R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

- Implemented basic extraction for vidlii but requires improvement

Browse Source
This commit is contained in:
Patrick Jattke 2017-11-09 09:38:47 +01:00
parent 7d1b38c972
commit f4d55fbe13
1 changed files with 48 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
youtube_dl/extractor/vidlii.py
View File

@ -1,11 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from ..utils import (
int_or_none,
get_element_by_id)
from .common import InfoExtractor
class VidliiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_VALID_URL = r'(?:https*?:\/\/)*(?:www\.)*vidlii.com\/watch\?v=(?P<id>[^?\s]{11})'
_TEST = {
'url': 'https://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
@ -23,16 +28,52 @@ class VidliiIE(InfoExtractor):
}
def _real_extract(self, url):
# get required video properties
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
description = get_element_by_id('des_text', webpage).strip()
uploader = self._html_search_regex(
r'<div[^>]+class="wt_person"[^>]*>(?:[^<]+)<a href="\/user\/[^>]*?>([^<]*?)<', webpage, 'uploader')
url = self._html_search_regex(r'videoInfo[\s]*=[\s]*{[^}]*src:[\s]*(?:"|\')([^"]*?)(?:"|\')', webpage, 'url')
# get additional properties
uploader_url = "https://www.vidlii.com/user/%s" % uploader
upload_date = self._html_search_meta('datePublished', webpage, 'upload_date', default=False).replace('-', '')
categories = self._html_search_regex(
r'<div>Category:\s*<\/div>[\s\r]*<div>[\s\r]*<a href="\/videos\?c=[^>]*>([^<]*?)<\/a>', webpage,
'categories')
tags = re.findall(r'<a href="/results\?q=[^>]*>[\s]*([^<]*)</a>', webpage)
duration = int_or_none(self._html_search_meta('video:duration', webpage, 'duration', default=False))
view_count = int_or_none(
self._html_search_regex(r'<div[^>]+class="w_views"[^>]*><strong>([^<]+?)<\/strong>', webpage,
'view_count'))
comment_count = int_or_none(self._html_search_regex(r'<span[^>]+id="cmt_num"[^>]*>([^<]+?)<\/span>', webpage,
'comment_count'))
average_rating = int_or_none(
self._html_search_regex(r'{[\s\r]*\$\("#rateYo"\).rateYo\({[^}]*rating:\s*([0-9]*?),[^}]*}',
webpage, 'average_rating'))
thumbnail_link = self._html_search_regex(r'videoInfo[\s]*=[\s]*{[^}]*img:[\s]*(?:"|\')([^"]*?)(?:"|\')',
webpage, 'thumbnail')
thumbnail = 'https://www.vidlii.com%s' % thumbnail_link
type = self._og_search_property('type', webpage, 'type')
# use youtube-dl --print-json to show extracted metadata or debugger (watch value)
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
'description': description,
'uploader': uploader,
'url': url,
'uploader_url': uploader_url,
'upload_date': upload_date, # should we use release_date instead?
'categories': categories,
'tags': tags,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
'average_rating': average_rating,
'thumbnail': thumbnail,
'type': type
}