aa09f96 · searx · git.iko.soy

searx/engines/currency_convert.py+1−1

@@ -9,7 +9,7 @@ categories = []

99url = 'https://download.finance.yahoo.com/d/quotes.csv?e=.csv&f=sl1d1t1&s={query}=X'

1010weight = 100

1111

12−parser_re = re.compile(u'.*?(\d+(?:\.\d+)?) ([^.0-9]+) (?:in|to) ([^.0-9]+)', re.I) # noqa

12+parser_re = re.compile(u'.*?(\\d+(?:\\.\\d+)?) ([^.0-9]+) (?:in|to) ([^.0-9]+)', re.I) # noqa

1313

1414db = 1

1515

searx/engines/deviantart.py+1−1

@@ -47,7 +47,7 @@ def response(resp):

4747

4848 dom = html.fromstring(resp.text)

4949

50− regex = re.compile('\/200H\/')

50+ regex = re.compile(r'\/200H\/')

5151

5252 # parse results

5353 for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'):

searx/engines/google.py+2−2

@@ -300,9 +300,9 @@ def parse_map_detail(parsed_url, result, google_hostname):

300300 results = []

301301

302302 # try to parse the geoloc

303− m = re.search('@([0-9\.]+),([0-9\.]+),([0-9]+)', parsed_url.path)

303+ m = re.search(r'@([0-9\.]+),([0-9\.]+),([0-9]+)', parsed_url.path)

304304 if m is None:

305− m = re.search('ll\=([0-9\.]+),([0-9\.]+)\&z\=([0-9]+)', parsed_url.query)

305+ m = re.search(r'll\=([0-9\.]+),([0-9\.]+)\&z\=([0-9]+)', parsed_url.query)

306306

307307 if m is not None:

308308 # geoloc found (ignored)

searx/engines/startpage.py+5−5

@@ -68,15 +68,15 @@ def response(resp):

6868 url = link.attrib.get('href')

6969

7070 # block google-ad url's

71− if re.match("^http(s|)://(www\.)?google\.[a-z]+/aclk.*$", url):

71+ if re.match(r"^http(s|)://(www\.)?google\.[a-z]+/aclk.*$", url):

7272 continue

7373

7474 # block startpage search url's

75− if re.match("^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):

75+ if re.match(r"^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):

7676 continue

7777

7878 # block ixquick search url's

79− if re.match("^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):

79+ if re.match(r"^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):

8080 continue

8181

8282 title = escape(extract_text(link))

@@ -89,7 +89,7 @@ def response(resp):

8989 published_date = None

9090

9191 # check if search result starts with something like: "2 Sep 2014 ... "

92− if re.match("^([1-9]|[1-2][0-9]|3[0-1]) [A-Z][a-z]{2} [0-9]{4} \.\.\. ", content):

92+ if re.match(r"^([1-9]|[1-2][0-9]|3[0-1]) [A-Z][a-z]{2} [0-9]{4} \.\.\. ", content):

9393 date_pos = content.find('...') + 4

9494 date_string = content[0:date_pos - 5]

9595 published_date = parser.parse(date_string, dayfirst=True)

@@ -98,7 +98,7 @@ def response(resp):

9898 content = content[date_pos:]

9999

100100 # check if search result starts with something like: "5 days ago ... "

101− elif re.match("^[0-9]+ days? ago \.\.\. ", content):

101+ elif re.match(r"^[0-9]+ days? ago \.\.\. ", content):

102102 date_pos = content.find('...') + 4

103103 date_string = content[0:date_pos - 5]

104104

searx/engines/swisscows.py+4−4

@@ -25,10 +25,10 @@ base_url = 'https://swisscows.ch/'

2525search_string = '?{query}&page={page}'

2626

2727# regex

28−regex_json = re.compile('initialData: {"Request":(.|\n)*},\s*environment')

29−regex_json_remove_start = re.compile('^initialData:\s*')

30−regex_json_remove_end = re.compile(',\s*environment$')

31−regex_img_url_remove_start = re.compile('^https?://i\.swisscows\.ch/\?link=')

28+regex_json = re.compile(r'initialData: {"Request":(.|\n)*},\s*environment')

29+regex_json_remove_start = re.compile(r'^initialData:\s*')

30+regex_json_remove_end = re.compile(r',\s*environment$')

31+regex_img_url_remove_start = re.compile(r'^https?://i\.swisscows\.ch/\?link=')

3232

3333

3434# do search-request

searx/engines/tokyotoshokan.py+1−1

@@ -48,7 +48,7 @@ def response(resp):

4848 return []

4949

5050 # regular expression for parsing torrent size strings

51− size_re = re.compile('Size:\s*([\d.]+)(TB|GB|MB|B)', re.IGNORECASE)

51+ size_re = re.compile(r'Size:\s*([\d.]+)(TB|GB|MB|B)', re.IGNORECASE)

5252

5353 # processing the results, two rows at a time

5454 for i in xrange(0, len(rows), 2):

searx/engines/www500px.py+1−1

@@ -41,7 +41,7 @@ def response(resp):

4141 results = []

4242

4343 dom = html.fromstring(resp.text)

44− regex = re.compile('3\.jpg.*$')

44+ regex = re.compile(r'3\.jpg.*$')

4545

4646 # parse results

4747 for result in dom.xpath('//div[@class="photo"]'):

searx/engines/yahoo_news.py+1−1

@@ -55,7 +55,7 @@ def request(query, params):

5555

5656def sanitize_url(url):

5757 if ".yahoo.com/" in url:

58− return re.sub(u"\;\_ylt\=.+$", "", url)

58+ return re.sub(u"\\;\\_ylt\\=.+$", "", url)

5959 else:

6060 return url

6161

searx/plugins/https_rewrite.py+1−1

@@ -87,7 +87,7 @@ def load_single_https_ruleset(rules_path):

8787

8888 # convert host-rule to valid regex

8989 host = ruleset.attrib.get('host')\

90− .replace('.', '\.').replace('*', '.*')

90+ .replace('.', r'\.').replace('*', '.*')

9191

9292 # append to host list

9393 hosts.append(host)

searx/results.py+1−1

@@ -5,7 +5,7 @@ from threading import RLock

55from urlparse import urlparse, unquote

66from searx.engines import engines

77

8−CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile('[,;:!?\./\\\\ ()-_]', re.M | re.U)

8+CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile(r'[,;:!?\./\\\\ ()-_]', re.M | re.U)

99WHITESPACE_REGEX = re.compile('( |\t|\n)+', re.M | re.U)

1010

1111

searx/utils.py+1−1

@@ -63,7 +63,7 @@ def highlight_content(content, query):

6363 regex_parts = []

6464 for chunk in query.split():

6565 if len(chunk) == 1:

66− regex_parts.append(u'\W+{0}\W+'.format(re.escape(chunk)))

66+ regex_parts.append(u'\\W+{0}\\W+'.format(re.escape(chunk)))

6767 else:

6868 regex_parts.append(u'{0}'.format(re.escape(chunk)))

6969 query_regex = u'({0})'.format('|'.join(regex_parts))

tests/unit/engines/test_dailymotion.py+1−1

@@ -62,7 +62,7 @@ class TestDailymotionEngine(SearxTestCase):

6262 self.assertEqual(results[0]['content'], 'Description')

6363 self.assertIn('x2fit7q', results[0]['embedded'])

6464

65− json = """

65+ json = r"""

6666 {"toto":[

6767 {"id":200,"name":"Artist Name",

6868 "link":"http:\/\/www.dailymotion.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_deezer.py+2−2

@@ -27,7 +27,7 @@ class TestDeezerEngine(SearxTestCase):

2727 response = mock.Mock(text='{"data": []}')

2828 self.assertEqual(deezer.response(response), [])

2929

30− json = """

30+ json = r"""

3131 {"data":[

3232 {"id":100, "title":"Title of track",

3333 "link":"https:\/\/www.deezer.com\/track\/1094042","duration":232,

@@ -45,7 +45,7 @@ class TestDeezerEngine(SearxTestCase):

4545 self.assertEqual(results[0]['content'], 'Artist Name • Album Title • Title of track')

4646 self.assertTrue('100' in results[0]['embedded'])

4747

48− json = """

48+ json = r"""

4949 {"data":[

5050 {"id":200,"name":"Artist Name",

5151 "link":"https:\/\/www.deezer.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_flickr.py+5−5

@@ -27,7 +27,7 @@ class TestFlickrEngine(SearxTestCase):

2727 response = mock.Mock(text='{"data": []}')

2828 self.assertEqual(flickr.response(response), [])

2929

30− json = """

30+ json = r"""

3131 { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",

3232 "photo": [

3333 { "id": "15751017054", "owner": "66847915@N08",

@@ -55,7 +55,7 @@ class TestFlickrEngine(SearxTestCase):

5555 self.assertTrue('Owner' in results[0]['content'])

5656 self.assertTrue('Description' in results[0]['content'])

5757

58− json = """

58+ json = r"""

5959 { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",

6060 "photo": [

6161 { "id": "15751017054", "owner": "66847915@N08",

@@ -79,7 +79,7 @@ class TestFlickrEngine(SearxTestCase):

7979 self.assertTrue('Owner' in results[0]['content'])

8080 self.assertTrue('Description' in results[0]['content'])

8181

82− json = """

82+ json = r"""

8383 { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",

8484 "photo": [

8585 { "id": "15751017054", "owner": "66847915@N08",

@@ -103,7 +103,7 @@ class TestFlickrEngine(SearxTestCase):

103103 self.assertTrue('Owner' in results[0]['content'])

104104 self.assertTrue('Description' in results[0]['content'])

105105

106− json = """

106+ json = r"""

107107 { "photos": { "page": 1, "pages": "41001", "perpage": 100, "total": "4100032",

108108 "photo": [

109109 { "id": "15751017054", "owner": "66847915@N08",

@@ -130,7 +130,7 @@ class TestFlickrEngine(SearxTestCase):

130130 self.assertEqual(type(results), list)

131131 self.assertEqual(len(results), 0)

132132

133− json = """

133+ json = r"""

134134 {"toto":[

135135 {"id":200,"name":"Artist Name",

136136 "link":"http:\/\/www.flickr.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_flickr_noapi.py+1−1

@@ -316,7 +316,7 @@ class TestFlickrNoapiEngine(SearxTestCase):

316316 self.assertEqual(len(results), 0)

317317

318318 # garbage test

319− json = """

319+ json = r"""

320320 {"toto":[

321321 {"id":200,"name":"Artist Name",

322322 "link":"http:\/\/www.flickr.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_ina.py+12−12

@@ -33,23 +33,23 @@ class TestInaEngine(SearxTestCase):

3333 <div class=\\"search-results--list\\"><div class=\\"media\\">\\n\

3434 \\t\\t\\t\\t<a class=\\"media-left media-video premium xiti_click_action\\" \

3535 data-xiti-params=\\"recherche_v4::resultats_conference_de_presse_du_general_de_gaulle::N\\" \

36− href=\\"\/video\/CAF89035682\/conference-de-presse-du-general-de-gaulle-video.html\\">\\n\

37− <img src=\\"https:\/\/www.ina.fr\/images_v2\/140x105\/CAF89035682.jpeg\\" \

36+ href=\\"\\/video\\/CAF89035682\\/conference-de-presse-du-general-de-gaulle-video.html\\">\\n\

37+ <img src=\\"https:\\/\\/www.ina.fr\\/images_v2\\/140x105\\/CAF89035682.jpeg\\" \

3838 alt=\\"Conf\\u00e9rence de presse du G\\u00e9n\\u00e9ral de Gaulle \\">\\n\

39− \\t\\t\\t\\t\\t<\/a>\\n\

39+ \\t\\t\\t\\t\\t<\\/a>\\n\

4040 \\t\\t\\t\\t\\t<div class=\\"media-body\\">\\n\\t\\t\\t\\t\\t\\t<h3 class=\\"h3--title media-heading\\">\\n\

4141 \\t\\t\\t\\t\\t\\t\\t<a class=\\"xiti_click_action\\" \

4242 data-xiti-params=\\"recherche_v4::resultats_conference_de_presse_du_general_de_gaulle::N\\" \

43− href=\\"\/video\/CAF89035682\/conference-de-presse-du-general-de-gaulle-video.html\\">\

44− Conf\\u00e9rence de presse du G\\u00e9n\\u00e9ral de Gaulle <\/a>\\n\

45− <\/h3>\\n\

46− <div class=\\"media-body__info\\">\\n<span class=\\"broadcast\\">27\/11\/1967<\/span>\\n\

47− <span class=\\"views\\">29321 vues<\/span>\\n\

48− <span class=\\"duration\\">01h 33m 07s<\/span>\\n\

49− <\/div>\\n\

43+ href=\\"\\/video\\/CAF89035682\\/conference-de-presse-du-general-de-gaulle-video.html\\">\

44+ Conf\\u00e9rence de presse du G\\u00e9n\\u00e9ral de Gaulle <\\/a>\\n\

45+ <\\/h3>\\n\

46+ <div class=\\"media-body__info\\">\\n<span class=\\"broadcast\\">27\\/11\\/1967<\\/span>\\n\

47+ <span class=\\"views\\">29321 vues<\\/span>\\n\

48+ <span class=\\"duration\\">01h 33m 07s<\\/span>\\n\

49+ <\\/div>\\n\

5050 <p class=\\"media-body__summary\\">VERSION INTEGRALE DE LA CONFERENCE DE PRESSE DU GENERAL DE GAULLE . \

51− - PA le Pr\\u00e9sident DE GAULLE : il ouvre les bras et s'assied. DP journalis...<\/p>\\n\

52− <\/div>\\n<\/div>\\n"

51+ - PA le Pr\\u00e9sident DE GAULLE : il ouvre les bras et s'assied. DP journalis...<\\/p>\\n\

52+ <\\/div>\\n<\\/div>\\n"

5353 }

5454 """

5555 response = mock.Mock(text=json)

tests/unit/engines/test_mediawiki.py+1−1

@@ -118,7 +118,7 @@ class TestMediawikiEngine(SearxTestCase):

118118 self.assertEqual(type(results), list)

119119 self.assertEqual(len(results), 0)

120120

121− json = """

121+ json = r"""

122122 {"toto":[

123123 {"id":200,"name":"Artist Name",

124124 "link":"http:\/\/www.mediawiki.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_mixcloud.py+1−1

@@ -55,7 +55,7 @@ class TestMixcloudEngine(SearxTestCase):

5555 self.assertEqual(results[0]['content'], 'User')

5656 self.assertTrue('http://www.mixcloud.com/user/this-is-the-url/' in results[0]['embedded'])

5757

58− json = """

58+ json = r"""

5959 {"toto":[

6060 {"id":200,"name":"Artist Name",

6161 "link":"http:\/\/www.mixcloud.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_searchcode_code.py+1−1

@@ -63,7 +63,7 @@ class TestSearchcodeCodeEngine(SearxTestCase):

6363 self.assertEqual(results[0]['repository'], 'https://repo')

6464 self.assertEqual(results[0]['code_language'], 'cpp')

6565

66− json = """

66+ json = r"""

6767 {"toto":[

6868 {"id":200,"name":"Artist Name",

6969 "link":"http:\/\/www.searchcode_code.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_searchcode_doc.py+1−1

@@ -61,7 +61,7 @@ class TestSearchcodeDocEngine(SearxTestCase):

6161 self.assertIn('test', results[0]['content'])

6262 self.assertIn('Description', results[0]['content'])

6363

64− json = """

64+ json = r"""

6565 {"toto":[

6666 {"id":200,"name":"Artist Name",

6767 "link":"http:\/\/www.searchcode_doc.com\/artist\/1217","type":"artist"}

tests/unit/engines/test_wolframalpha_noapi.py+3−3

@@ -28,7 +28,7 @@ class TestWolframAlphaNoAPIEngine(SearxTestCase):

2828 request = Request(headers={'Referer': referer_url})

2929

3030 # test failure

31− json = '''

31+ json = r'''

3232 {"queryresult" : {

3333 "success" : false,

3434 "error" : false,

@@ -42,7 +42,7 @@ class TestWolframAlphaNoAPIEngine(SearxTestCase):

4242 self.assertEqual(wolframalpha_noapi.response(response), [])

4343

4444 # test basic case

45− json = '''

45+ json = r'''

4646 {"queryresult" : {

4747 "success" : true,

4848 "error" : false,

@@ -143,7 +143,7 @@ class TestWolframAlphaNoAPIEngine(SearxTestCase):

143143 self.assertEqual('Wolfram|Alpha', results[1]['title'])

144144

145145 # test calc

146− json = """

146+ json = r"""

147147 {"queryresult" : {

148148 "success" : true,

149149 "error" : false,