zaclys/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng synced 2024-01-01 19:24:07 +01:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'master' into patch-1

Browse source
This commit is contained in:
Alexandre Flament 2019-04-09 03:32:39 +02:00 • committed by GitHub
commit 3e9ce2638a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 93 additions and 148 deletions
Download patch file Download diff file Expand all files Collapse all files

64
searx/engines/youtube_noapi.py
View file

@ -8,7 +8,8 @@
# @stable no
# @parse url, title, content, publishedDate, thumbnail, embedded
from lxml import html
from functools import reduce
from json import loads
from searx.engines.xpath import extract_text
from searx.utils import list_get
from searx.url_utils import quote_plus
@ -34,20 +35,6 @@ embedded_url = '<iframe width="540" height="304" ' +\
base_youtube_url = 'https://www.youtube.com/watch?v='
# specific xpath variables
results_xpath = "//ol/li/div[contains(@class, 'yt-lockup yt-lockup-tile yt-lockup-video vve-check')]"
url_xpath = './/h3/a/@href'
title_xpath = './/div[@class="yt-lockup-content"]/h3/a'
content_xpath = './/div[@class="yt-lockup-content"]/div[@class="yt-lockup-description yt-ui-ellipsis yt-ui-ellipsis-2"]'
# returns extract_text on the first result selected by the xpath or None
def extract_text_from_dom(result, xpath):
r = result.xpath(xpath)
if len(r) > 0:
return extract_text(r[0])
return None
# do search-request
def request(query, params):
@ -63,27 +50,38 @@ def request(query, params):
def response(resp):
results = []
dom = html.fromstring(resp.text)
results_data = resp.text[resp.text.find('ytInitialData'):]
results_data = results_data[results_data.find('{'):results_data.find(';\n')]
# parse results
for result in dom.xpath(results_xpath):
videoid = list_get(result.xpath('@data-context-item-id'), 0)
if videoid is not None:
url = base_youtube_url + videoid
thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'
results_json = loads(results_data) if results_data else {}
sections = results_json.get('contents', {})\
.get('twoColumnSearchResultsRenderer', {})\
.get('primaryContents', {})\
.get('sectionListRenderer', {})\
.get('contents', [])
title = extract_text_from_dom(result, title_xpath) or videoid
content = extract_text_from_dom(result, content_xpath)
for section in sections:
for video_container in section.get('itemSectionRenderer', {}).get('contents', []):
video = video_container.get('videoRenderer', {})
videoid = video.get('videoId')
if videoid is not None:
url = base_youtube_url + videoid
thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg'
title = video.get('title', {}).get('simpleText', videoid)
description_snippet = 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
results.append({'url': url,
'title': title,
'content': content,
'template': 'videos.html',
'embedded': embedded,
'thumbnail': thumbnail})
# append result
results.append({'url': url,
'title': title,
'content': content,
'template': 'videos.html',
'embedded': embedded,
'thumbnail': thumbnail})
# return results
return results

15
searx/query.py
View file

@ -113,19 +113,16 @@ class RawTextQuery(object):
parse_next = True
engine_name = engine_shortcuts[prefix]
if engine_name in engines:
for engine_category in engines[engine_name].categories:
self.engines.append({'category': engine_category,
'name': engine_name,
'from_bang': True})
self.engines.append({'category': 'none',
'name': engine_name,
'from_bang': True})
# check if prefix is equal with engine name
elif prefix in engines:
parse_next = True
if prefix in engines:
for engine_category in engines[prefix].categories:
self.engines.append({'category': engine_category,
'name': prefix,
'from_bang': True})
self.engines.append({'category': 'none',
'name': prefix,
'from_bang': True})
# check if prefix is equal with categorie name
elif prefix in categories: