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

tests for _fetch_supported_languages in engines

marc 8 年前
父节点
e0c270bd72
当前提交
af35eee10b
共有 27 个文件被更改，包括 387 次插入 和 3388 次删除
合并视图 显示文件统计
  1. 1
    3256
      searx/data/engines_languages.json
  2. 二进制
      searx/engines/.yandex.py.swp
  3. 10
    3
      searx/engines/__init__.py
  4. 2
    4
      searx/engines/bing.py
  5. 1
    1
      searx/engines/bing_images.py
  6. 1
    1
      searx/engines/bing_news.py
  7. 2
    3
      searx/engines/dailymotion.py
  8. 2
    3
      searx/engines/duckduckgo.py
  9. 1
    1
      searx/engines/duckduckgo_definitions.py
  10. 2
    4
      searx/engines/gigablast.py
  11. 5
    7
      searx/engines/google.py
  12. 1
    1
      searx/engines/google_news.py
  13. 4
    4
      searx/engines/swisscows.py
  14. 1
    1
      searx/engines/wikidata.py
  15. 2
    4
      searx/engines/wikipedia.py
  16. 3
    5
      searx/engines/yahoo.py
  17. 1
    1
      searx/engines/yahoo_news.py
  18. 25
    85
      searx/languages.py
  19. 32
    0
      tests/unit/engines/test_bing.py
  20. 37
    0
      tests/unit/engines/test_dailymotion.py
  21. 14
    0
      tests/unit/engines/test_duckduckgo.py
  22. 25
    0
      tests/unit/engines/test_gigablast.py
  23. 57
    0
      tests/unit/engines/test_google.py
  24. 27
    0
      tests/unit/engines/test_swisscows.py
  25. 93
    0
      tests/unit/engines/test_wikipedia.py
  26. 30
    0
      tests/unit/engines/test_yahoo.py
  27. 8
    4
      utils/fetch_languages.py

+ 1
- 3256
searx/data/engines_languages.json
文件差异内容过多而无法显示
查看文件


二进制
searx/engines/.yandex.py.swp 查看文件


+ 10
- 3
searx/engines/__init__.py 查看文件

21 
 from flask_babel import gettext
 21 
 from flask_babel import gettext
22 
 from operator import itemgetter
 22 
 from operator import itemgetter
23 
 from json import loads
 23 
 from json import loads
24 
+from requests import get
24 
 from searx import settings
 25 
 from searx import settings
25 
 from searx import logger
 26 
 from searx import logger
26 
 from searx.utils import load_module
 27 
 from searx.utils import load_module
79 
         if not hasattr(engine, arg_name):
 80 
         if not hasattr(engine, arg_name):
80 
             setattr(engine, arg_name, arg_value)
 81 
             setattr(engine, arg_name, arg_value)
81
82
82 
-    if engine_data['name'] in languages:
83 
-        setattr(engine, 'supported_languages', languages[engine_data['name']])
84 
-
85 
     # checking required variables
 83 
     # checking required variables
86 
     for engine_attr in dir(engine):
 84 
     for engine_attr in dir(engine):
87 
         if engine_attr.startswith('_'):
 85 
         if engine_attr.startswith('_'):
91 
                          .format(engine.name, engine_attr))
 89 
                          .format(engine.name, engine_attr))
92 
             sys.exit(1)
 90 
             sys.exit(1)
93
91
92 
+    # assign supported languages from json file
93 
+    if engine_data['name'] in languages:
94 
+        setattr(engine, 'supported_languages', languages[engine_data['name']])
95 
+
96 
+    # assign language fetching method if auxiliary method exists
97 
+    if hasattr(engine, '_fetch_supported_languages'):
98 
+        setattr(engine, 'fetch_supported_languages',
99 
+                lambda: engine._fetch_supported_languages(get(engine.supported_languages_url)))
100 
+
94 
     engine.stats = {
 101 
     engine.stats = {
95 
         'result_count': 0,
 102 
         'result_count': 0,
96 
         'search_count': 0,
 103 
         'search_count': 0,

+ 2
- 4
searx/engines/bing.py 查看文件

15
15
16 
 from urllib import urlencode
 16 
 from urllib import urlencode
17 
 from lxml import html
 17 
 from lxml import html
18 
-from requests import get
19 
 from searx.engines.xpath import extract_text
 18 
 from searx.engines.xpath import extract_text
20
19
21 
 # engine dependent config
 20 
 # engine dependent config
86
85
87
86
88 
 # get supported languages from their site
 87 
 # get supported languages from their site
89 
-def fetch_supported_languages():
88 
+def _fetch_supported_languages(resp):
90 
     supported_languages = []
 89 
     supported_languages = []
91 
-    response = get(supported_languages_url)
92 
-    dom = html.fromstring(response.text)
90 
+    dom = html.fromstring(resp.text)
93 
     options = dom.xpath('//div[@id="limit-languages"]//input')
 91 
     options = dom.xpath('//div[@id="limit-languages"]//input')
94 
     for option in options:
 92 
     for option in options:
95 
         code = option.xpath('./@id')[0].replace('_', '-')
 93 
         code = option.xpath('./@id')[0].replace('_', '-')

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

19 
 from lxml import html
 19 
 from lxml import html
20 
 from json import loads
 20 
 from json import loads
21 
 import re
 21 
 import re
22 
-from searx.engines.bing import fetch_supported_languages
22 
+from searx.engines.bing import _fetch_supported_languages, supported_languages_url
23
23
24 
 # engine dependent config
 24 
 # engine dependent config
25 
 categories = ['images']
 25 
 categories = ['images']

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

17 
 from dateutil import parser
 17 
 from dateutil import parser
18 
 from lxml import etree
 18 
 from lxml import etree
19 
 from searx.utils import list_get
 19 
 from searx.utils import list_get
20 
-from searx.engines.bing import fetch_supported_languages
20 
+from searx.engines.bing import _fetch_supported_languages, supported_languages_url
21
21
22 
 # engine dependent config
 22 
 # engine dependent config
23 
 categories = ['news']
 23 
 categories = ['news']

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

80
80
81
81
82 
 # get supported languages from their site
 82 
 # get supported languages from their site
83 
-def fetch_supported_languages():
83 
+def _fetch_supported_languages(resp):
84 
     supported_languages = {}
 84 
     supported_languages = {}
85
85
86 
-    response = get(supported_languages_url)
87 
-    response_json = loads(response.text)
86 
+    response_json = loads(resp.text)
88
87
89 
     for language in response_json['list']:
 88 
     for language in response_json['list']:
90 
         supported_languages[language['code']] = {}
 89 
         supported_languages[language['code']] = {}

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

119
119
120
120
121 
 # get supported languages from their site
 121 
 # get supported languages from their site
122 
-def fetch_supported_languages():
123 
-    response = get(supported_languages_url)
122 
+def _fetch_supported_languages(resp):
124
123
125 
     # response is a js file with regions as an embedded object
 124 
     # response is a js file with regions as an embedded object
126 
-    response_page = response.text
125 
+    response_page = resp.text
127 
     response_page = response_page[response_page.find('regions:{') + 8:]
 126 
     response_page = response_page[response_page.find('regions:{') + 8:]
128 
     response_page = response_page[:response_page.find('}') + 1]
 127 
     response_page = response_page[:response_page.find('}') + 1]
129
128

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

4 
 from lxml import html
 4 
 from lxml import html
5 
 from searx.utils import html_to_text
 5 
 from searx.utils import html_to_text
6 
 from searx.engines.xpath import extract_text
 6 
 from searx.engines.xpath import extract_text
7 
-from searx.engines.duckduckgo import fetch_supported_languages
7 
+from searx.engines.duckduckgo import _fetch_supported_languages, supported_languages_url
8
8
9 
 url = 'https://api.duckduckgo.com/'\
 9 
 url = 'https://api.duckduckgo.com/'\
10 
     + '?{query}&format=json&pretty=0&no_redirect=1&d=1'
 10 
     + '?{query}&format=json&pretty=0&no_redirect=1&d=1'

+ 2
- 4
searx/engines/gigablast.py 查看文件

14 
 from random import randint
 14 
 from random import randint
15 
 from time import time
 15 
 from time import time
16 
 from urllib import urlencode
 16 
 from urllib import urlencode
17 
-from requests import get
18 
 from lxml.html import fromstring
 17 
 from lxml.html import fromstring
19
18
20 
 # engine dependent config
 19 
 # engine dependent config
91
90
92
91
93 
 # get supported languages from their site
 92 
 # get supported languages from their site
94 
-def fetch_supported_languages():
93 
+def _fetch_supported_languages(resp):
95 
     supported_languages = []
 94 
     supported_languages = []
96 
-    response = get(supported_languages_url)
97 
-    dom = fromstring(response.text)
95 
+    dom = fromstring(resp.text)
98 
     links = dom.xpath('//span[@id="menu2"]/a')
 96 
     links = dom.xpath('//span[@id="menu2"]/a')
99 
     for link in links:
 97 
     for link in links:
100 
         code = link.xpath('./@href')[0][-2:]
 98 
         code = link.xpath('./@href')[0][-2:]

+ 5
- 7
searx/engines/google.py 查看文件

12 
 from urllib import urlencode
 12 
 from urllib import urlencode
13 
 from urlparse import urlparse, parse_qsl
 13 
 from urlparse import urlparse, parse_qsl
14 
 from lxml import html, etree
 14 
 from lxml import html, etree
15 
-from requests import get
16 
 from searx.engines.xpath import extract_text, extract_url
 15 
 from searx.engines.xpath import extract_text, extract_url
17 
 from searx.search import logger
 16 
 from searx.search import logger
18
17
364
363
365
364
366 
 # get supported languages from their site
 365 
 # get supported languages from their site
367 
-def fetch_supported_languages():
366 
+def _fetch_supported_languages(resp):
368 
     supported_languages = {}
 367 
     supported_languages = {}
369 
-    response = get(supported_languages_url)
370 
-    dom = html.fromstring(response.text)
371 
-    options = dom.xpath('//select[@name="hl"]/option')
368 
+    dom = html.fromstring(resp.text)
369 
+    options = dom.xpath('//table//td/font/label/span')
372 
     for option in options:
 370 
     for option in options:
373 
-        code = option.xpath('./@value')[0].split('-')[0]
374 
-        name = option.text[:-1].title()
371 
+        code = option.xpath('./@id')[0][1:]
372 
+        name = option.text.title()
375 
         supported_languages[code] = {"name": name}
 373 
         supported_languages[code] = {"name": name}
376
374
377 
     return supported_languages
 375 
     return supported_languages

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

13 
 from lxml import html
 13 
 from lxml import html
14 
 from urllib import urlencode
 14 
 from urllib import urlencode
15 
 from json import loads
 15 
 from json import loads
16 
-from searx.engines.google import fetch_supported_languages
16 
+from searx.engines.google import _fetch_supported_languages, supported_languages_url
17
17
18 
 # search-url
 18 
 # search-url
19 
 categories = ['news']
 19 
 categories = ['news']

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

13 
 from json import loads
 13 
 from json import loads
14 
 from urllib import urlencode, unquote
 14 
 from urllib import urlencode, unquote
15 
 import re
 15 
 import re
16 
-from requests import get
17 
 from lxml.html import fromstring
 16 
 from lxml.html import fromstring
18
17
19 
 # engine dependent config
 18 
 # engine dependent config
25 
 base_url = 'https://swisscows.ch/'
 24 
 base_url = 'https://swisscows.ch/'
26 
 search_string = '?{query}&page={page}'
 25 
 search_string = '?{query}&page={page}'
27
26
27 
+supported_languages_url = base_url
28 
+
28 
 # regex
 29 
 # regex
29 
 regex_json = re.compile(r'initialData: {"Request":(.|\n)*},\s*environment')
 30 
 regex_json = re.compile(r'initialData: {"Request":(.|\n)*},\s*environment')
30 
 regex_json_remove_start = re.compile(r'^initialData:\s*')
 31 
 regex_json_remove_start = re.compile(r'^initialData:\s*')
113
114
114
115
115 
 # get supported languages from their site
 116 
 # get supported languages from their site
116 
-def fetch_supported_languages():
117 
+def _fetch_supported_languages(resp):
117 
     supported_languages = []
 118 
     supported_languages = []
118 
-    response = get(base_url)
119 
-    dom = fromstring(response.text)
119 
+    dom = fromstring(resp.text)
120 
     options = dom.xpath('//div[@id="regions-popup"]//ul/li/a')
 120 
     options = dom.xpath('//div[@id="regions-popup"]//ul/li/a')
121 
     for option in options:
 121 
     for option in options:
122 
         code = option.xpath('./@data-val')[0]
 122 
         code = option.xpath('./@data-val')[0]

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

15 
 from searx.poolrequests import get
 15 
 from searx.poolrequests import get
16 
 from searx.engines.xpath import extract_text
 16 
 from searx.engines.xpath import extract_text
17 
 from searx.utils import format_date_by_locale
 17 
 from searx.utils import format_date_by_locale
18 
-from searx.engines.wikipedia import fetch_supported_languages
18 
+from searx.engines.wikipedia import _fetch_supported_languages, supported_languages_url
19
19
20 
 from json import loads
 20 
 from json import loads
21 
 from lxml.html import fromstring
 21 
 from lxml.html import fromstring

+ 2
- 4
searx/engines/wikipedia.py 查看文件

12
12
13 
 from json import loads
 13 
 from json import loads
14 
 from urllib import urlencode, quote
 14 
 from urllib import urlencode, quote
15 
-from requests import get
16 
 from lxml.html import fromstring
 15 
 from lxml.html import fromstring
17
16
18
17
119
118
120
119
121 
 # get supported languages from their site
 120 
 # get supported languages from their site
122 
-def fetch_supported_languages():
121 
+def _fetch_supported_languages(resp):
123 
     supported_languages = {}
 122 
     supported_languages = {}
124 
-    response = get(supported_languages_url)
125 
-    dom = fromstring(response.text)
123 
+    dom = fromstring(resp.text)
126 
     tables = dom.xpath('//table[contains(@class,"sortable")]')
 124 
     tables = dom.xpath('//table[contains(@class,"sortable")]')
127 
     for table in tables:
 125 
     for table in tables:
128 
         # exclude header row
 126 
         # exclude header row

+ 3
- 5
searx/engines/yahoo.py 查看文件

14 
 from urllib import urlencode
 14 
 from urllib import urlencode
15 
 from urlparse import unquote
 15 
 from urlparse import unquote
16 
 from lxml import html
 16 
 from lxml import html
17 
-from requests import get
18 
 from searx.engines.xpath import extract_text, extract_url
 17 
 from searx.engines.xpath import extract_text, extract_url
19
18
20 
 # engine dependent config
 19 
 # engine dependent config
144
143
145
144
146 
 # get supported languages from their site
 145 
 # get supported languages from their site
147 
-def fetch_supported_languages():
146 
+def _fetch_supported_languages(resp):
148 
     supported_languages = []
 147 
     supported_languages = []
149 
-    response = get(supported_languages_url)
150 
-    dom = html.fromstring(response.text)
148 
+    dom = html.fromstring(resp.text)
151 
     options = dom.xpath('//div[@id="yschlang"]/span/label/input')
 149 
     options = dom.xpath('//div[@id="yschlang"]/span/label/input')
152 
     for option in options:
 150 
     for option in options:
153 
-        code = option.xpath('./@value')[0][5:]
151 
+        code = option.xpath('./@value')[0][5:].replace('_', '-')
154 
         supported_languages.append(code)
 152 
         supported_languages.append(code)
155
153
156 
     return supported_languages
 154 
     return supported_languages

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

12 
 from urllib import urlencode
 12 
 from urllib import urlencode
13 
 from lxml import html
 13 
 from lxml import html
14 
 from searx.engines.xpath import extract_text, extract_url
 14 
 from searx.engines.xpath import extract_text, extract_url
15 
-from searx.engines.yahoo import parse_url, fetch_supported_languages
15 
+from searx.engines.yahoo import parse_url, _fetch_supported_languages, supported_languages_url
16 
 from datetime import datetime, timedelta
 16 
 from datetime import datetime, timedelta
17 
 import re
 17 
 import re
18 
 from dateutil import parser
 18 
 from dateutil import parser

+ 25
- 85
searx/languages.py 查看文件

3 
 # this file is generated automatically by utils/update_search_languages.py
 3 
 # this file is generated automatically by utils/update_search_languages.py
4
4
5 
 language_codes = (
 5 
 language_codes = (
6 
-    (u"ach", u"Acoli", u"", u""),
7 
     (u"af", u"Afrikaans", u"", u""),
 6 
     (u"af", u"Afrikaans", u"", u""),
8 
-    (u"ak", u"Akan", u"", u""),
9 
-    (u"am", u"አማርኛ", u"", u""),
7 
+    (u"am", u"አማርኛ", u"", u"Amharic"),
10 
     (u"ar-SA", u"العربية", u"المملكة العربية السعودية", u"Arabic"),
 8 
     (u"ar-SA", u"العربية", u"المملكة العربية السعودية", u"Arabic"),
11 
     (u"az", u"Azərbaycanca", u"", u"Azerbaijani"),
 9 
     (u"az", u"Azərbaycanca", u"", u"Azerbaijani"),
12 
-    (u"ban", u"Balinese", u"", u""),
13 
     (u"be", u"Беларуская", u"", u"Belarusian"),
 10 
     (u"be", u"Беларуская", u"", u"Belarusian"),
14 
-    (u"bem", u"Ichibemba", u"", u""),
15 
     (u"bg-BG", u"Български", u"България", u"Bulgarian"),
 11 
     (u"bg-BG", u"Български", u"България", u"Bulgarian"),
16 
-    (u"bn", u"বাংলা", u"", u""),
17 
-    (u"br", u"Brezhoneg", u"", u""),
18 
-    (u"bs", u"Bosanski", u"", u""),
12 
+    (u"bn", u"বাংলা", u"", u"Bengali"),
13 
+    (u"br", u"Brezhoneg", u"", u"Breton"),
14 
+    (u"bs", u"Bosnian", u"", u"Bosnian"),
19 
     (u"ca", u"Català", u"", u"Catalan"),
 15 
     (u"ca", u"Català", u"", u"Catalan"),
20 
     (u"ca-CT", u"Català", u"", u"Catalan"),
 16 
     (u"ca-CT", u"Català", u"", u"Catalan"),
21 
     (u"ca-ES", u"Català", u"Espanya", u"Catalan"),
 17 
     (u"ca-ES", u"Català", u"Espanya", u"Catalan"),
22 
     (u"ce", u"Нохчийн", u"", u"Chechen"),
 18 
     (u"ce", u"Нохчийн", u"", u"Chechen"),
23 
     (u"ceb", u"Sinugboanong Binisaya", u"", u"Cebuano"),
 19 
     (u"ceb", u"Sinugboanong Binisaya", u"", u"Cebuano"),
24 
-    (u"chr", u"ᏣᎳᎩ", u"", u""),
25 
-    (u"ckb", u"Central Kurdish", u"", u""),
26 
-    (u"co", u"Corsican", u"", u""),
27 
-    (u"crs", u"Seychellois Creole", u"", u""),
28 
     (u"cs-CZ", u"Čeština", u"Česko", u"Czech"),
 20 
     (u"cs-CZ", u"Čeština", u"Česko", u"Czech"),
29 
-    (u"cy", u"Cymraeg", u"", u""),
21 
+    (u"cy", u"Cymraeg", u"", u"Welsh"),
30 
     (u"da-DK", u"Dansk", u"Danmark", u"Danish"),
 22 
     (u"da-DK", u"Dansk", u"Danmark", u"Danish"),
31 
     (u"de", u"Deutsch", u"", u"German"),
 23 
     (u"de", u"Deutsch", u"", u"German"),
32 
     (u"de-AT", u"Deutsch", u"Österreich", u"German"),
 24 
     (u"de-AT", u"Deutsch", u"Österreich", u"German"),
33 
     (u"de-CH", u"Deutsch", u"Schweiz", u"German"),
 25 
     (u"de-CH", u"Deutsch", u"Schweiz", u"German"),
34 
     (u"de-DE", u"Deutsch", u"Deutschland", u"German"),
 26 
     (u"de-DE", u"Deutsch", u"Deutschland", u"German"),
35 
-    (u"ee", u"Eʋegbe", u"", u""),
36 
     (u"el-GR", u"Ελληνικά", u"Ελλάδα", u"Greek"),
 27 
     (u"el-GR", u"Ελληνικά", u"Ελλάδα", u"Greek"),
37 
     (u"en", u"English", u"", u"English"),
 28 
     (u"en", u"English", u"", u"English"),
38 
     (u"en-AU", u"English", u"Australia", u"English"),
 29 
     (u"en-AU", u"English", u"Australia", u"English"),
60 
     (u"eu", u"Euskara", u"", u"Basque"),
 51 
     (u"eu", u"Euskara", u"", u"Basque"),
61 
     (u"fa", u"فارسی", u"", u"Persian"),
 52 
     (u"fa", u"فارسی", u"", u"Persian"),
62 
     (u"fi-FI", u"Suomi", u"Suomi", u"Finnish"),
 53 
     (u"fi-FI", u"Suomi", u"Suomi", u"Finnish"),
63 
-    (u"fo", u"Føroyskt", u"", u""),
64 
     (u"fr", u"Français", u"", u"French"),
 54 
     (u"fr", u"Français", u"", u"French"),
65 
     (u"fr-BE", u"Français", u"Belgique", u"French"),
 55 
     (u"fr-BE", u"Français", u"Belgique", u"French"),
66 
     (u"fr-CA", u"Français", u"Canada", u"French"),
 56 
     (u"fr-CA", u"Français", u"Canada", u"French"),
67 
     (u"fr-CH", u"Français", u"Suisse", u"French"),
 57 
     (u"fr-CH", u"Français", u"Suisse", u"French"),
68 
     (u"fr-FR", u"Français", u"France", u"French"),
 58 
     (u"fr-FR", u"Français", u"France", u"French"),
69 
-    (u"fy", u"West-Frysk", u"", u""),
70 
-    (u"ga", u"Gaeilge", u"", u""),
71 
-    (u"gaa", u"Ga", u"", u""),
72 
-    (u"gd", u"Gàidhlig", u"", u""),
59 
+    (u"ga", u"Gaeilge", u"", u"Irish"),
73 
     (u"gl", u"Galego", u"", u"Galician"),
 60 
     (u"gl", u"Galego", u"", u"Galician"),
74 
-    (u"gn", u"Guarani", u"", u""),
75 
-    (u"gu", u"ગુજરાતી", u"", u""),
76 
-    (u"ha", u"Hausa", u"", u""),
77 
-    (u"haw", u"ʻŌlelo HawaiʻI", u"", u""),
61 
+    (u"gu", u"ગુજરાતી", u"", u"Gujarati"),
78 
     (u"he-IL", u"עברית", u"ישראל", u"Hebrew"),
 62 
     (u"he-IL", u"עברית", u"ישראל", u"Hebrew"),
79 
     (u"hi", u"हिन्दी", u"", u"Hindi"),
 63 
     (u"hi", u"हिन्दी", u"", u"Hindi"),
80 
     (u"hr-HR", u"Hrvatski", u"Hrvatska", u"Croatian"),
 64 
     (u"hr-HR", u"Hrvatski", u"Hrvatska", u"Croatian"),
81 
-    (u"ht", u"Haitian Creole", u"", u""),
82 
     (u"hu-HU", u"Magyar", u"Magyarország", u"Hungarian"),
 65 
     (u"hu-HU", u"Magyar", u"Magyarország", u"Hungarian"),
83 
     (u"hy", u"Հայերեն", u"", u"Armenian"),
 66 
     (u"hy", u"Հայերեն", u"", u"Armenian"),
84 
-    (u"ia", u"Interlingua", u"", u""),
85 
     (u"id-ID", u"Bahasa Indonesia", u"Indonesia", u"Indonesian"),
 67 
     (u"id-ID", u"Bahasa Indonesia", u"Indonesia", u"Indonesian"),
86 
-    (u"ig", u"Igbo", u"", u""),
87 
     (u"is", u"Íslenska", u"", u""),
 68 
     (u"is", u"Íslenska", u"", u""),
88 
     (u"it", u"Italiano", u"", u"Italian"),
 69 
     (u"it", u"Italiano", u"", u"Italian"),
89 
     (u"it-CH", u"Italiano", u"Svizzera", u"Italian"),
 70 
     (u"it-CH", u"Italiano", u"Svizzera", u"Italian"),
91 
     (u"iw", u"עברית", u"", u""),
 72 
     (u"iw", u"עברית", u"", u""),
92 
     (u"ja-JP", u"日本語", u"日本", u"Japanese"),
 73 
     (u"ja-JP", u"日本語", u"日本", u"Japanese"),
93 
     (u"ka", u"ქართული", u"", u"Georgian"),
 74 
     (u"ka", u"ქართული", u"", u"Georgian"),
94 
-    (u"kg", u"Kongo", u"", u""),
95 
     (u"kk", u"Қазақша", u"", u"Kazakh"),
 75 
     (u"kk", u"Қазақша", u"", u"Kazakh"),
96 
-    (u"km", u"ខ្មែរ", u"", u""),
97 
-    (u"kn", u"ಕನ್ನಡ", u"", u""),
76 
+    (u"kn", u"ಕನ್ನಡ", u"", u"Kannada"),
98 
     (u"ko-KR", u"한국어", u"대한민국", u"Korean"),
 77 
     (u"ko-KR", u"한국어", u"대한민국", u"Korean"),
99 
-    (u"kri", u"Krio", u"", u""),
100 
-    (u"ky", u"Кыргызча", u"", u""),
101 
     (u"la", u"Latina", u"", u"Latin"),
 78 
     (u"la", u"Latina", u"", u"Latin"),
102 
-    (u"lg", u"Luganda", u"", u""),
103 
-    (u"ln", u"Lingála", u"", u""),
104 
-    (u"lo", u"ລາວ", u"", u""),
105 
-    (u"loz", u"Lozi", u"", u""),
106 
     (u"lt-LT", u"Lietuvių", u"Lietuva", u"Lithuanian"),
 79 
     (u"lt-LT", u"Lietuvių", u"Lietuva", u"Lithuanian"),
107 
-    (u"lua", u"Luba-Lulua", u"", u""),
108 
     (u"lv-LV", u"Latviešu", u"Latvijas Republika", u""),
 80 
     (u"lv-LV", u"Latviešu", u"Latvijas Republika", u""),
109 
-    (u"mfe", u"Kreol Morisien", u"", u""),
110 
-    (u"mg", u"Malagasy", u"", u""),
111 
-    (u"mi", u"Maori", u"", u""),
81 
+    (u"mi", u"Reo Māori", u"", u"Maori"),
112 
     (u"min", u"Minangkabau", u"", u"Minangkabau"),
 82 
     (u"min", u"Minangkabau", u"", u"Minangkabau"),
113 
-    (u"mk", u"Македонски", u"", u""),
114 
-    (u"ml", u"മലയാളം", u"", u""),
115 
-    (u"mn", u"Монгол", u"", u""),
116 
-    (u"mr", u"मराठी", u"", u""),
83 
+    (u"mk", u"Македонски", u"", u"Macedonian"),
84 
+    (u"mn", u"Монгол", u"", u"Mongolian"),
85 
+    (u"mr", u"मराठी", u"", u"Marathi"),
117 
     (u"ms-MY", u"Bahasa Melayu", u"Malaysia", u"Malay"),
 86 
     (u"ms-MY", u"Bahasa Melayu", u"Malaysia", u"Malay"),
118 
-    (u"mt", u"Malti", u"", u""),
119 
-    (u"my", u"ဗမာ", u"", u""),
87 
+    (u"mt", u"Malti", u"", u"Maltese"),
120 
     (u"nb-NO", u"Norwegian Bokmål", u"Norge", u"Norwegian Bokmål"),
 88 
     (u"nb-NO", u"Norwegian Bokmål", u"Norge", u"Norwegian Bokmål"),
121 
-    (u"ne", u"नेपाली", u"", u""),
122 
     (u"nl", u"Nederlands", u"", u"Dutch"),
 89 
     (u"nl", u"Nederlands", u"", u"Dutch"),
123 
     (u"nl-BE", u"Nederlands", u"België", u"Dutch"),
 90 
     (u"nl-BE", u"Nederlands", u"België", u"Dutch"),
124 
     (u"nl-NL", u"Nederlands", u"Nederland", u"Dutch"),
 91 
     (u"nl-NL", u"Nederlands", u"Nederland", u"Dutch"),
125 
     (u"nn", u"Nynorsk", u"", u"Norwegian"),
 92 
     (u"nn", u"Nynorsk", u"", u"Norwegian"),
126 
     (u"no-NO", u"Norsk", u"Norge", u"Norwegian"),
 93 
     (u"no-NO", u"Norsk", u"Norge", u"Norwegian"),
127 
-    (u"nso", u"Northern Sotho", u"", u""),
128 
-    (u"ny", u"Nyanja", u"", u""),
129 
-    (u"nyn", u"Runyankore", u"", u""),
130 
-    (u"oc", u"Occitan", u"", u""),
131 
-    (u"om", u"Oromoo", u"", u""),
132 
-    (u"or", u"ଓଡ଼ିଆ", u"", u""),
133 
-    (u"pa", u"ਪੰਜਾਬੀ", u"", u""),
134 
-    (u"pcm", u"Nigerian Pidgin", u"", u""),
94 
+    (u"oc", u"Occitan", u"", u"Occitan"),
95 
+    (u"or", u"Oriya", u"", u"Oriya"),
96 
+    (u"pa", u"ਪੰਜਾਬੀ", u"", u"Panjabi"),
135 
     (u"pl-PL", u"Polski", u"Rzeczpospolita Polska", u"Polish"),
 97 
     (u"pl-PL", u"Polski", u"Rzeczpospolita Polska", u"Polish"),
136 
-    (u"ps", u"پښتو", u"", u""),
98 
+    (u"ps", u"Pushto", u"", u"Pushto"),
137 
     (u"pt", u"Português", u"", u"Portuguese"),
 99 
     (u"pt", u"Português", u"", u"Portuguese"),
138 
     (u"pt-BR", u"Português", u"Brasil", u"Portuguese"),
 100 
     (u"pt-BR", u"Português", u"Brasil", u"Portuguese"),
139 
     (u"pt-PT", u"Português", u"Portugal", u"Portuguese"),
 101 
     (u"pt-PT", u"Português", u"Portugal", u"Portuguese"),
140 
-    (u"qu", u"Runasimi", u"", u""),
141 
-    (u"rm", u"Rumantsch", u"", u""),
142 
-    (u"rn", u"Ikirundi", u"", u""),
143 
     (u"ro-RO", u"Română", u"România", u"Romanian"),
 102 
     (u"ro-RO", u"Română", u"România", u"Romanian"),
144 
     (u"ru-RU", u"Русский", u"Россия", u"Russian"),
 103 
     (u"ru-RU", u"Русский", u"Россия", u"Russian"),
145 
-    (u"rw", u"Kinyarwanda", u"", u""),
146 
-    (u"sd", u"Sindhi", u"", u""),
104 
+    (u"rw", u"Ikinyarwanda", u"", u"Kinyarwanda"),
147 
     (u"sh", u"Srpskohrvatski / Српскохрватски", u"", u"Serbo-Croatian"),
 105 
     (u"sh", u"Srpskohrvatski / Српскохрватски", u"", u"Serbo-Croatian"),
148 
-    (u"si", u"සිංහල", u"", u""),
149 
     (u"sk-SK", u"Slovenčina", u"Slovenská republika", u"Slovak"),
 106 
     (u"sk-SK", u"Slovenčina", u"Slovenská republika", u"Slovak"),
150 
     (u"sl", u"Slovenščina", u"", u"Slovenian"),
 107 
     (u"sl", u"Slovenščina", u"", u"Slovenian"),
151 
-    (u"sn", u"Chishona", u"", u""),
152 
-    (u"so", u"Soomaali", u"", u""),
153 
-    (u"sq", u"Shqip", u"", u""),
154 
     (u"sr", u"Српски / Srpski", u"", u"Serbian"),
 108 
     (u"sr", u"Српски / Srpski", u"", u"Serbian"),
155 
-    (u"st", u"Southern Sotho", u"", u""),
156 
-    (u"su", u"Sundanese", u"", u""),
157 
     (u"sv-SE", u"Svenska", u"Sverige", u"Swedish"),
 109 
     (u"sv-SE", u"Svenska", u"Sverige", u"Swedish"),
158 
     (u"sw", u"Kiswahili", u"", u""),
 110 
     (u"sw", u"Kiswahili", u"", u""),
159 
-    (u"ta", u"தமிழ்", u"", u""),
160 
-    (u"te", u"తెలుగు", u"", u""),
161 
-    (u"tg", u"Tajik", u"", u""),
111 
+    (u"ta", u"தமிழ்", u"", u"Tamil"),
162 
     (u"th-TH", u"ไทย", u"ไทย", u"Thai"),
 112 
     (u"th-TH", u"ไทย", u"ไทย", u"Thai"),
163 
-    (u"ti", u"ትግርኛ", u"", u""),
164 
-    (u"tk", u"Turkmen", u"", u""),
113 
+    (u"ti", u"ትግርኛ", u"", u"Tigrinya"),
165 
     (u"tl-PH", u"Filipino", u"Pilipinas", u""),
 114 
     (u"tl-PH", u"Filipino", u"Pilipinas", u""),
166 
-    (u"tlh", u"Klingon", u"", u""),
167 
-    (u"tn", u"Tswana", u"", u""),
168 
-    (u"to", u"Lea Fakatonga", u"", u""),
169 
     (u"tr-TR", u"Türkçe", u"Türkiye", u"Turkish"),
 115 
     (u"tr-TR", u"Türkçe", u"Türkiye", u"Turkish"),
170 
-    (u"tt", u"Tatar", u"", u""),
171 
-    (u"tum", u"Tumbuka", u"", u""),
172 
-    (u"tw", u"Twi", u"", u""),
173 
-    (u"ug", u"ئۇيغۇرچە", u"", u""),
116 
+    (u"tt", u"Татарча", u"", u"Tatar"),
174 
     (u"uk-UA", u"Українська", u"Україна", u"Ukrainian"),
 117 
     (u"uk-UA", u"Українська", u"Україна", u"Ukrainian"),
175 
     (u"ur", u"اردو", u"", u"Urdu"),
 118 
     (u"ur", u"اردو", u"", u"Urdu"),
176 
     (u"uz", u"O‘zbek", u"", u"Uzbek"),
 119 
     (u"uz", u"O‘zbek", u"", u"Uzbek"),
179 
     (u"vo", u"Volapük", u"", u"Volapük"),
 122 
     (u"vo", u"Volapük", u"", u"Volapük"),
180 
     (u"wa", u"Walon", u"", u"Walloon"),
 123 
     (u"wa", u"Walon", u"", u"Walloon"),
181 
     (u"war", u"Winaray", u"", u"Waray-Waray"),
 124 
     (u"war", u"Winaray", u"", u"Waray-Waray"),
182 
-    (u"wo", u"Wolof", u"", u""),
183 
-    (u"xh", u"Xhosa", u"", u""),
184 
-    (u"yi", u"ייִדיש", u"", u""),
185 
-    (u"yo", u"Èdè Yorùbá", u"", u""),
125 
+    (u"xh", u"Xhosa", u"", u"Xhosa"),
186 
     (u"zh", u"中文", u"", u"Chinese"),
 126 
     (u"zh", u"中文", u"", u"Chinese"),
187 
-    (u"zh-CN", u"中文", u"中国", u"Chinese"),
127 
+    (u"zh-CN", u"中文", u"中国", u""),
188 
     (u"zh-HK", u"中文", u"香港", u"Chinese"),
 128 
     (u"zh-HK", u"中文", u"香港", u"Chinese"),
189 
-    (u"zh-TW", u"中文", u"台湾", u"Chinese"),
190 
-    (u"zu", u"Isizulu", u"", u"")
129 
+    (u"zh-TW", u"中文", u"台湾", u""),
130 
+    (u"zu", u"Isi-Zulu", u"", u"Zulu")
191 
 )
 131 
 )

+ 32
- 0
tests/unit/engines/test_bing.py 查看文件

86 
         self.assertEqual(results[0]['title'], 'This should be the title')
 86 
         self.assertEqual(results[0]['title'], 'This should be the title')
87 
         self.assertEqual(results[0]['url'], 'http://this.should.be.the.link/')
 87 
         self.assertEqual(results[0]['url'], 'http://this.should.be.the.link/')
88 
         self.assertEqual(results[0]['content'], 'This should be the content.')
 88 
         self.assertEqual(results[0]['content'], 'This should be the content.')
89 
+
90 
+    def test_fetch_supported_languages(self):
91 
+        html = """<html></html>"""
92 
+        response = mock.Mock(text=html)
93 
+        results = bing._fetch_supported_languages(response)
94 
+        self.assertEqual(type(results), list)
95 
+        self.assertEqual(len(results), 0)
96 
+
97 
+        html = """
98 
+        <html>
99 
+            <body>
100 
+                <form>
101 
+                    <div id="limit-languages">
102 
+                        <div>
103 
+                            <div><input id="es" value="es"></input></div>
104 
+                        </div>
105 
+                        <div>
106 
+                            <div><input id="pt_BR" value="pt_BR"></input></div>
107 
+                            <div><input id="pt_PT" value="pt_PT"></input></div>
108 
+                        </div>
109 
+                    </div>
110 
+                </form>
111 
+            </body>
112 
+        </html>
113 
+        """
114 
+        response = mock.Mock(text=html)
115 
+        languages = bing._fetch_supported_languages(response)
116 
+        self.assertEqual(type(languages), list)
117 
+        self.assertEqual(len(languages), 3)
118 
+        self.assertIn('es', languages)
119 
+        self.assertIn('pt-BR', languages)
120 
+        self.assertIn('pt-PT', languages)

+ 37
- 0
tests/unit/engines/test_dailymotion.py 查看文件

1 
+# -*- coding: utf-8 -*-
1 
 from collections import defaultdict
 2 
 from collections import defaultdict
2 
 import mock
 3 
 import mock
3 
 from searx.engines import dailymotion
 4 
 from searx.engines import dailymotion
72 
         results = dailymotion.response(response)
 73 
         results = dailymotion.response(response)
73 
         self.assertEqual(type(results), list)
 74 
         self.assertEqual(type(results), list)
74 
         self.assertEqual(len(results), 0)
 75 
         self.assertEqual(len(results), 0)
76 
+
77 
+    def test_fetch_supported_languages(self):
78 
+        json = r"""
79 
+        {"list":[{"code":"af","name":"Afrikaans","native_name":"Afrikaans",
80 
+                  "localized_name":"Afrikaans","display_name":"Afrikaans"},
81 
+                 {"code":"ar","name":"Arabic","native_name":"\u0627\u0644\u0639\u0631\u0628\u064a\u0629",
82 
+                  "localized_name":"Arabic","display_name":"Arabic"},
83 
+                 {"code":"la","name":"Latin","native_name":null,
84 
+                  "localized_name":"Latin","display_name":"Latin"}
85 
+        ]}
86 
+        """
87 
+        response = mock.Mock(text=json)
88 
+        languages = dailymotion._fetch_supported_languages(response)
89 
+        self.assertEqual(type(languages), dict)
90 
+        self.assertEqual(len(languages), 3)
91 
+        self.assertIn('af', languages)
92 
+        self.assertIn('ar', languages)
93 
+        self.assertIn('la', languages)
94 
+
95 
+        self.assertEqual(type(languages['af']), dict)
96 
+        self.assertEqual(type(languages['ar']), dict)
97 
+        self.assertEqual(type(languages['la']), dict)
98 
+
99 
+        self.assertIn('name', languages['af'])
100 
+        self.assertIn('name', languages['ar'])
101 
+        self.assertNotIn('name', languages['la'])
102 
+
103 
+        self.assertIn('english_name', languages['af'])
104 
+        self.assertIn('english_name', languages['ar'])
105 
+        self.assertIn('english_name', languages['la'])
106 
+
107 
+        self.assertEqual(languages['af']['name'], 'Afrikaans')
108 
+        self.assertEqual(languages['af']['english_name'], 'Afrikaans')
109 
+        self.assertEqual(languages['ar']['name'], u'العربية')
110 
+        self.assertEqual(languages['ar']['english_name'], 'Arabic')
111 
+        self.assertEqual(languages['la']['english_name'], 'Latin')

+ 14
- 0
tests/unit/engines/test_duckduckgo.py 查看文件

84 
         self.assertEqual(results[0]['title'], 'This is the title')
 84 
         self.assertEqual(results[0]['title'], 'This is the title')
85 
         self.assertEqual(results[0]['url'], u'http://this.should.be.the.link/ű')
 85 
         self.assertEqual(results[0]['url'], u'http://this.should.be.the.link/ű')
86 
         self.assertEqual(results[0]['content'], 'This should be the content.')
 86 
         self.assertEqual(results[0]['content'], 'This should be the content.')
87 
+
88 
+    def test_fetch_supported_languages(self):
89 
+        js = """some code...regions:{
90 
+        "wt-wt":"All Results","ar-es":"Argentina","au-en":"Australia","at-de":"Austria","be-fr":"Belgium (fr)"
91 
+        }some more code..."""
92 
+        response = mock.Mock(text=js)
93 
+        languages = duckduckgo._fetch_supported_languages(response)
94 
+        self.assertEqual(type(languages), list)
95 
+        self.assertEqual(len(languages), 5)
96 
+        self.assertIn('wt-WT', languages)
97 
+        self.assertIn('es-AR', languages)
98 
+        self.assertIn('en-AU', languages)
99 
+        self.assertIn('de-AT', languages)
100 
+        self.assertIn('fr-BE', languages)

+ 25
- 0
tests/unit/engines/test_gigablast.py 查看文件

89 
         self.assertEqual(results[0]['title'], 'South by Southwest 2016')
 89 
         self.assertEqual(results[0]['title'], 'South by Southwest 2016')
90 
         self.assertEqual(results[0]['url'], 'www.sxsw.com')
 90 
         self.assertEqual(results[0]['url'], 'www.sxsw.com')
91 
         self.assertEqual(results[0]['content'], 'This should be the content.')
 91 
         self.assertEqual(results[0]['content'], 'This should be the content.')
92 
+
93 
+    def test_fetch_supported_languages(self):
94 
+        html = """<html></html>"""
95 
+        response = mock.Mock(text=html)
96 
+        results = gigablast._fetch_supported_languages(response)
97 
+        self.assertEqual(type(results), list)
98 
+        self.assertEqual(len(results), 0)
99 
+
100 
+        html = """
101 
+        <html>
102 
+            <body>
103 
+                <span id="menu2">
104 
+                    <a href="/search?&rxikd=1&qlang=xx"></a>
105 
+                    <a href="/search?&rxikd=1&qlang=en"></a>
106 
+                    <a href="/search?&rxikd=1&qlang=fr"></a>
107 
+                </span>
108 
+            </body>
109 
+        </html>
110 
+        """
111 
+        response = mock.Mock(text=html)
112 
+        languages = gigablast._fetch_supported_languages(response)
113 
+        self.assertEqual(type(languages), list)
114 
+        self.assertEqual(len(languages), 2)
115 
+        self.assertIn('en', languages)
116 
+        self.assertIn('fr', languages)

+ 57
- 0
tests/unit/engines/test_google.py 查看文件

177 
         self.assertEqual(results[0]['title'], '')
 177 
         self.assertEqual(results[0]['title'], '')
178 
         self.assertEqual(results[0]['content'], '')
 178 
         self.assertEqual(results[0]['content'], '')
179 
         self.assertEqual(results[0]['img_src'], 'https://this.is.the.image/image.jpg')
 179 
         self.assertEqual(results[0]['img_src'], 'https://this.is.the.image/image.jpg')
180 
+
181 
+    def test_fetch_supported_languages(self):
182 
+        html = """<html></html>"""
183 
+        response = mock.Mock(text=html)
184 
+        languages = google._fetch_supported_languages(response)
185 
+        self.assertEqual(type(languages), dict)
186 
+        self.assertEqual(len(languages), 0)
187 
+
188 
+        html = u"""
189 
+        <html>
190 
+            <body>
191 
+                <table>
192 
+                    <tbody>
193 
+                        <tr>
194 
+                            <td>
195 
+                                <font>
196 
+                                    <label>
197 
+                                        <span id="ten">English</span>
198 
+                                    </label>
199 
+                                </font>
200 
+                            </td>
201 
+                            <td>
202 
+                                <font>
203 
+                                    <label>
204 
+                                        <span id="tzh-CN">中文 (简体)</span>
205 
+                                    </label>
206 
+                                    <label>
207 
+                                        <span id="tzh-TW">中文 (繁體)</span>
208 
+                                    </label>
209 
+                                </font>
210 
+                            </td>
211 
+                        </tr>
212 
+                    </tbody>
213 
+                </table>
214 
+            </body>
215 
+        </html>
216 
+        """
217 
+        response = mock.Mock(text=html)
218 
+        languages = google._fetch_supported_languages(response)
219 
+        self.assertEqual(type(languages), dict)
220 
+        self.assertEqual(len(languages), 3)
221 
+
222 
+        self.assertIn('en', languages)
223 
+        self.assertIn('zh-CN', languages)
224 
+        self.assertIn('zh-TW', languages)
225 
+
226 
+        self.assertEquals(type(languages['en']), dict)
227 
+        self.assertEquals(type(languages['zh-CN']), dict)
228 
+        self.assertEquals(type(languages['zh-TW']), dict)
229 
+
230 
+        self.assertIn('name', languages['en'])
231 
+        self.assertIn('name', languages['zh-CN'])
232 
+        self.assertIn('name', languages['zh-TW'])
233 
+
234 
+        self.assertEquals(languages['en']['name'], 'English')
235 
+        self.assertEquals(languages['zh-CN']['name'], u'中文 (简体)')
236 
+        self.assertEquals(languages['zh-TW']['name'], u'中文 (繁體)')

+ 27
- 0
tests/unit/engines/test_swisscows.py 查看文件

126 
         self.assertEqual(results[2]['url'], 'http://de.wikipedia.org/wiki/Datei:This should.svg')
 126 
         self.assertEqual(results[2]['url'], 'http://de.wikipedia.org/wiki/Datei:This should.svg')
127 
         self.assertEqual(results[2]['img_src'], 'http://ts2.mm.This/should.png')
 127 
         self.assertEqual(results[2]['img_src'], 'http://ts2.mm.This/should.png')
128 
         self.assertEqual(results[2]['template'], 'images.html')
 128 
         self.assertEqual(results[2]['template'], 'images.html')
129 
+
130 
+    def test_fetch_supported_languages(self):
131 
+        html = """<html></html>"""
132 
+        response = mock.Mock(text=html)
133 
+        languages = swisscows._fetch_supported_languages(response)
134 
+        self.assertEqual(type(languages), list)
135 
+        self.assertEqual(len(languages), 0)
136 
+
137 
+        html = """
138 
+        <html>
139 
+            <div id="regions-popup">
140 
+                <div>
141 
+                    <ul>
142 
+                        <li><a data-val="browser"></a></li>
143 
+                        <li><a data-val="de-CH"></a></li>
144 
+                        <li><a data-val="fr-CH"></a></li>
145 
+                    </ul>
146 
+                </div>
147 
+            </div>
148 
+        </html>
149 
+        """
150 
+        response = mock.Mock(text=html)
151 
+        languages = swisscows._fetch_supported_languages(response)
152 
+        self.assertEqual(type(languages), list)
153 
+        self.assertEqual(len(languages), 3)
154 
+        self.assertIn('de-CH', languages)
155 
+        self.assertIn('fr-CH', languages)

+ 93
- 0
tests/unit/engines/test_wikipedia.py 查看文件

164 
         self.assertEqual(len(results), 2)
 164 
         self.assertEqual(len(results), 2)
165 
         self.assertEqual(results[1]['infobox'], u'披頭四樂隊')
 165 
         self.assertEqual(results[1]['infobox'], u'披頭四樂隊')
166 
         self.assertIn(u'披头士乐队...', results[1]['content'])
 166 
         self.assertIn(u'披头士乐队...', results[1]['content'])
167 
+
168 
+    def test_fetch_supported_languages(self):
169 
+        html = u"""<html></html>"""
170 
+        response = mock.Mock(text=html)
171 
+        languages = wikipedia._fetch_supported_languages(response)
172 
+        self.assertEqual(type(languages), dict)
173 
+        self.assertEqual(len(languages), 0)
174 
+
175 
+        html = u"""
176 
+        <html>
177 
+            <body>
178 
+                <div>
179 
+                    <div>
180 
+                        <h3>Table header</h3>
181 
+                        <table class="sortable jquery-tablesorter">
182 
+                            <thead>
183 
+                                <tr>
184 
+                                    <th>N</th>
185 
+                                    <th>Language</th>
186 
+                                    <th>Language (local)</th>
187 
+                                    <th>Wiki</th>
188 
+                                    <th>Articles</th>
189 
+                                </tr>
190 
+                            </thead>
191 
+                            <tbody>
192 
+                                <tr>
193 
+                                    <td>2</td>
194 
+                                    <td><a>Swedish</a></td>
195 
+                                    <td><a>Svenska</a></td>
196 
+                                    <td><a>sv</a></td>
197 
+                                    <td><a><b>3000000</b></a></td>
198 
+                                </tr>
199 
+                                <tr>
200 
+                                    <td>3</td>
201 
+                                    <td><a>Cebuano</a></td>
202 
+                                    <td><a>Sinugboanong Binisaya</a></td>
203 
+                                    <td><a>ceb</a></td>
204 
+                                    <td><a><b>3000000</b></a></td>
205 
+                                </tr>
206 
+                            </tbody>
207 
+                        </table>
208 
+                        <h3>Table header</h3>
209 
+                        <table class="sortable jquery-tablesorter">
210 
+                            <thead>
211 
+                                <tr>
212 
+                                    <th>N</th>
213 
+                                    <th>Language</th>
214 
+                                    <th>Language (local)</th>
215 
+                                    <th>Wiki</th>
216 
+                                    <th>Articles</th>
217 
+                                </tr>
218 
+                            </thead>
219 
+                            <tbody>
220 
+                                <tr>
221 
+                                    <td>2</td>
222 
+                                    <td><a>Norwegian (Bokmål)</a></td>
223 
+                                    <td><a>Norsk (Bokmål)</a></td>
224 
+                                    <td><a>no</a></td>
225 
+                                    <td><a><b>100000</b></a></td>
226 
+                                </tr>
227 
+                            </tbody>
228 
+                        </table>
229 
+                    </div>
230 
+                </div>
231 
+            </body>
232 
+        </html>
233 
+        """
234 
+        response = mock.Mock(text=html)
235 
+        languages = wikipedia._fetch_supported_languages(response)
236 
+        self.assertEqual(type(languages), dict)
237 
+        self.assertEqual(len(languages), 3)
238 
+
239 
+        self.assertIn('sv', languages)
240 
+        self.assertIn('ceb', languages)
241 
+        self.assertIn('no', languages)
242 
+
243 
+        self.assertEqual(type(languages['sv']), dict)
244 
+        self.assertEqual(type(languages['ceb']), dict)
245 
+        self.assertEqual(type(languages['no']), dict)
246 
+
247 
+        self.assertIn('name', languages['sv'])
248 
+        self.assertIn('english_name', languages['sv'])
249 
+        self.assertIn('articles', languages['sv'])
250 
+
251 
+        self.assertEqual(languages['sv']['name'], 'Svenska')
252 
+        self.assertEqual(languages['sv']['english_name'], 'Swedish')
253 
+        self.assertEqual(languages['sv']['articles'], 3000000)
254 
+        self.assertEqual(languages['ceb']['name'], 'Sinugboanong Binisaya')
255 
+        self.assertEqual(languages['ceb']['english_name'], 'Cebuano')
256 
+        self.assertEqual(languages['ceb']['articles'], 3000000)
257 
+        self.assertEqual(languages['no']['name'], u'Norsk (Bokmål)')
258 
+        self.assertEqual(languages['no']['english_name'], u'Norwegian (Bokmål)')
259 
+        self.assertEqual(languages['no']['articles'], 100000)

+ 30
- 0
tests/unit/engines/test_yahoo.py 查看文件

147 
         results = yahoo.response(response)
 147 
         results = yahoo.response(response)
148 
         self.assertEqual(type(results), list)
 148 
         self.assertEqual(type(results), list)
149 
         self.assertEqual(len(results), 0)
 149 
         self.assertEqual(len(results), 0)
150 
+
151 
+    def test_fetch_supported_languages(self):
152 
+        html = """<html></html>"""
153 
+        response = mock.Mock(text=html)
154 
+        results = yahoo._fetch_supported_languages(response)
155 
+        self.assertEqual(type(results), list)
156 
+        self.assertEqual(len(results), 0)
157 
+
158 
+        html = """
159 
+        <html>
160 
+            <div>
161 
+                <div id="yschlang">
162 
+                    <span>
163 
+                        <label><input value="lang_ar"></input></label>
164 
+                    </span>
165 
+                    <span>
166 
+                        <label><input value="lang_zh_chs"></input></label>
167 
+                        <label><input value="lang_zh_cht"></input></label>
168 
+                    </span>
169 
+                </div>
170 
+            </div>
171 
+        </html>
172 
+        """
173 
+        response = mock.Mock(text=html)
174 
+        languages = yahoo._fetch_supported_languages(response)
175 
+        self.assertEqual(type(languages), list)
176 
+        self.assertEqual(len(languages), 3)
177 
+        self.assertIn('ar', languages)
178 
+        self.assertIn('zh-chs', languages)
179 
+        self.assertIn('zh-cht', languages)

+ 8
- 4
utils/fetch_languages.py 查看文件

84
84
85 
     # write json file
 85 
     # write json file
86 
     f = io.open(engines_languages_file, "w", encoding="utf-8")
 86 
     f = io.open(engines_languages_file, "w", encoding="utf-8")
87 
-    f.write(unicode(dumps(engines_languages, indent=4, ensure_ascii=False, encoding="utf-8")))
87 
+    f.write(unicode(dumps(engines_languages, ensure_ascii=False, encoding="utf-8")))
88 
     f.close()
 88 
     f.close()
89
89
90
90
110 
                 else:
 110 
                 else:
111 
                     languages[locale] = {}
 111 
                     languages[locale] = {}
112
112
113 
-    # get locales that have no name yet
113 
+    # get locales that have no name or country yet
114 
     for locale in languages.keys():
 114 
     for locale in languages.keys():
115 
         if not languages[locale].get('name'):
 115 
         if not languages[locale].get('name'):
116 
-            # try to get language and country names
116 
+            # try to get language names
117 
             name = languages.get(locale.split('-')[0], {}).get('name', None)
 117 
             name = languages.get(locale.split('-')[0], {}).get('name', None)
118 
             if name:
 118 
             if name:
119 
                 languages[locale]['name'] = name
 119 
                 languages[locale]['name'] = name
120 
-                languages[locale]['country'] = get_country_name(locale) or ''
121 
                 languages[locale]['english_name'] = languages.get(locale.split('-')[0], {}).get('english_name', '')
 120 
                 languages[locale]['english_name'] = languages.get(locale.split('-')[0], {}).get('english_name', '')
122 
             else:
 121 
             else:
123 
                 # filter out locales with no name
 122 
                 # filter out locales with no name
124 
                 del languages[locale]
 123 
                 del languages[locale]
124 
+                continue
125 
+
126 
+        # try to get country name
127 
+        if locale.find('-') > 0 and not languages[locale].get('country'):
128 
+            languages[locale]['country'] = get_country_name(locale) or ''
125
129
126
130
127 
 # Remove countryless language if language is featured in only one country.
 131 
 # Remove countryless language if language is featured in only one country.