Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 15:25:49 +00:00
Code Issues Projects Releases Wiki Activity

[empflix] Fix extraction

Browse Source
This commit is contained in:
Sergey M․ 2014-05-24 01:06:03 +07:00
parent 4d78f3b770
commit b1e6f55912
1 changed files with 14 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/empflix.py
View File

@ -3,20 +3,18 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
)
class EmpflixIE(InfoExtractor): class EmpflixIE(InfoExtractor):
_VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
_TEST = { _TEST = {
'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
'md5': '5e5cc160f38ca9857f318eb97146e13e', 'md5': 'b1bc15b6412d33902d6e5952035fcabc',
'info_dict': { 'info_dict': {
'id': '33051', 'id': '33051',
'ext': 'flv', 'ext': 'mp4',
'title': 'Amateur Finger Fuck', 'title': 'Amateur Finger Fuck',
'description': 'Amateur solo finger fucking.',
'age_limit': 18, 'age_limit': 18,
} }
} }
@ -30,6 +28,8 @@ def _real_extract(self, url):
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
video_description = self._html_search_regex(
r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
cfg_url = self._html_search_regex( cfg_url = self._html_search_regex(
r'flashvars\.config = escape\("([^"]+)"', r'flashvars\.config = escape\("([^"]+)"',
@ -37,12 +37,18 @@ def _real_extract(self, url):
cfg_xml = self._download_xml( cfg_xml = self._download_xml(
cfg_url, video_id, note='Downloading metadata') cfg_url, video_id, note='Downloading metadata')
video_url = cfg_xml.find('videoLink').text
formats = [
{
'url': item.find('videoLink').text,
'format_id': item.find('res').text,
} for item in cfg_xml.findall('./quality/item')
]
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'ext': 'flv',
'title': video_title, 'title': video_title,
'description': video_description,
'formats': formats,
'age_limit': age_limit, 'age_limit': age_limit,
} }