dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[presstv] Improve and simplify

This commit is contained in:
Yen Chi Hsuan 2016-04-11 16:14:07 +08:00
parent 7d58ea7c5b
commit dfbc7f7f3f
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
1 changed files with 25 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
youtube_dl/extractor/presstv.py
View File

@ -1,19 +1,21 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import str_to_int from ..utils import remove_start
class PressTVIE(InfoExtractor): class PressTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>[0-9]+)/(?P<m>[0-9]+)/(?P<d>[0-9]+)/(?P<id>[0-9]+)/' _VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>\d+)/(?P<m>\d+)/(?P<d>\d+)/(?P<id>\d+)/(?P<display_id>[^/]+)?'
_TEST = { _TEST = {
'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/', 'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
'md5': '5d7e3195a447cb13e9267e931d8dd5a5', 'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
'info_dict': { 'info_dict': {
'id': '459911', 'id': '459911',
'display_id': 'Australian-sewerage-treatment-facility-',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Organic mattresses used to clean waste water', 'title': 'Organic mattresses used to clean waste water',
'upload_date': '20160409', 'upload_date': '20160409',
@ -23,47 +25,47 @@ class PressTVIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, video_id) video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
# extract video URL from webpage # extract video URL from webpage
video_url = self._html_search_regex(r'<input type="hidden" id="inpPlayback" value="([^"]+)" />', webpage, video_url = self._hidden_inputs(webpage)['inpPlayback']
'Video URL')
# build list of available formats # build list of available formats
# specified in http://www.presstv.ir/Scripts/playback.js # specified in http://www.presstv.ir/Scripts/playback.js
base_url = 'http://192.99.219.222:82/presstv' base_url = 'http://192.99.219.222:82/presstv'
_formats = [ _formats = [
("180p", "_low200.mp4"), (180, '_low200.mp4'),
("360p", "_low400.mp4"), (360, '_low400.mp4'),
("720p", "_low800.mp4"), (720, '_low800.mp4'),
("1080p", ".mp4") (1080, '.mp4')
] ]
formats = [] formats = [{
for fmt in _formats:
format_id, extension = fmt
formats.append({
'url': base_url + video_url[:-4] + extension, 'url': base_url + video_url[:-4] + extension,
'format_id': format_id 'format_id': '%dp' % height,
}) 'height': height,
} for height, extension in _formats]
# extract video metadata # extract video metadata
title = self._html_search_meta('title', webpage, 'Title', True) title = remove_start(
title = title.partition('-')[2].strip() self._html_search_meta('title', webpage, fatal=True), 'PressTV-')
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage) description = self._og_search_description(webpage)
match = re.match(PressTVIE._VALID_URL, url)
upload_date = '%04d%02d%02d' % ( upload_date = '%04d%02d%02d' % (
str_to_int(match.group('y')), int(mobj.group('y')),
str_to_int(match.group('m')), int(mobj.group('m')),
str_to_int(match.group('d')) int(mobj.group('d')),
) )
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'title': title, 'title': title,
'formats': formats, 'formats': formats,
'thumbnail': thumbnail, 'thumbnail': thumbnail,