..340a38440 100644
--- a/youtube_dl/extractor/spiegel.py
+++ b/youtube_dl/extractor/spiegel.py
@@ -1,3 +1,4 @@
+# encoding: utf-8
from __future__ import unicode_literals
import re
@@ -9,18 +10,33 @@ class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
_TESTS = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
- 'file': '1259285.mp4',
'md5': '2c2754212136f35fb4b19767d242f66e',
'info_dict': {
+ 'id': '1259285',
+ 'ext': 'mp4',
'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
+ 'description': 'md5:8029d8310232196eb235d27575a8b9f4',
+ 'duration': 49,
},
- },
- {
+ }, {
'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
- 'file': '1309159.mp4',
'md5': 'f2cdf638d7aa47654e251e1aee360af1',
'info_dict': {
+ 'id': '1309159',
+ 'ext': 'mp4',
'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
+ 'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
+ 'duration': 983,
+ },
+ }, {
+ 'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
+ 'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
+ 'info_dict': {
+ 'id': '1502367',
+ 'ext': 'mp4',
+ 'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
+ 'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
+ 'duration': 42,
},
}]
@@ -30,19 +46,15 @@ class SpiegelIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
- video_title = self._html_search_regex(
+ title = self._html_search_regex(
r'<div class="module-title">(.*?)</div>', webpage, 'title')
+ description = self._html_search_meta('description', webpage, 'description')
base_url = self._search_regex(
- r'var\s+server\s+=\s+\"(http://video\d*\.spiegel\.de/flash/\d+/\d+/)\";',
- webpage,
- 'base_url',
- )
+ r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
xml_url = base_url + video_id + '.xml'
- idoc = self._download_xml(
- xml_url, video_id,
- note='Downloading XML', errnote='Failed to download XML from "{0}"'.format(xml_url))
+ idoc = self._download_xml(xml_url, video_id)
formats = [
{
@@ -65,7 +77,8 @@ class SpiegelIE(InfoExtractor):
return {
'id': video_id,
- 'title': video_title,
+ 'title': title,
+ 'description': description,
'duration': duration,
'formats': formats,
}
--
cgit v1.2.3