Update pep8 tools to pycodestyle

pep8 is deprecated, it is replaced by pycodestyle.

manage.sh

@@ -35,7 +35,8 @@ pep8_check() {
     # ignored rules:
     #  E402 module level import not at top of file
     #  W503 line break before binary operator
-    pep8 --exclude=searx/static --max-line-length=120 --ignore "E402,W503" "$SEARX_DIR" "$BASE_DIR/tests"
+    #  E722 do not use bare 'except'
+    pycodestyle --exclude=searx/static --max-line-length=120 --ignore "E402,W503,E722" "$SEARX_DIR" "$BASE_DIR/tests"
 }
 
 unit_tests() {

requirements-dev.txt

 babel==2.3.4
 mock==2.0.0
-pep8==1.7.0
+pycodestyle==2.4.0
 mockredispy==2.9.3
 pytest==4.1.0
 pytest-cov==2.6.1

searx/__init__.py

@@ -23,7 +23,7 @@ from io import open
 from ssl import OPENSSL_VERSION_INFO, OPENSSL_VERSION
 try:
     from yaml import load
-except:
+except ImportError:
     from sys import exit, stderr
     stderr.write('[E] install pyyaml\n')
     exit(2)
@@ -38,6 +38,7 @@ def check_settings_yml(file_name):
     else:
         return None
 
+
 # find location of settings.yml
 if 'SEARX_SETTINGS_PATH' in environ:
     # if possible set path to settings using the

searx/engines/bing_images.py

@@ -116,7 +116,7 @@ def _fetch_supported_languages(resp):
 
     regions = dom.xpath(regions_xpath)
     for region in regions:
-        code = re.search('setmkt=[^\&]+', region).group()[7:]
+        code = re.search('setmkt=[^&]+', region).group()[7:]
         if code == 'nb-NO':
             code = 'no-NO'
 

searx/engines/genius.py

@@ -72,6 +72,7 @@ def parse_album(hit):
             result.update({'content': 'Released: {}'.format(year)})
     return result
 
+
 parse = {'lyric': parse_lyric, 'song': parse_lyric, 'artist': parse_artist, 'album': parse_album}
 
 

searx/engines/google.py

@@ -89,9 +89,8 @@ url_map = 'https://www.openstreetmap.org/'\
 
 # search-url
 search_path = '/search'
-search_url = ('https://{hostname}' +
-              search_path +
-              '?{query}&start={offset}&gws_rd=cr&gbv=1&lr={lang}&hl={lang_short}&ei=x')
+search_url = ('https://{hostname}' + search_path + '?{query}'
+              '&start={offset}&gws_rd=cr&gbv=1&lr={lang}&hl={lang_short}&ei=x')
 
 time_range_search = "&tbs=qdr:{range}"
 time_range_dict = {'day': 'd',

searx/engines/google_videos.py

@@ -76,11 +76,11 @@ def response(resp):
         # get thumbnails
         script = str(dom.xpath('//script[contains(., "_setImagesSrc")]')[0].text)
         id = result.xpath('.//div[@class="s"]//img/@id')[0]
-        thumbnails_data = re.findall('s=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id,
+        thumbnails_data = re.findall(r's=\'(.*?)(?:\\\\[a-z,1-9,\\\\]+\'|\')\;var ii=\[(?:|[\'vidthumb\d+\',]+)\'' + id,
                                      script)
         tmp = []
         if len(thumbnails_data) != 0:
-            tmp = re.findall('(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
+            tmp = re.findall(r'(data:image/jpeg;base64,[a-z,A-Z,0-9,/,\+]+)', thumbnails_data[0])
         thumbnail = ''
         if len(tmp) != 0:
             thumbnail = tmp[-1]

searx/engines/swisscows.py

@@ -28,10 +28,10 @@ search_string = '?{query}&page={page}'
 supported_languages_url = base_url
 
 # regex
-regex_json = re.compile('initialData: {"Request":(.|\n)*},\s*environment')
-regex_json_remove_start = re.compile('^initialData:\s*')
-regex_json_remove_end = re.compile(',\s*environment$')
-regex_img_url_remove_start = re.compile('^https?://i\.swisscows\.ch/\?link=')
+regex_json = re.compile(r'initialData: {"Request":(.|\n)*},\s*environment')
+regex_json_remove_start = re.compile(r'^initialData:\s*')
+regex_json_remove_end = re.compile(r',\s*environment$')
+regex_img_url_remove_start = re.compile(r'^https?://i\.swisscows\.ch/\?link=')
 
 
 # do search-request

searx/query.py

@@ -49,7 +49,7 @@ class RawTextQuery(object):
         self.query_parts = []
 
         # split query, including whitespaces
-        raw_query_parts = re.split(r'(\s+)' if isinstance(self.query, str) else b'(\s+)', self.query)
+        raw_query_parts = re.split(r'(\s+)' if isinstance(self.query, str) else r'(\s+)'.encode(), self.query)
 
         parse_next = True
 

searx/results.py

@@ -171,7 +171,7 @@ class ResultContainer(object):
                 continue
             try:
                 result['url'] = result['url']
-            except:
+            except KeyError:
                 pass
             if 'title' in result and not isinstance(result['title'], str):
                 continue

searx/utils.py

@@ -6,6 +6,7 @@ import re
 
 from babel.core import get_global
 from babel.dates import format_date
+from babel import UnknownLocaleError
 from codecs import getincrementalencoder
 from imp import load_source
 from numbers import Number
@@ -205,7 +206,7 @@ def format_date_by_locale(date, locale_string):
     # to avoid crashing if locale is not supported by babel
     try:
         formatted_date = format_date(date, locale=locale_string)
-    except:
+    except UnknownLocaleError:
         formatted_date = format_date(date, "YYYY-MM-dd")
 
     return formatted_date
@@ -255,7 +256,7 @@ def get_torrent_size(filesize, filesize_multiplier):
             filesize = int(filesize * 1000 * 1000)
         elif filesize_multiplier == 'KiB':
             filesize = int(filesize * 1000)
-    except:
+    except ValueError:
         filesize = None
 
     return filesize

searx/webapp.py

@@ -40,8 +40,9 @@ logger = logger.getChild('webapp')
 try:
     from pygments import highlight
     from pygments.lexers import get_lexer_by_name
+    from pygments.util import ClassNotFound
     from pygments.formatters import HtmlFormatter
-except:
+except ImportError:
     logger.critical("cannot import dependency: pygments")
     from sys import exit
 
@@ -178,7 +179,7 @@ def code_highlighter(codelines, language=None):
     try:
         # find lexer by programing language
         lexer = get_lexer_by_name(language, stripall=True)
-    except:
+    except ClassNotFound:
         # if lexer is not found, using default one
         logger.debug('highlighter cannot find lexer for {0}'.format(language))
         lexer = get_lexer_by_name('text', stripall=True)

tests/unit/engines/test_currency_convert.py

@@ -48,8 +48,11 @@ class TestCurrencyConvertEngine(TestCase):
         results = currency_convert.response(response)
         self.assertEqual(type(results), list)
         self.assertEqual(len(results), 1)
-        self.assertEqual(results[0]['answer'], '10.0 GBP = 5.0 USD, 1 GBP (pound sterling)' +
-                         ' = 0.5 USD (United States dollar)')
+        self.assertEqual(
+            results[0]['answer'],
+            ('10.0 GBP = 5.0 USD, 1 GBP (pound sterling)'
+             ' = 0.5 USD (United States dollar)')
+        )
 
         target_url = 'https://duckduckgo.com/js/spice/currency/1/{}/{}'.format(
             dicto['from'], dicto['to'])