OwlBurst/Ponysearch
1
0
Fork 0
forked from Ponysearch/Ponysearch
Code Pull requests 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
Show stats 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 # append result
if thumbnail is not None: if thumbnail is not None:
results.append({'template': 'videos.html', results.append({'url': url,
'url': url,
'title': title, 'title': title,
'publishedDate': publishedDate, 'publishedDate': publishedDate,
'content': content, 'content': content,
'thumbnail': thumbnail}) 'img_src': thumbnail})
else: else:
results.append({'url': url, results.append({'url': url,
'title': title, 'title': title,

21
searx/engines/qwant.py
View file

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

7
searx/engines/twitter.py
View file

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

6
tests/unit/engines/test_bing_news.py
View file

@ -81,11 +81,11 @@ class TestBingNewsEngine(SearxTestCase):
self.assertEqual(results[0]['title'], 'Title') self.assertEqual(results[0]['title'], 'Title')
self.assertEqual(results[0]['url'], 'http://url.of.article/') self.assertEqual(results[0]['url'], 'http://url.of.article/')
self.assertEqual(results[0]['content'], 'Article Content') self.assertEqual(results[0]['content'], 'Article Content')
self.assertEqual(results[0]['thumbnail'], 'https://www.bing.com/th?id=ON.13371337133713371337133713371337') self.assertEqual(results[0]['img_src'], 'https://www.bing.com/th?id=ON.13371337133713371337133713371337')
self.assertEqual(results[1]['title'], 'Another Title') self.assertEqual(results[1]['title'], 'Another Title')
self.assertEqual(results[1]['url'], 'http://another.url.of.article/') self.assertEqual(results[1]['url'], 'http://another.url.of.article/')
self.assertEqual(results[1]['content'], 'Another Article Content') self.assertEqual(results[1]['content'], 'Another Article Content')
self.assertNotIn('thumbnail', results[1]) self.assertNotIn('img_src', results[1])
html = """<?xml version="1.0" encoding="utf-8" ?> html = """<?xml version="1.0" encoding="utf-8" ?>
<rss version="2.0" xmlns:News="https://www.bing.com:443/news/search?q=python&amp;setmkt=en-US&amp;first=1&amp;format=RSS"> <rss version="2.0" xmlns:News="https://www.bing.com:443/news/search?q=python&amp;setmkt=en-US&amp;first=1&amp;format=RSS">
@ -120,7 +120,7 @@ class TestBingNewsEngine(SearxTestCase):
self.assertEqual(results[0]['title'], 'Title') self.assertEqual(results[0]['title'], 'Title')
self.assertEqual(results[0]['url'], 'http://another.url.of.article/') self.assertEqual(results[0]['url'], 'http://another.url.of.article/')
self.assertEqual(results[0]['content'], 'Article Content') self.assertEqual(results[0]['content'], 'Article Content')
self.assertEqual(results[0]['thumbnail'], 'http://another.bing.com/image') self.assertEqual(results[0]['img_src'], 'http://another.bing.com/image')
html = """<?xml version="1.0" encoding="utf-8" ?> html = """<?xml version="1.0" encoding="utf-8" ?>
<rss version="2.0" xmlns:News="https://www.bing.com:443/news/search?q=python&amp;setmkt=en-US&amp;first=1&amp;format=RSS"> <rss version="2.0" xmlns:News="https://www.bing.com:443/news/search?q=python&amp;setmkt=en-US&amp;first=1&amp;format=RSS">