[jove] Simplify, extract full description and add test for video that requires subscription

This commit is contained in:
Sergey M․ 2014-08-19 20:02:08 +07:00
parent d5638d974f
commit fe556f1b0c
2 changed files with 47 additions and 30 deletions

View file

@ -1,64 +1,80 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from datetime import datetime
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext, ExtractorError from ..utils import (
ExtractorError,
unified_strdate
)
class JoveIE(InfoExtractor): class JoveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?jove\.com/video/(?P<id>[0-9]+)'
_CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}' _CHAPTERS_URL = 'http://www.jove.com/video-chapters?videoid={video_id:}'
_TEST = { _TESTS = [
'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current', {
'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b', 'url': 'http://www.jove.com/video/2744/electrode-positioning-montage-transcranial-direct-current',
'info_dict': { 'md5': '93723888d82dbd6ba8b3d7d0cd65dd2b',
'id': '2744', 'info_dict': {
'ext': 'mp4', 'id': '2744',
'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation', 'ext': 'mp4',
'description': 'Transcranial direct current stimulation (tDCS) is an established technique to modulate cortical excitability1,2. It has been ...', 'title': 'Electrode Positioning and Montage in Transcranial Direct Current Stimulation',
'thumbnail': 're:^https?://.*\.png$', 'description': 'md5:015dd4509649c0908bc27f049e0262c6',
'upload_date': '20110523', 'thumbnail': 're:^https?://.*\.png$',
} 'upload_date': '20110523',
} }
},
{
'url': 'http://www.jove.com/video/51796/culturing-caenorhabditis-elegans-axenic-liquid-media-creation',
'md5': '914aeb356f416811d911996434811beb',
'info_dict': {
'id': '51796',
'ext': 'mp4',
'title': 'Culturing Caenorhabditis elegans in Axenic Liquid Media and Creation of Transgenic Worms by Microparticle Bombardment',
'description': 'md5:35ff029261900583970c4023b70f1dc9',
'thumbnail': 're:^https?://.*\.png$',
'upload_date': '20140802',
}
},
]
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) webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('citation_title', webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage)
description = self._html_search_meta(
'description', webpage, 'description', fatal=False)
publish_date = self._html_search_meta(
'citation_publication_date', webpage, 'publish date', fatal=False)
if publish_date:
publish_date = datetime.strptime(publish_date,
'%Y/%m/%d').strftime('%Y%m%d')
# Not the same as video_id.
chapters_id = self._html_search_regex( chapters_id = self._html_search_regex(
r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id') r'/video-chapters\?videoid=([0-9]+)', webpage, 'chapters id')
chapters_xml = self._download_xml( chapters_xml = self._download_xml(
self._CHAPTERS_URL.format(video_id=chapters_id), self._CHAPTERS_URL.format(video_id=chapters_id),
video_id, note='Downloading chapter XML', video_id, note='Downloading chapters XML',
errnote='Failed to download chapter XML' errnote='Failed to download chapters XML')
)
video_url = chapters_xml.attrib.get('video') video_url = chapters_xml.attrib.get('video')
if not video_url: if not video_url:
raise ExtractorError('Failed to get the video URL') raise ExtractorError('Failed to get the video URL')
ext = determine_ext(video_url) title = self._html_search_meta('citation_title', webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage)
description = self._html_search_regex(
r'<div id="section_body_summary"><p class="jove_content">(.+?)</p>',
webpage, 'description', fatal=False)
publish_date = unified_strdate(self._html_search_meta(
'citation_publication_date', webpage, 'publish date', fatal=False))
comment_count = self._html_search_regex(
r'<meta name="num_comments" content="(\d+) Comments?"',
webpage, 'comment count', fatal=False)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'url': video_url,
'ext': ext,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': description, 'description': description,
'upload_date': publish_date, 'upload_date': publish_date,
'comment_count': comment_count,
} }

View file

@ -827,6 +827,7 @@ def unified_strdate(date_str):
'%b %dnd %Y %I:%M%p', '%b %dnd %Y %I:%M%p',
'%b %dth %Y %I:%M%p', '%b %dth %Y %I:%M%p',
'%Y-%m-%d', '%Y-%m-%d',
'%Y/%m/%d',
'%d.%m.%Y', '%d.%m.%Y',
'%d/%m/%Y', '%d/%m/%Y',
'%Y/%m/%d %H:%M:%S', '%Y/%m/%d %H:%M:%S',