searx

commit: f5128c7cb96d7564cc7bebeae13a319557b84aaa
parent: 4cffd78650c3f1dfce413ae0a1cd0453ebe6f277
Author: Alexandre Flament <alex@al-f.net>
Date:   Sun, 12 Feb 2017 14:58:49 +0100

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

Diffstat:
M
searx/engines/bing_news.py
5
++---
M
searx/engines/qwant.py
19
++++++++++++++++---
M
searx/engines/twitter.py
7
++++++-
M
tests/unit/engines/test_bing_news.py
6
+++---

4 files changed, 27 insertions(+), 10 deletions(-)
diff --git a/searx/engines/bing_news.py b/searx/engines/bing_news.py
@@ -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,
diff --git a/searx/engines/qwant.py b/searx/engines/qwant.py
@@ -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,
+                            '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})
+                            'content': content,
+                            'img_src': img_src})
 
     return results
 
diff --git a/searx/engines/twitter.py b/searx/engines/twitter.py
@@ -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
diff --git a/tests/unit/engines/test_bing_news.py b/tests/unit/engines/test_bing_news.py
@@ -81,11 +81,11 @@ class TestBingNewsEngine(SearxTestCase):
         self.assertEqual(results[0]['title'], 'Title')
         self.assertEqual(results[0]['url'], 'http://url.of.article/')
         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]['url'], 'http://another.url.of.article/')
         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" ?>
 <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]['url'], 'http://another.url.of.article/')
         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" ?>
 <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">