[eporner] Extract all formats

This commit is contained in:
Sergey M․ 2014-09-02 21:39:22 +07:00
parent 3baa62e8d1
commit a7862a1bc8
1 changed files with 23 additions and 6 deletions

View File

@ -11,12 +11,13 @@ from ..utils import (
class EpornerIE(InfoExtractor): class EpornerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<title_dash>[\w-]+)/?' _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)'
_TEST = { _TEST = {
'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
'md5': '3b427ae4b9d60619106de3185c2987cd', 'md5': '3b427ae4b9d60619106de3185c2987cd',
'info_dict': { 'info_dict': {
'id': '95008', 'id': '95008',
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
'ext': 'flv', 'ext': 'flv',
'title': 'Infamous Tiffany Teen Strip Tease Video', 'title': 'Infamous Tiffany Teen Strip Tease Video',
'duration': 194, 'duration': 194,
@ -28,7 +29,9 @@ class EpornerIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>(.*?) - EPORNER', webpage, 'title') r'<title>(.*?) - EPORNER', webpage, 'title')
@ -37,9 +40,22 @@ class EpornerIE(InfoExtractor):
webpage, 'redirect_code') webpage, 'redirect_code')
redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code) redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code)
player_code = self._download_webpage( player_code = self._download_webpage(
redirect_url, video_id, note='Downloading player config') redirect_url, display_id, note='Downloading player config')
video_url = self._html_search_regex(
r'file: "(.*?)",', player_code, 'video_url') sources = self._search_regex(
r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
formats = []
for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
fmt = {
'url': video_url,
'format_id': format_id,
}
m = re.search(r'^(\d+)', format_id)
if m:
fmt['height'] = int(m.group(1))
formats.append(fmt)
self._sort_formats(formats)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'class="mbtim">([0-9:]+)</div>', webpage, 'duration', r'class="mbtim">([0-9:]+)</div>', webpage, 'duration',
@ -50,9 +66,10 @@ class EpornerIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'url': video_url, 'display_id': display_id,
'title': title, 'title': title,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'formats': formats,
'age_limit': self._rta_search(webpage), 'age_limit': self._rta_search(webpage),
} }