Icycoide/searxng
1
0
Fork 1
mirror of https://github.com/searxng/searxng.git synced 2025-08-03 10:32:21 +02:00
Code Issues Projects Releases Packages Wiki Activity

[mod] add/modify image fetching for bing_news, qwant and twitter engines

Browse source
This commit is contained in:
Alexandre Flament 2017-02-12 14:58:49 +01:00 • committed by Adam Tauber
parent 4cffd78650
commit f5128c7cb9
4 changed files with 28 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

5
searx/engines/bing_news.py
View file

@ -112,12 +112,11 @@ def response(resp):
# append result
if thumbnail is not None:
results.append({'template': 'videos.html',
'url': url,
results.append({'url': url,
'title': title,
'publishedDate': publishedDate,
'content': content,
'thumbnail': thumbnail})
'img_src': thumbnail})
else:
results.append({'url': url,
'title': title,

21
searx/engines/qwant.py
View file

@ -96,14 +96,27 @@ def response(resp):
'thumbnail_src': thumbnail_src,
'img_src': img_src})
elif (category_to_keyword.get(categories[0], '') == 'news' or
category_to_keyword.get(categories[0], '') == 'social'):
elif category_to_keyword.get(categories[0], '') == 'social':
published_date = datetime.fromtimestamp(result['date'], None)
img_src = result.get('img', None)
results.append({'url': res_url,
'title': title,
'publishedDate': published_date,
'content': content})
'content': content,
'img_src': img_src})
elif category_to_keyword.get(categories[0], '') == 'news':
published_date = datetime.fromtimestamp(result['date'], None)
media = result.get('media', [])
if len(media) > 0:
img_src = media[0].get('pict', {}).get('url', None)
else:
img_src = None
results.append({'url': res_url,
'title': title,
'publishedDate': published_date,
'content': content,
'img_src': img_src})
return results

7
searx/engines/twitter.py
View file

@ -27,6 +27,7 @@ search_url = base_url + 'search?'
# specific xpath variables
results_xpath = '//li[@data-item-type="tweet"]'
avatar_xpath = './/img[contains(@class, "avatar")]/@src'
link_xpath = './/small[@class="time"]//a'
title_xpath = './/span[contains(@class, "username")]'
content_xpath = './/p[contains(@class, "tweet-text")]'
@ -57,6 +58,8 @@ def response(resp):
try:
link = tweet.xpath(link_xpath)[0]
content = extract_text(tweet.xpath(content_xpath)[0])
img_src = tweet.xpath(avatar_xpath)[0]
img_src = img_src.replace('_bigger', '_normal')
except Exception:
continue
@ -71,12 +74,14 @@ def response(resp):
results.append({'url': url,
'title': title,
'content': content,
'img_src': img_src,
'publishedDate': publishedDate})
else:
# append result
results.append({'url': url,
'title': title,
'content': content})
'content': content,
'img_src': img_src})
# return results
return results