Fix anomalous backslash in string

searx/engines/currency_convert.py

@@ -9,7 +9,7 @@ categories = []
 url = 'https://download.finance.yahoo.com/d/quotes.csv?e=.csv&f=sl1d1t1&s={query}=X'
 weight = 100
 
-parser_re = re.compile(u'.*?(\d+(?:\.\d+)?) ([^.0-9]+) (?:in|to) ([^.0-9]+)', re.I)  # noqa
+parser_re = re.compile(u'.*?(\\d+(?:\\.\\d+)?) ([^.0-9]+) (?:in|to) ([^.0-9]+)', re.I)  # noqa
 
 db = 1
 

searx/engines/deviantart.py

@@ -47,7 +47,7 @@ def response(resp):
 
     dom = html.fromstring(resp.text)
 
-    regex = re.compile('\/200H\/')
+    regex = re.compile(r'\/200H\/')
 
     # parse results
     for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'):

searx/engines/google.py

@@ -300,9 +300,9 @@ def parse_map_detail(parsed_url, result, google_hostname):
     results = []
 
     # try to parse the geoloc
-    m = re.search('@([0-9\.]+),([0-9\.]+),([0-9]+)', parsed_url.path)
+    m = re.search(r'@([0-9\.]+),([0-9\.]+),([0-9]+)', parsed_url.path)
     if m is None:
-        m = re.search('ll\=([0-9\.]+),([0-9\.]+)\&z\=([0-9]+)', parsed_url.query)
+        m = re.search(r'll\=([0-9\.]+),([0-9\.]+)\&z\=([0-9]+)', parsed_url.query)
 
     if m is not None:
         # geoloc found (ignored)

searx/engines/startpage.py

@@ -68,15 +68,15 @@ def response(resp):
         url = link.attrib.get('href')
 
         # block google-ad url's
-        if re.match("^http(s|)://(www\.)?google\.[a-z]+/aclk.*$", url):
+        if re.match(r"^http(s|)://(www\.)?google\.[a-z]+/aclk.*$", url):
             continue
 
         # block startpage search url's
-        if re.match("^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):
+        if re.match(r"^http(s|)://(www\.)?startpage\.com/do/search\?.*$", url):
             continue
 
         # block ixquick search url's
-        if re.match("^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):
+        if re.match(r"^http(s|)://(www\.)?ixquick\.com/do/search\?.*$", url):
             continue
 
         title = escape(extract_text(link))
@@ -89,7 +89,7 @@ def response(resp):
         published_date = None
 
         # check if search result starts with something like: "2 Sep 2014 ... "
-        if re.match("^([1-9]|[1-2][0-9]|3[0-1]) [A-Z][a-z]{2} [0-9]{4} \.\.\. ", content):
+        if re.match(r"^([1-9]|[1-2][0-9]|3[0-1]) [A-Z][a-z]{2} [0-9]{4} \.\.\. ", content):
             date_pos = content.find('...') + 4
             date_string = content[0:date_pos - 5]
             published_date = parser.parse(date_string, dayfirst=True)
@@ -98,7 +98,7 @@ def response(resp):
             content = content[date_pos:]
 
         # check if search result starts with something like: "5 days ago ... "
-        elif re.match("^[0-9]+ days? ago \.\.\. ", content):
+        elif re.match(r"^[0-9]+ days? ago \.\.\. ", content):
             date_pos = content.find('...') + 4
             date_string = content[0:date_pos - 5]
 

searx/engines/swisscows.py

@@ -25,10 +25,10 @@ base_url = 'https://swisscows.ch/'
 search_string = '?{query}&page={page}'
 
 # 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/engines/tokyotoshokan.py

@@ -48,7 +48,7 @@ def response(resp):
         return []
 
     # regular expression for parsing torrent size strings
-    size_re = re.compile('Size:\s*([\d.]+)(TB|GB|MB|B)', re.IGNORECASE)
+    size_re = re.compile(r'Size:\s*([\d.]+)(TB|GB|MB|B)', re.IGNORECASE)
 
     # processing the results, two rows at a time
     for i in xrange(0, len(rows), 2):

searx/engines/www500px.py

@@ -41,7 +41,7 @@ def response(resp):
     results = []
 
     dom = html.fromstring(resp.text)
-    regex = re.compile('3\.jpg.*$')
+    regex = re.compile(r'3\.jpg.*$')
 
     # parse results
     for result in dom.xpath('//div[@class="photo"]'):

searx/engines/yahoo_news.py

@@ -55,7 +55,7 @@ def request(query, params):
 
 def sanitize_url(url):
     if ".yahoo.com/" in url:
-        return re.sub(u"\;\_ylt\=.+$", "", url)
+        return re.sub(u"\\;\\_ylt\\=.+$", "", url)
     else:
         return url
 

searx/plugins/https_rewrite.py

@@ -87,7 +87,7 @@ def load_single_https_ruleset(rules_path):
 
             # convert host-rule to valid regex
             host = ruleset.attrib.get('host')\
-                .replace('.', '\.').replace('*', '.*')
+                .replace('.', r'\.').replace('*', '.*')
 
             # append to host list
             hosts.append(host)

searx/results.py

@@ -5,7 +5,7 @@ from threading import RLock
 from urlparse import urlparse, unquote
 from searx.engines import engines
 
-CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile('[,;:!?\./\\\\ ()-_]', re.M | re.U)
+CONTENT_LEN_IGNORED_CHARS_REGEX = re.compile(r'[,;:!?\./\\\\ ()-_]', re.M | re.U)
 WHITESPACE_REGEX = re.compile('( |\t|\n)+', re.M | re.U)
 
 

searx/utils.py

@@ -63,7 +63,7 @@ def highlight_content(content, query):
         regex_parts = []
         for chunk in query.split():
             if len(chunk) == 1:
-                regex_parts.append(u'\W+{0}\W+'.format(re.escape(chunk)))
+                regex_parts.append(u'\\W+{0}\\W+'.format(re.escape(chunk)))
             else:
                 regex_parts.append(u'{0}'.format(re.escape(chunk)))
         query_regex = u'({0})'.format('|'.join(regex_parts))