lasers/searx
1
0
Fork 0
mirror of https://github.com/searx/searx synced 2024-12-11 19:49:33 +01:00
Code Issues Projects Releases Wiki Activity

Merge pull request #1658 from dalf/video-fixes

Browse Source 
Fix dailymotion, google_videos and youtube_noapi engines
This commit is contained in:
Alexandre Flament 2019-08-01 07:44:30 +02:00 committed by GitHub
commit 1bed39e6cb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 22 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
searx/engines/dailymotion.py
View File

@ -15,7 +15,7 @@
from json import loads from json import loads
from datetime import datetime from datetime import datetime
from searx.url_utils import urlencode from searx.url_utils import urlencode
from searx.utils import match_language from searx.utils import match_language, html_to_text
# engine dependent config # engine dependent config
categories = ['videos'] categories = ['videos']
@ -59,7 +59,7 @@ def response(resp):
for res in search_res['list']: for res in search_res['list']:
title = res['title'] title = res['title']
url = res['url'] url = res['url']
content = res['description'] content = html_to_text(res['description'])
thumbnail = res['thumbnail_360_url'] thumbnail = res['thumbnail_360_url']
publishedDate = datetime.fromtimestamp(res['created_time'], None) publishedDate = datetime.fromtimestamp(res['created_time'], None)
embedded = embedded_url.format(videoid=res['id']) embedded = embedded_url.format(videoid=res['id'])

6
searx/engines/google_videos.py
View File

@ -75,8 +75,10 @@ def response(resp):
# get thumbnails # get thumbnails
script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text) script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
id = result.xpath('.//div[@class="s"]//img/@id')[0] ids = result.xpath('.//div[@class="s"]//img/@id')
thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id, if len(ids) > 0:
thumbnails_data = \
re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + ids[0],
script) script)
tmp = [] tmp = []
if len(thumbnails_data) != 0: if len(thumbnails_data) != 0:

15
searx/engines/youtube_noapi.py
View File

@ -67,12 +67,8 @@ def response(resp):
if videoid is not None: if videoid is not None:
url = base_youtube_url + videoid url = base_youtube_url + videoid
thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg' thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'
title = video.get('title', {}).get('simpleText', videoid) title = get_text_from_json(video.get('title', {}))
description_snippet = video.get('descriptionSnippet', {}) content = get_text_from_json(video.get('descriptionSnippet', {}))
if 'runs' in description_snippet:
content = reduce(lambda a, b: a + b.get('text', ''), description_snippet.get('runs'), '')
else:
content = description_snippet.get('simpleText', '')
embedded = embedded_url.format(videoid=videoid) embedded = embedded_url.format(videoid=videoid)
# append result # append result
@ -85,3 +81,10 @@ def response(resp):
# return results # return results
return results return results
def get_text_from_json(element):
if 'runs' in element:
return reduce(lambda a, b: a + b.get('text', ''), element.get('runs'), '')
else:
return element.get('simpleText', '')