free
/
searx
关注 1
点赞 0
派生 0
代码 工单 0 合并请求 0 版本发布 11 百科 动态
浏览代码

Merge pull request #139 from dalf/master 

pep8 : engines
Adam Tauber 11 年前
父节点
611f4e2a86 7c13d630e4
当前提交
9517f7a6e7
共有 24 个文件被更改，包括 277 次插入 和 187 次删除
分列视图 显示文件统计
  1. 8
    7
      searx/engines/bing.py
  2. 11
    9
      searx/engines/bing_images.py
  3. 10
    9
      searx/engines/bing_news.py
  4. 1
    1
      searx/engines/currency_convert.py
  5. 2
    3
      searx/engines/dailymotion.py
  6. 2
    2
      searx/engines/deviantart.py
  7. 7
    5
      searx/engines/duckduckgo.py
  8. 46
    31
      searx/engines/duckduckgo_definitions.py
  9. 1
    1
      searx/engines/dummy.py
  10. 6
    5
      searx/engines/faroo.py
  11. 2
    2
      searx/engines/generalfile.py
  12. 2
    2
      searx/engines/github.py
  13. 4
    3
      searx/engines/google_images.py
  14. 4
    3
      searx/engines/google_news.py
  15. 15
    15
      searx/engines/openstreetmap.py
  16. 3
    3
      searx/engines/piratebay.py
  17. 2
    2
      searx/engines/soundcloud.py
  18. 4
    4
      searx/engines/stackoverflow.py
  19. 2
    2
      searx/engines/twitter.py
  20. 7
    5
      searx/engines/vimeo.py
  21. 122
    59
      searx/engines/wikidata.py
  22. 6
    5
      searx/engines/yacy.py
  23. 8
    7
      searx/engines/yahoo.py
  24. 2
    2
      searx/engines/youtube.py

+ 8
- 7
searx/engines/bing.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Bing (Web)
2 
-#
2 
+#
3 3 
 # @website     https://www.bing.com
4 
-# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
5 
-#
4 
+# @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
5 
+#              max. 5000 query/month
6 
+#
6 7 
 # @using-api   no (because of query limit)
7 8 
 # @results     HTML (using search portal)
8 9 
 # @stable      no (HTML can change)
 
@@ -58,8 +59,8 @@ def response(resp):
58 59 
         content = escape(' '.join(result.xpath('.//p//text()')))
59 60
60 61 
         # append result
61 
-        results.append({'url': url,
62 
-                        'title': title,
62 
+        results.append({'url': url,
63 
+                        'title': title,
63 64 
                         'content': content})
64 65
65 66 
     # return results if something is found
 
@@ -74,8 +75,8 @@ def response(resp):
74 75 
         content = escape(' '.join(result.xpath('.//p//text()')))
75 76
76 77 
         # append result
77 
-        results.append({'url': url,
78 
-                        'title': title,
78 
+        results.append({'url': url,
79 
+                        'title': title,
79 80 
                         'content': content})
80 81
81 82 
     # return results

+ 11
- 9
searx/engines/bing_images.py 查看文件 

@@ -1,17 +1,19 @@
1 1 
 ## Bing (Images)
2 
-#
2 
+#
3 3 
 # @website     https://www.bing.com/images
4 
-# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
5 
-#
4 
+# @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
5 
+#              max. 5000 query/month
6 
+#
6 7 
 # @using-api   no (because of query limit)
7 8 
 # @results     HTML (using search portal)
8 9 
 # @stable      no (HTML can change)
9 10 
 # @parse       url, title, img_src
10 11 
 #
11 
-# @todo        currently there are up to 35 images receive per page, because bing does not parse count=10. limited response to 10 images
12 
+# @todo        currently there are up to 35 images receive per page,
13 
+#              because bing does not parse count=10.
14 
+#              limited response to 10 images
12 15
13 16 
 from urllib import urlencode
14 
-from cgi import escape
15 17 
 from lxml import html
16 18 
 from yaml import load
17 19 
 import re
 
@@ -51,15 +53,15 @@ def response(resp):
51 53 
     dom = html.fromstring(resp.content)
52 54
53 55 
     # init regex for yaml-parsing
54 
-    p = re.compile( '({|,)([a-z]+):(")')
56 
+    p = re.compile('({|,)([a-z]+):(")')
55 57
56 58 
     # parse results
57 59 
     for result in dom.xpath('//div[@class="dg_u"]'):
58 60 
         link = result.xpath('./a')[0]
59 61
60 62 
         # parse yaml-data (it is required to add a space, to make it parsable)
61 
-        yaml_data = load(p.sub( r'\1\2: \3', link.attrib.get('m')))
62 
-
63 
+        yaml_data = load(p.sub(r'\1\2: \3', link.attrib.get('m')))
64 
+
63 65 
         title = link.attrib.get('t1')
64 66 
         #url = 'http://' + link.attrib.get('t3')
65 67 
         url = yaml_data.get('surl')
 
@@ -69,7 +71,7 @@ def response(resp):
69 71 
         results.append({'template': 'images.html',
70 72 
                         'url': url,
71 73 
                         'title': title,
72 
-                        'content': '',
74 
+                        'content': '',
73 75 
                         'img_src': img_src})
74 76
75 77 
         # TODO stop parsing if 10 images are found

+ 10
- 9
searx/engines/bing_news.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Bing (News)
2 
-#
2 
+#
3 3 
 # @website     https://www.bing.com/news
4 
-# @provide-api yes (http://datamarket.azure.com/dataset/bing/search), max. 5000 query/month
5 
-#
4 
+# @provide-api yes (http://datamarket.azure.com/dataset/bing/search),
5 
+#              max. 5000 query/month
6 
+#
6 7 
 # @using-api   no (because of query limit)
7 8 
 # @results     HTML (using search portal)
8 9 
 # @stable      no (HTML can change)
 
@@ -57,12 +58,12 @@ def response(resp):
57 58 
         url = link.attrib.get('href')
58 59 
         title = ' '.join(link.xpath('.//text()'))
59 60 
         contentXPath = result.xpath('.//div[@class="sn_txt"]/div//span[@class="sn_snip"]//text()')
60 
-        if contentXPath != None:
61 
+        if contentXPath is not None:
61 62 
             content = escape(' '.join(contentXPath))
62 
-
63 
+
63 64 
         # parse publishedDate
64 65 
         publishedDateXPath = result.xpath('.//div[@class="sn_txt"]/div//span[contains(@class,"sn_ST")]//span[contains(@class,"sn_tm")]//text()')
65 
-        if publishedDateXPath != None:
66 
+        if publishedDateXPath is not None:
66 67 
             publishedDate = escape(' '.join(publishedDateXPath))
67 68
68 69 
         if re.match("^[0-9]+ minute(s|) ago$", publishedDate):
 
@@ -89,10 +90,10 @@ def response(resp):
89 90 
             except TypeError:
90 91 
                 # FIXME
91 92 
                 publishedDate = datetime.now()
92 
-
93 
+
93 94 
         # append result
94 
-        results.append({'url': url,
95 
-                        'title': title,
95 
+        results.append({'url': url,
96 
+                        'title': title,
96 97 
                         'publishedDate': publishedDate,
97 98 
                         'content': content})
98 99

+ 1
- 1
searx/engines/currency_convert.py 查看文件 

@@ -55,6 +55,6 @@ def response(resp):
55 55 
         resp.search_params['to'].lower()
56 56 
     )
57 57
58 
-    results.append({'answer' : answer, 'url': url})
58 
+    results.append({'answer': answer, 'url': url})
59 59
60 60 
     return results

+ 2
- 3
searx/engines/dailymotion.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Dailymotion (Videos)
2 
-#
2 
+#
3 3 
 # @website     https://www.dailymotion.com
4 4 
 # @provide-api yes (http://www.dailymotion.com/developer)
5 
-#
5 
+#
6 6 
 # @using-api   yes
7 7 
 # @results     JSON
8 8 
 # @stable      yes
 
@@ -12,7 +12,6 @@
12 12
13 13 
 from urllib import urlencode
14 14 
 from json import loads
15 
-from lxml import html
16 15
17 16 
 # engine dependent config
18 17 
 categories = ['videos']

+ 2
- 2
searx/engines/deviantart.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Deviantart (Images)
2 
-#
2 
+#
3 3 
 # @website     https://www.deviantart.com/
4 4 
 # @provide-api yes (https://www.deviantart.com/developers/) (RSS)
5 
-#
5 
+#
6 6 
 # @using-api   no (TODO, rewrite to api)
7 7 
 # @results     HTML
8 8 
 # @stable      no (HTML can change)

+ 7
- 5
searx/engines/duckduckgo.py 查看文件 

@@ -1,15 +1,17 @@
1 1 
 ## DuckDuckGo (Web)
2 
-#
2 
+#
3 3 
 # @website     https://duckduckgo.com/
4 
-# @provide-api yes (https://duckduckgo.com/api), but not all results from search-site
5 
-#
4 
+# @provide-api yes (https://duckduckgo.com/api),
5 
+#              but not all results from search-site
6 
+#
6 7 
 # @using-api   no
7 8 
 # @results     HTML (using search portal)
8 9 
 # @stable      no (HTML can change)
9 10 
 # @parse       url, title, content
10 11 
 #
11 12 
 # @todo        rewrite to api
12 
-# @todo        language support (the current used site does not support language-change)
13 
+# @todo        language support
14 
+#              (the current used site does not support language-change)
13 15
14 16 
 from urllib import urlencode
15 17 
 from lxml.html import fromstring
 
@@ -37,7 +39,7 @@ def request(query, params):
37 39 
     if params['language'] == 'all':
38 40 
         locale = 'en-us'
39 41 
     else:
40 
-        locale = params['language'].replace('_','-').lower()
42 
+        locale = params['language'].replace('_', '-').lower()
41 43
42 44 
     params['url'] = url.format(
43 45 
         query=urlencode({'q': query, 'kl': locale}),

+ 46
- 31
searx/engines/duckduckgo_definitions.py 查看文件 

@@ -3,21 +3,25 @@ from urllib import urlencode
3 3 
 from lxml import html
4 4 
 from searx.engines.xpath import extract_text
5 5
6 
-url = 'https://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1&d=1'
6 
+url = 'https://api.duckduckgo.com/'\
7 
+    + '?{query}&format=json&pretty=0&no_redirect=1&d=1'
8 
+
7 9
8 10 
 def result_to_text(url, text, htmlResult):
9 11 
     # TODO : remove result ending with "Meaning" or "Category"
10 12 
     dom = html.fromstring(htmlResult)
11 13 
     a = dom.xpath('//a')
12 
-    if len(a)>=1:
14 
+    if len(a) >= 1:
13 15 
         return extract_text(a[0])
14 16 
     else:
15 17 
         return text
16 18
19 
+
17 20 
 def html_to_text(htmlFragment):
18 21 
     dom = html.fromstring(htmlFragment)
19 22 
     return extract_text(dom)
20 23
24 
+
21 25 
 def request(query, params):
22 26 
     # TODO add kl={locale}
23 27 
     params['url'] = url.format(query=urlencode({'q': query}))
 
@@ -38,16 +42,15 @@ def response(resp):
38 42 
     # add answer if there is one
39 43 
     answer = search_res.get('Answer', '')
40 44 
     if answer != '':
41 
-        results.append({ 'answer' : html_to_text(answer) })
45 
+        results.append({'answer': html_to_text(answer)})
42 46
43 47 
     # add infobox
44 48 
     if 'Definition' in search_res:
45 
-        content = content + search_res.get('Definition', '')
49 
+        content = content + search_res.get('Definition', '')
46 50
47 51 
     if 'Abstract' in search_res:
48 52 
         content = content + search_res.get('Abstract', '')
49 53
50 
-
51 54 
     # image
52 55 
     image = search_res.get('Image', '')
53 56 
     image = None if image == '' else image
 
@@ -55,29 +58,35 @@ def response(resp):
55 58 
     # attributes
56 59 
     if 'Infobox' in search_res:
57 60 
         infobox = search_res.get('Infobox', None)
58 
-        if  'content' in infobox:
61 
+        if 'content' in infobox:
59 62 
             for info in infobox.get('content'):
60 
-                attributes.append({'label': info.get('label'), 'value': info.get('value')})
63 
+                attributes.append({'label': info.get('label'),
64 
+                                  'value': info.get('value')})
61 65
62 66 
     # urls
63 67 
     for ddg_result in search_res.get('Results', []):
64 68 
         if 'FirstURL' in ddg_result:
65 69 
             firstURL = ddg_result.get('FirstURL', '')
66 70 
             text = ddg_result.get('Text', '')
67 
-            urls.append({'title':text, 'url':firstURL})
68 
-            results.append({'title':heading, 'url': firstURL})
71 
+            urls.append({'title': text, 'url': firstURL})
72 
+            results.append({'title': heading, 'url': firstURL})
69 73
70 74 
     # related topics
71 75 
     for ddg_result in search_res.get('RelatedTopics', None):
72 76 
         if 'FirstURL' in ddg_result:
73 
-            suggestion = result_to_text(ddg_result.get('FirstURL', None), ddg_result.get('Text', None), ddg_result.get('Result', None))
77 
+            suggestion = result_to_text(ddg_result.get('FirstURL', None),
78 
+                                        ddg_result.get('Text', None),
79 
+                                        ddg_result.get('Result', None))
74 80 
             if suggestion != heading:
75 81 
                 results.append({'suggestion': suggestion})
76 82 
         elif 'Topics' in ddg_result:
77 83 
             suggestions = []
78 
-            relatedTopics.append({ 'name' : ddg_result.get('Name', ''), 'suggestions': suggestions })
84 
+            relatedTopics.append({'name': ddg_result.get('Name', ''),
85 
+                                 'suggestions': suggestions})
79 86 
             for topic_result in ddg_result.get('Topics', []):
80 
-                suggestion = result_to_text(topic_result.get('FirstURL', None), topic_result.get('Text', None), topic_result.get('Result', None))
87 
+                suggestion = result_to_text(topic_result.get('FirstURL', None),
88 
+                                            topic_result.get('Text', None),
89 
+                                            topic_result.get('Result', None))
81 90 
                 if suggestion != heading:
82 91 
                     suggestions.append(suggestion)
83 92 
 
@@ -86,21 +95,26 @@ def response(resp):
86 95 
     if abstractURL != '':
87 96 
         # add as result ? problem always in english
88 97 
         infobox_id = abstractURL
89 
-        urls.append({'title': search_res.get('AbstractSource'), 'url': abstractURL})
98 
+        urls.append({'title': search_res.get('AbstractSource'),
99 
+                    'url': abstractURL})
90 100
91 101 
     # definition
92 102 
     definitionURL = search_res.get('DefinitionURL', '')
93 103 
     if definitionURL != '':
94 104 
         # add as result ? as answer ? problem always in english
95 105 
         infobox_id = definitionURL
96 
-        urls.append({'title': search_res.get('DefinitionSource'), 'url': definitionURL})
106 
+        urls.append({'title': search_res.get('DefinitionSource'),
107 
+                    'url': definitionURL})
97 108
98 109 
     # entity
99 110 
     entity = search_res.get('Entity', None)
100 
-    # TODO continent / country / department / location / waterfall / mountain range : link to map search, get weather, near by locations
111 
+    # TODO continent / country / department / location / waterfall /
112 
+    #      mountain range :
113 
+    #      link to map search, get weather, near by locations
101 114 
     # TODO musician : link to music search
102 115 
     # TODO concert tour : ??
103 
-    # TODO film / actor / television  / media franchise : links to IMDB / rottentomatoes (or scrap result)
116 
+    # TODO film / actor / television  / media franchise :
117 
+    #      links to IMDB / rottentomatoes (or scrap result)
104 118 
     # TODO music : link tu musicbrainz / last.fm
105 119 
     # TODO book : ??
106 120 
     # TODO artist / playwright : ??
 
@@ -114,24 +128,25 @@ def response(resp):
114 128 
     # TODO programming language : ??
115 129 
     # TODO file format : ??
116 130
117 
-    if len(heading)>0:
131 
+    if len(heading) > 0:
118 132 
         # TODO get infobox.meta.value where .label='article_title'
119 
-        if image==None and len(attributes)==0 and len(urls)==1 and len(relatedTopics)==0 and len(content)==0:
133 
+        if image is None and len(attributes) == 0 and len(urls) == 1 and\
134 
+           len(relatedTopics) == 0 and len(content) == 0:
120 135 
             results.append({
121 
-                    'url': urls[0]['url'],
122 
-                    'title': heading,
123 
-                    'content': content
124 
-                    })
136 
+                           'url': urls[0]['url'],
137 
+                           'title': heading,
138 
+                           'content': content
139 
+                           })
125 140 
         else:
126 141 
             results.append({
127 
-                    'infobox': heading,
128 
-                    'id': infobox_id,
129 
-                    'entity': entity,
130 
-                    'content': content,
131 
-                    'img_src' : image,
132 
-                    'attributes': attributes,
133 
-                    'urls': urls,
134 
-                    'relatedTopics': relatedTopics
135 
-                    })
142 
+                           'infobox': heading,
143 
+                           'id': infobox_id,
144 
+                           'entity': entity,
145 
+                           'content': content,
146 
+                           'img_src': image,
147 
+                           'attributes': attributes,
148 
+                           'urls': urls,
149 
+                           'relatedTopics': relatedTopics
150 
+                           })
136 151
137 152 
     return results

+ 1
- 1
searx/engines/dummy.py 查看文件 

@@ -1,5 +1,5 @@
1 1 
 ## Dummy
2 
-#
2 
+#
3 3 
 # @results     empty array
4 4 
 # @stable      yes
5 5

+ 6
- 5
searx/engines/faroo.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Faroo (Web, News)
2 
-#
2 
+#
3 3 
 # @website     http://www.faroo.com
4 4 
 # @provide-api yes (http://www.faroo.com/hp/api/api.html), require API-key
5 
-#
5 
+#
6 6 
 # @using-api   yes
7 7 
 # @results     JSON
8 8 
 # @stable      yes
 
@@ -24,9 +24,10 @@ api_key = None
24 24 
 url = 'http://www.faroo.com/'
25 25 
 search_url = url + 'api?{query}&start={offset}&length={number_of_results}&l={language}&src={categorie}&i=false&f=json&key={api_key}'
26 26
27 
-search_category = {'general': 'web',
27 
+search_category = {'general': 'web',
28 28 
                 'news': 'news'}
29 29
30 
+
30 31 
 # do search-request
31 32 
 def request(query, params):
32 33 
     offset = (params['pageno']-1) * number_of_results + 1
 
@@ -48,7 +49,7 @@ def request(query, params):
48 49 
                                       query=urlencode({'q': query}),
49 50 
                                       language=language,
50 51 
                                       categorie=categorie,
51 
-                                      api_key=api_key )
52 
+                                      api_key=api_key)
52 53
53 54 
     # using searx User-Agent
54 55 
     params['headers']['User-Agent'] = searx_useragent()
 
@@ -101,7 +102,7 @@ def response(resp):
101 102 
             results.append({'template': 'images.html',
102 103 
                             'url': result['url'],
103 104 
                             'title': result['title'],
104 
-                            'content': result['kwic'],
105 
+                            'content': result['kwic'],
105 106 
                             'img_src': result['iurl']})
106 107
107 108 
     # return results

+ 2
- 2
searx/engines/generalfile.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## General Files (Files)
2 
-#
2 
+#
3 3 
 # @website     http://www.general-files.org
4 4 
 # @provide-api no (nothing found)
5 
-#
5 
+#
6 6 
 # @using-api   no (because nothing found)
7 7 
 # @results     HTML (using search portal)
8 8 
 # @stable      no (HTML can change)

+ 2
- 2
searx/engines/github.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Github (It)
2 
-#
2 
+#
3 3 
 # @website     https://github.com/
4 4 
 # @provide-api yes (https://developer.github.com/v3/)
5 
-#
5 
+#
6 6 
 # @using-api   yes
7 7 
 # @results     JSON
8 8 
 # @stable      yes (using api)

+ 4
- 3
searx/engines/google_images.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Google (Images)
2 
-#
2 
+#
3 3 
 # @website     https://www.google.com
4 
-# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
5 
-#
4 
+# @provide-api yes (https://developers.google.com/web-search/docs/),
5 
+#              deprecated!
6 
+#
6 7 
 # @using-api   yes
7 8 
 # @results     JSON
8 9 
 # @stable      yes (but deprecated)

+ 4
- 3
searx/engines/google_news.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Google (News)
2 
-#
2 
+#
3 3 
 # @website     https://www.google.com
4 
-# @provide-api yes (https://developers.google.com/web-search/docs/), deprecated!
5 
-#
4 
+# @provide-api yes (https://developers.google.com/web-search/docs/),
5 
+#              deprecated!
6 
+#
6 7 
 # @using-api   yes
7 8 
 # @results     JSON
8 9 
 # @stable      yes (but deprecated)

+ 15
- 15
searx/engines/openstreetmap.py 查看文件 

@@ -39,16 +39,16 @@ def response(resp):
39 39 
         url = result_base_url.format(osm_type=osm_type,
40 40 
                                      osm_id=r['osm_id'])
41 41
42 
-        osm = {'type':osm_type,
43 
-               'id':r['osm_id']}
42 
+        osm = {'type': osm_type,
43 
+               'id': r['osm_id']}
44 44
45 
-        geojson =  r.get('geojson')
45 
+        geojson = r.get('geojson')
46 46
47 47 
         # if no geojson is found and osm_type is a node, add geojson Point
48 48 
         if not geojson and\
49 49 
            osm_type == 'node':
50 
-            geojson = {u'type':u'Point',
51 
-                       u'coordinates':[r['lon'],r['lat']]}
50 
+            geojson = {u'type': u'Point',
51 
+                       u'coordinates': [r['lon'], r['lat']]}
52 52
53 53 
         address_raw = r.get('address')
54 54 
         address = {}
 
@@ -59,20 +59,20 @@ def response(resp):
59 59 
            r['class'] == 'tourism' or\
60 60 
            r['class'] == 'leisure':
61 61 
             if address_raw.get('address29'):
62 
-                address = {'name':address_raw.get('address29')}
62 
+                address = {'name': address_raw.get('address29')}
63 63 
             else:
64 
-                address = {'name':address_raw.get(r['type'])}
64 
+                address = {'name': address_raw.get(r['type'])}
65 65
66 66 
         # add rest of adressdata, if something is already found
67 67 
         if address.get('name'):
68 
-            address.update({'house_number':address_raw.get('house_number'),
69 
-                       'road':address_raw.get('road'),
70 
-                       'locality':address_raw.get('city',
71 
-                                  address_raw.get('town',
72 
-                                  address_raw.get('village'))),
73 
-                       'postcode':address_raw.get('postcode'),
74 
-                       'country':address_raw.get('country'),
75 
-                       'country_code':address_raw.get('country_code')})
68 
+            address.update({'house_number': address_raw.get('house_number'),
69 
+                           'road': address_raw.get('road'),
70 
+                           'locality': address_raw.get('city',
71 
+                                       address_raw.get('town',
72 
+                                       address_raw.get('village'))),
73 
+                           'postcode': address_raw.get('postcode'),
74 
+                           'country': address_raw.get('country'),
75 
+                           'country_code': address_raw.get('country_code')})
76 76 
         else:
77 77 
             address = None
78 78

+ 3
- 3
searx/engines/piratebay.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Piratebay (Videos, Music, Files)
2 
-#
2 
+#
3 3 
 # @website     https://thepiratebay.se
4 4 
 # @provide-api no (nothing found)
5 
-#
5 
+#
6 6 
 # @using-api   no
7 7 
 # @results     HTML (using search portal)
8 8 
 # @stable      yes (HTML can change)
 
@@ -23,7 +23,7 @@ url = 'https://thepiratebay.se/'
23 23 
 search_url = url + 'search/{search_term}/{pageno}/99/{search_type}'
24 24
25 25 
 # piratebay specific type-definitions
26 
-search_types = {'files': '0',
26 
+search_types = {'files': '0',
27 27 
                 'music': '100',
28 28 
                 'videos': '200'}
29 29

+ 2
- 2
searx/engines/soundcloud.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Soundcloud (Music)
2 
-#
2 
+#
3 3 
 # @website     https://soundcloud.com
4 4 
 # @provide-api yes (https://developers.soundcloud.com/)
5 
-#
5 
+#
6 6 
 # @using-api   yes
7 7 
 # @results     JSON
8 8 
 # @stable      yes

+ 4
- 4
searx/engines/stackoverflow.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Stackoverflow (It)
2 
-#
2 
+#
3 3 
 # @website     https://stackoverflow.com/
4 4 
 # @provide-api not clear (https://api.stackexchange.com/docs/advanced-search)
5 
-#
5 
+#
6 6 
 # @using-api   no
7 7 
 # @results     HTML
8 8 
 # @stable      no (HTML can change)
 
@@ -50,8 +50,8 @@ def response(resp):
50 50 
         content = escape(' '.join(result.xpath(content_xpath)))
51 51
52 52 
         # append result
53 
-        results.append({'url': href,
54 
-                        'title': title,
53 
+        results.append({'url': href,
54 
+                        'title': title,
55 55 
                         'content': content})
56 56
57 57 
     # return results

+ 2
- 2
searx/engines/twitter.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Twitter (Social media)
2 
-#
2 
+#
3 3 
 # @website     https://www.bing.com/news
4 4 
 # @provide-api yes (https://dev.twitter.com/docs/using-search)
5 
-#
5 
+#
6 6 
 # @using-api   no
7 7 
 # @results     HTML (using search portal)
8 8 
 # @stable      no (HTML can change)

+ 7
- 5
searx/engines/vimeo.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Vimeo (Videos)
2 
-#
2 
+#
3 3 
 # @website     https://vimeo.com/
4 
-# @provide-api yes (http://developer.vimeo.com/api), they have a maximum count of queries/hour
5 
-#
4 
+# @provide-api yes (http://developer.vimeo.com/api),
5 
+#              they have a maximum count of queries/hour
6 
+#
6 7 
 # @using-api   no (TODO, rewrite to api)
7 8 
 # @results     HTML (using search portal)
8 9 
 # @stable      no (HTML can change)
 
@@ -35,11 +36,12 @@ publishedDate_xpath = './/p[@class="meta"]//attribute::datetime'
35 36
36 37 
 # do search-request
37 38 
 def request(query, params):
38 
-    params['url'] = search_url.format(pageno=params['pageno'] ,
39 
+    params['url'] = search_url.format(pageno=params['pageno'],
39 40 
                                       query=urlencode({'q': query}))
40 41
41 42 
     # TODO required?
42 
-    params['cookies']['__utma'] = '00000000.000#0000000.0000000000.0000000000.0000000000.0'
43 
+    params['cookies']['__utma'] =\
44 
+        '00000000.000#0000000.0000000000.0000000000.0000000000.0'
43 45
44 46 
     return params
45 47

+ 122
- 59
searx/engines/wikidata.py 查看文件 

@@ -2,13 +2,25 @@ import json
2 2 
 from requests import get
3 3 
 from urllib import urlencode
4 4
5 
-resultCount=1
6 
-urlSearch = 'https://www.wikidata.org/w/api.php?action=query&list=search&format=json&srnamespace=0&srprop=sectiontitle&{query}'
7 
-urlDetail = 'https://www.wikidata.org/w/api.php?action=wbgetentities&format=json&props=labels%7Cinfo%7Csitelinks%7Csitelinks%2Furls%7Cdescriptions%7Cclaims&{query}'
8 
-urlMap = 'https://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
5 
+result_count = 1
6 
+wikidata_host = 'https://www.wikidata.org'
7 
+wikidata_api = wikidata_host + '/w/api.php'
8 
+url_search = wikidata_api \
9 
+    + '?action=query&list=search&format=json'\
10 
+    + '&srnamespace=0&srprop=sectiontitle&{query}'
11 
+url_detail = wikidata_api\
12 
+    + '?action=wbgetentities&format=json'\
13 
+    + '&props=labels%7Cinfo%7Csitelinks'\
14 
+    + '%7Csitelinks%2Furls%7Cdescriptions%7Cclaims'\
15 
+    + '&{query}'
16 
+url_map = 'https://www.openstreetmap.org/'\
17 
+    + '?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M'
18 
+
9 19
10 20 
 def request(query, params):
11 
-    params['url'] = urlSearch.format(query=urlencode({'srsearch': query, 'srlimit': resultCount}))
21 
+    params['url'] = url_search.format(
22 
+        query=urlencode({'srsearch': query,
23 
+                        'srlimit': result_count}))
12 24 
     return params
13 25
14 26 
 
@@ -23,7 +35,8 @@ def response(resp):
23 35 
     language = resp.search_params['language'].split('_')[0]
24 36 
     if language == 'all':
25 37 
         language = 'en'
26 
-    url = urlDetail.format(query=urlencode({'ids': '|'.join(wikidata_ids), 'languages': language + '|en'}))
38 
+    url = url_detail.format(query=urlencode({'ids': '|'.join(wikidata_ids),
39 
+                                            'languages': language + '|en'}))
27 40
28 41 
     htmlresponse = get(url)
29 42 
     jsonresponse = json.loads(htmlresponse.content)
 
@@ -32,6 +45,7 @@ def response(resp):
32 45
33 46 
     return results
34 47
48 
+
35 49 
 def getDetail(jsonresponse, wikidata_id, language):
36 50 
     results = []
37 51 
     urls = []
 
@@ -40,60 +54,103 @@ def getDetail(jsonresponse, wikidata_id, language):
40 54 
     result = jsonresponse.get('entities', {}).get(wikidata_id, {})
41 55
42 56 
     title = result.get('labels', {}).get(language, {}).get('value', None)
43 
-    if title == None:
57 
+    if title is None:
44 58 
         title = result.get('labels', {}).get('en', {}).get('value', None)
45 
-    if title == None:
59 
+    if title is None:
46 60 
         return results
47 61
48 
-    description = result.get('descriptions', {}).get(language, {}).get('value', None)
49 
-    if description == None:
50 
-        description = result.get('descriptions', {}).get('en', {}).get('value', '')
62 
+    description = result\
63 
+        .get('descriptions', {})\
64 
+        .get(language, {})\
65 
+        .get('value', None)
66 
+
67 
+    if description is None:
68 
+        description = result\
69 
+            .get('descriptions', {})\
70 
+            .get('en', {})\
71 
+            .get('value', '')
51 72
52 73 
     claims = result.get('claims', {})
53 74 
     official_website = get_string(claims, 'P856', None)
54 
-    if official_website != None:
55 
-        urls.append({ 'title' : 'Official site', 'url': official_website })
56 
-        results.append({ 'title': title, 'url' : official_website })
75 
+    if official_website is not None:
76 
+        urls.append({'title': 'Official site', 'url': official_website})
77 
+        results.append({'title': title, 'url': official_website})
57 78
58 79 
     wikipedia_link_count = 0
59 80 
     if language != 'en':
60 
-        wikipedia_link_count += add_url(urls, 'Wikipedia (' + language + ')', get_wikilink(result, language + 'wiki'))
81 
+        wikipedia_link_count += add_url(urls,
82 
+                                        'Wikipedia (' + language + ')',
83 
+                                        get_wikilink(result, language +
84 
+                                                     'wiki'))
61 85 
     wikipedia_en_link = get_wikilink(result, 'enwiki')
62 
-    wikipedia_link_count += add_url(urls, 'Wikipedia (en)', wikipedia_en_link)
86 
+    wikipedia_link_count += add_url(urls,
87 
+                                    'Wikipedia (en)',
88 
+                                    wikipedia_en_link)
63 89 
     if wikipedia_link_count == 0:
64 90 
         misc_language = get_wiki_firstlanguage(result, 'wiki')
65 
-        if misc_language != None:
66 
-            add_url(urls, 'Wikipedia (' + misc_language + ')', get_wikilink(result, misc_language + 'wiki'))
91 
+        if misc_language is not None:
92 
+            add_url(urls,
93 
+                    'Wikipedia (' + misc_language + ')',
94 
+                    get_wikilink(result, misc_language + 'wiki'))
67 95
68 96 
     if language != 'en':
69 
-        add_url(urls, 'Wiki voyage (' + language + ')', get_wikilink(result, language + 'wikivoyage'))
70 
-    add_url(urls, 'Wiki voyage (en)', get_wikilink(result, 'enwikivoyage'))
97 
+        add_url(urls,
98 
+                'Wiki voyage (' + language + ')',
99 
+                get_wikilink(result, language + 'wikivoyage'))
100 
+
101 
+    add_url(urls,
102 
+            'Wiki voyage (en)',
103 
+            get_wikilink(result, 'enwikivoyage'))
71 104
72 105 
     if language != 'en':
73 
-        add_url(urls, 'Wikiquote (' + language + ')', get_wikilink(result, language + 'wikiquote'))
74 
-    add_url(urls, 'Wikiquote (en)', get_wikilink(result, 'enwikiquote'))
106 
+        add_url(urls,
107 
+                'Wikiquote (' + language + ')',
108 
+                get_wikilink(result, language + 'wikiquote'))
75 109
76 
-    add_url(urls, 'Commons wiki', get_wikilink(result, 'commonswiki'))
110 
+    add_url(urls,
111 
+            'Wikiquote (en)',
112 
+            get_wikilink(result, 'enwikiquote'))
77 113
78 
-    add_url(urls, 'Location', get_geolink(claims, 'P625', None))
114 
+    add_url(urls,
115 
+            'Commons wiki',
116 
+            get_wikilink(result, 'commonswiki'))
79 117
80 
-    add_url(urls, 'Wikidata', 'https://www.wikidata.org/wiki/' + wikidata_id + '?uselang='+ language)
118 
+    add_url(urls,
119 
+            'Location',
120 
+            get_geolink(claims, 'P625', None))
121 
+
122 
+    add_url(urls,
123 
+            'Wikidata',
124 
+            'https://www.wikidata.org/wiki/'
125 
+            + wikidata_id + '?uselang=' + language)
81 126
82 127 
     musicbrainz_work_id = get_string(claims, 'P435')
83 
-    if musicbrainz_work_id != None:
84 
-        add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/work/' + musicbrainz_work_id)
128 
+    if musicbrainz_work_id is not None:
129 
+        add_url(urls,
130 
+                'MusicBrainz',
131 
+                'http://musicbrainz.org/work/'
132 
+                + musicbrainz_work_id)
85 133
86 134 
     musicbrainz_artist_id = get_string(claims, 'P434')
87 
-    if musicbrainz_artist_id != None:
88 
-        add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/artist/' + musicbrainz_artist_id)
135 
+    if musicbrainz_artist_id is not None:
136 
+        add_url(urls,
137 
+                'MusicBrainz',
138 
+                'http://musicbrainz.org/artist/'
139 
+                + musicbrainz_artist_id)
89 140
90 141 
     musicbrainz_release_group_id = get_string(claims, 'P436')
91 
-    if musicbrainz_release_group_id != None:
92 
-        add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/release-group/' + musicbrainz_release_group_id)
142 
+    if musicbrainz_release_group_id is not None:
143 
+        add_url(urls,
144 
+                'MusicBrainz',
145 
+                'http://musicbrainz.org/release-group/'
146 
+                + musicbrainz_release_group_id)
93 147
94 148 
     musicbrainz_label_id = get_string(claims, 'P966')
95 
-    if musicbrainz_label_id != None:
96 
-        add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/label/' + musicbrainz_label_id)
149 
+    if musicbrainz_label_id is not None:
150 
+        add_url(urls,
151 
+                'MusicBrainz',
152 
+                'http://musicbrainz.org/label/'
153 
+                + musicbrainz_label_id)
97 154
98 155 
     # musicbrainz_area_id = get_string(claims, 'P982')
99 156 
     # P1407 MusicBrainz series ID
 
@@ -102,42 +159,43 @@ def getDetail(jsonresponse, wikidata_id, language):
102 159 
     # P1407 MusicBrainz series ID
103 160
104 161 
     postal_code = get_string(claims, 'P281', None)
105 
-    if postal_code != None:
106 
-        attributes.append({'label' : 'Postal code(s)', 'value' : postal_code})
162 
+    if postal_code is not None:
163 
+        attributes.append({'label': 'Postal code(s)', 'value': postal_code})
107 164
108 165 
     date_of_birth = get_time(claims, 'P569', None)
109 
-    if date_of_birth != None:
110 
-        attributes.append({'label' : 'Date of birth', 'value' : date_of_birth})
166 
+    if date_of_birth is not None:
167 
+        attributes.append({'label': 'Date of birth', 'value': date_of_birth})
111 168
112 169 
     date_of_death = get_time(claims, 'P570', None)
113 
-    if date_of_death != None:
114 
-        attributes.append({'label' : 'Date of death', 'value' : date_of_death})
170 
+    if date_of_death is not None:
171 
+        attributes.append({'label': 'Date of death', 'value': date_of_death})
115 172
116 
-    if len(attributes)==0 and len(urls)==2 and len(description)==0:
173 
+    if len(attributes) == 0 and len(urls) == 2 and len(description) == 0:
117 174 
         results.append({
118 
-                'url': urls[0]['url'],
119 
-                'title': title,
120 
-                'content': description
121 
-                })
175 
+                       'url': urls[0]['url'],
176 
+                       'title': title,
177 
+                       'content': description
178 
+                       })
122 179 
     else:
123 180 
         results.append({
124 
-                'infobox' : title,
125 
-                'id' : wikipedia_en_link,
126 
-                'content' : description,
127 
-                'attributes' : attributes,
128 
-                'urls' : urls
129 
-                })
181 
+                       'infobox': title,
182 
+                       'id': wikipedia_en_link,
183 
+                       'content': description,
184 
+                       'attributes': attributes,
185 
+                       'urls': urls
186 
+                       })
130 187
131 188 
     return results
132 189
133 190
134 191 
 def add_url(urls, title, url):
135 
-    if url != None:
136 
-        urls.append({'title' : title, 'url' : url})
192 
+    if url is not None:
193 
+        urls.append({'title': title, 'url': url})
137 194 
         return 1
138 195 
     else:
139 196 
         return 0
140 197
198 
+
141 199 
 def get_mainsnak(claims, propertyName):
142 200 
     propValue = claims.get(propertyName, {})
143 201 
     if len(propValue) == 0:
 
@@ -157,7 +215,7 @@ def get_string(claims, propertyName, defaultValue=None):
157 215 
         mainsnak = e.get('mainsnak', {})
158 216
159 217 
         datavalue = mainsnak.get('datavalue', {})
160 
-        if datavalue != None:
218 
+        if datavalue is not None:
161 219 
             result.append(datavalue.get('value', ''))
162 220
163 221 
     if len(result) == 0:
 
@@ -177,7 +235,7 @@ def get_time(claims, propertyName, defaultValue=None):
177 235 
         mainsnak = e.get('mainsnak', {})
178 236
179 237 
         datavalue = mainsnak.get('datavalue', {})
180 
-        if datavalue != None:
238 
+        if datavalue is not None:
181 239 
             value = datavalue.get('value', '')
182 240 
             result.append(value.get('time', ''))
183 241 
 
@@ -190,7 +248,7 @@ def get_time(claims, propertyName, defaultValue=None):
190 248 
 def get_geolink(claims, propertyName, defaultValue=''):
191 249 
     mainsnak = get_mainsnak(claims, propertyName)
192 250
193 
-    if mainsnak == None:
251 
+    if mainsnak is None:
194 252 
         return defaultValue
195 253
196 254 
     datatype = mainsnak.get('datatype', '')
 
@@ -209,21 +267,25 @@ def get_geolink(claims, propertyName, defaultValue=''):
209 267 
     # 1 --> 6
210 268 
     # 0.016666666666667 --> 9
211 269 
     # 0.00027777777777778 --> 19
212 
-    # wolframalpha : quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}}
270 
+    # wolframalpha :
271 
+    # quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}}
213 272 
     # 14.1186-8.8322 x+0.625447 x^2
214 273 
     if precision < 0.0003:
215 274 
         zoom = 19
216 275 
     else:
217 276 
         zoom = int(15 - precision*8.8322 + precision*precision*0.625447)
218 277
219 
-    url = urlMap.replace('{latitude}', str(value.get('latitude',0))).replace('{longitude}', str(value.get('longitude',0))).replace('{zoom}', str(zoom))
278 
+    url = url_map\
279 
+        .replace('{latitude}', str(value.get('latitude', 0)))\
280 
+        .replace('{longitude}', str(value.get('longitude', 0)))\
281 
+        .replace('{zoom}', str(zoom))
220 282
221 283 
     return url
222 284
223 285
224 286 
 def get_wikilink(result, wikiid):
225 287 
     url = result.get('sitelinks', {}).get(wikiid, {}).get('url', None)
226 
-    if url == None:
288 
+    if url is None:
227 289 
         return url
228 290 
     elif url.startswith('http://'):
229 291 
         url = url.replace('http://', 'https://')
 
@@ -231,8 +293,9 @@ def get_wikilink(result, wikiid):
231 293 
         url = 'https:' + url
232 294 
     return url
233 295
296 
+
234 297 
 def get_wiki_firstlanguage(result, wikipatternid):
235 298 
     for k in result.get('sitelinks', {}).keys():
236 
-        if k.endswith(wikipatternid) and len(k)==(2+len(wikipatternid)):
299 
+        if k.endswith(wikipatternid) and len(k) == (2+len(wikipatternid)):
237 300 
             return k[0:2]
238 301 
     return None

+ 6
- 5
searx/engines/yacy.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Yacy (Web, Images, Videos, Music, Files)
2 
-#
2 
+#
3 3 
 # @website     http://yacy.net
4 
-# @provide-api yes (http://www.yacy-websuche.de/wiki/index.php/Dev:APIyacysearch)
5 
-#
4 
+# @provide-api yes
5 
+#              (http://www.yacy-websuche.de/wiki/index.php/Dev:APIyacysearch)
6 
+#
6 7 
 # @using-api   yes
7 8 
 # @results     JSON
8 9 
 # @stable      yes
 
@@ -16,7 +17,7 @@ from urllib import urlencode
16 17 
 from dateutil import parser
17 18
18 19 
 # engine dependent config
19 
-categories = ['general', 'images'] #TODO , 'music', 'videos', 'files'
20 
+categories = ['general', 'images']  # TODO , 'music', 'videos', 'files'
20 21 
 paging = True
21 22 
 language_support = True
22 23 
 number_of_results = 5
 
@@ -28,7 +29,7 @@ search_url = '/yacysearch.json?{query}&startRecord={offset}&maximumRecords={limi
28 29 
 # yacy specific type-definitions
29 30 
 search_types = {'general': 'text',
30 31 
                 'images': 'image',
31 
-                'files': 'app',
32 
+                'files': 'app',
32 33 
                 'music': 'audio',
33 34 
                 'videos': 'video'}
34 35

+ 8
- 7
searx/engines/yahoo.py 查看文件 

@@ -1,8 +1,9 @@
1 1 
 ## Yahoo (Web)
2 
-#
2 
+#
3 3 
 # @website     https://search.yahoo.com/web
4 
-# @provide-api yes (https://developer.yahoo.com/boss/search/), $0.80/1000 queries
5 
-#
4 
+# @provide-api yes (https://developer.yahoo.com/boss/search/),
5 
+#              $0.80/1000 queries
6 
+#
6 7 
 # @using-api   no (because pricing)
7 8 
 # @results     HTML (using search portal)
8 9 
 # @stable      no (HTML can change)
 
@@ -40,8 +41,8 @@ def parse_url(url_string):
40 41 
         if endpos > -1:
41 42 
             endpositions.append(endpos)
42 43
43 
-    if start==0 or len(endpositions) == 0:
44 
-        return url_string
44 
+    if start == 0 or len(endpositions) == 0:
45 
+        return url_string
45 46 
     else:
46 47 
         end = min(endpositions)
47 48 
         return unquote(url_string[start:end])
 
@@ -84,8 +85,8 @@ def response(resp):
84 85 
         content = extract_text(result.xpath(content_xpath)[0])
85 86
86 87 
         # append result
87 
-        results.append({'url': url,
88 
-                        'title': title,
88 
+        results.append({'url': url,
89 
+                        'title': title,
89 90 
                         'content': content})
90 91
91 92 
     # if no suggestion found, return results

+ 2
- 2
searx/engines/youtube.py 查看文件 

@@ -1,8 +1,8 @@
1 1 
 ## Youtube (Videos)
2 
-#
2 
+#
3 3 
 # @website     https://www.youtube.com/
4 4 
 # @provide-api yes (http://gdata-samples-youtube-search-py.appspot.com/)
5 
-#
5 
+#
6 6 
 # @using-api   yes
7 7 
 # @results     JSON
8 8 
 # @stable      yes