Compare commits

..

4 Commits

Author SHA1 Message Date
Philipp Hagemeister
34814eb66e release 2015.02.10 2015-02-10 01:19:52 +01:00
Philipp Hagemeister
3a5bcd0326 [extractor/common] Wrap extractor errors (Fixes #1194)
For now, we just wrap some common errors. More may follow. We do not want to catch actual programming errors in the extractors, such as 1 // 0.
2015-02-10 01:17:23 +01:00
Philipp Hagemeister
99c2398bc6 [bandcamp] Use our API to get more stable error messages (#1194) 2015-02-09 19:08:51 +01:00
Philipp Hagemeister
28f1272870 [svtplay] Correct test case 2015-02-09 16:05:01 +01:00
4 changed files with 25 additions and 14 deletions

View File

@@ -72,26 +72,29 @@ class BandcampIE(InfoExtractor):
download_link = m_download.group(1)
video_id = self._search_regex(
r'var TralbumData = {.*?id: (?P<id>\d+),?$',
webpage, 'video id', flags=re.MULTILINE | re.DOTALL)
r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
webpage, 'video id')
download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
# We get the dictionary of the track from some javascript code
info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1)
info = json.loads(info)[0]
all_info = self._parse_json(self._search_regex(
r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
info = All_info[0]
# We pick mp3-320 for now, until format selection can be easily implemented.
mp3_info = info['downloads']['mp3-320']
# If we try to use this url it says the link has expired
initial_url = mp3_info['url']
re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$'
m_url = re.match(re_url, initial_url)
m_url = re.match(
r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
initial_url)
# We build the url we will use to get the final track url
# This url is build in Bandcamp in the script download_bunde_*.js
request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
# If we could correctly generate the .rand field the url would be
# in the "download_url" key
final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1)
final_url = self._search_regex(
r'"retry_url":"(.*?)"', final_url_webpage, 'final video URL')
return {
'id': video_id,

View File

@@ -264,8 +264,15 @@ class InfoExtractor(object):
def extract(self, url):
"""Extracts URL information and returns it in list of dicts."""
self.initialize()
return self._real_extract(url)
try:
self.initialize()
return self._real_extract(url)
except ExtractorError:
raise
except compat_http_client.IncompleteRead as e:
raise ExtractorError('A network error has occured.', cause=e, expected=True)
except (KeyError,) as e:
raise ExtractorError('An extractor error has occured.', cause=e)
def set_downloader(self, downloader):
"""Sets the downloader for this IE."""

View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
@@ -10,13 +11,13 @@ class SVTPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final',
'md5': '2521cd644e862936cf2e698206e47385',
'md5': 'f4a184968bc9c802a9b41316657aaa80',
'info_dict': {
'id': '3966754',
'id': '2609989',
'ext': 'mp4',
'title': 'FIFA 14 - E3 2013 Trailer',
'title': 'SM veckan vinter, Örebro - Rally, final',
'duration': 4500,
'thumbnail': 're:^https?://.*\.jpg$',
'thumbnail': 're:^https?://.*[\.-]jpg$',
},
}

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.02.09.3'
__version__ = '2015.02.10'