[traileraddict] Fix extraction

This commit is contained in:
Philipp Hagemeister 2014-02-02 12:52:47 +01:00
parent 7ac1f877a7
commit 56b6faf91e

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
@ -6,12 +8,13 @@
class TrailerAddictIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
_TEST = {
u'url': u'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
u'file': u'76184.mp4',
u'md5': u'57e39dbcf4142ceb8e1f242ff423fd71',
u'info_dict': {
u"title": u"Prince Avalanche Trailer",
u"description": u"Trailer for Prince Avalanche.Two highway road workers spend the summer of 1988 away from their city lives. The isolated landscape becomes a place of misadventure as the men find themselves at odds with each other and the women they left behind."
'url': 'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
'md5': '41365557f3c8c397d091da510e73ceb4',
'info_dict': {
'id': '76184',
'ext': 'mp4',
'title': 'Prince Avalanche Trailer',
'description': 'Trailer for Prince Avalanche.\n\nTwo highway road workers spend the summer of 1988 away from their city lives. The isolated landscape becomes a place of misadventure as the men find themselves at odds with each other and the women they left behind.',
}
}
@ -22,9 +25,15 @@ def _real_extract(self, url):
title = self._search_regex(r'<title>(.+?)</title>',
webpage, 'video title').replace(' - Trailer Addict','')
view_count = self._search_regex(r'Views: (.+?)<br />',
webpage, 'Views Count')
video_id = self._og_search_property('video', webpage, 'Video id').split('=')[1]
view_count_str = self._search_regex(
r'<span class="views_n">([0-9,.]+)</span>',
webpage, 'view count', fatal=False)
view_count = (
None if view_count_str is None
else int(view_count_str.replace(',', '')))
video_id = self._search_regex(
r'<param\s+name="movie"\s+value="/emb/([0-9]+)"\s*/>',
webpage, 'video id')
# Presence of (no)watchplus function indicates HD quality is available
if re.search(r'function (no)?watchplus()', webpage):
@ -39,14 +48,16 @@ def _real_extract(self, url):
info_webpage, 'Download url').replace('%3F','?')
thumbnail_url = self._search_regex(r'&image=(.+?)&',
info_webpage, 'thumbnail url')
ext = final_url.split('.')[-1].split('?')[0]
return [{
'id' : video_id,
'url' : final_url,
'ext' : ext,
'title' : title,
'thumbnail' : thumbnail_url,
'description' : self._og_search_description(webpage),
'view_count' : view_count,
}]
description = self._html_search_regex(
r'(?s)<div class="synopsis">.*?<div class="movie_label_info"[^>]*>(.*?)</div>',
webpage, 'description', fatal=False)
return {
'id': video_id,
'url': final_url,
'title': title,
'thumbnail': thumbnail_url,
'description': description,
'view_count': view_count,
}