[mod] move extract_text, extract_url to searx.utils

1 files changed, 2 insertions, 73 deletions

diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py
index bd97a93a5..a269253d7 100644
--- a/searx/engines/xpath.py
+++ b/searx/engines/xpath.py
@@ -1,7 +1,6 @@
-from urllib.parse import unquote, urlencode, urljoin, urlparse
 from lxml import html
-from lxml.etree import _ElementStringResult, _ElementUnicodeResult
-from searx.utils import html_to_text, eval_xpath
+from urllib.parse import urlencode
+from searx.utils import extract_text, extract_url, eval_xpath
 
 search_url = None
 url_xpath = None
@@ -21,76 +20,6 @@ page_size = 1
 first_page_num = 1
 
 
-'''
-if xpath_results is list, extract the text from each result and concat the list
-if xpath_results is a xml element, extract all the text node from it
-   ( text_content() method from lxml )
-if xpath_results is a string element, then it's already done
-'''
-
-
-def extract_text(xpath_results):
-    if type(xpath_results) == list:
-        # it's list of result : concat everything using recursive call
-        result = ''
-        for e in xpath_results:
-            result = result + extract_text(e)
-        return result.strip()
-    elif type(xpath_results) in [_ElementStringResult, _ElementUnicodeResult]:
-        # it's a string
-        return ''.join(xpath_results)
-    else:
-        # it's a element
-        text = html.tostring(
-            xpath_results, encoding='unicode', method='text', with_tail=False
-        )
-        text = text.strip().replace('\n', ' ')
-        return ' '.join(text.split())
-
-
-def extract_url(xpath_results, search_url):
-    if xpath_results == []:
-        raise Exception('Empty url resultset')
-    url = extract_text(xpath_results)
-
-    if url.startswith('//'):
-        # add http or https to this kind of url //example.com/
-        parsed_search_url = urlparse(search_url)
-        url = '{0}:{1}'.format(parsed_search_url.scheme or 'http', url)
-    elif url.startswith('/'):
-        # fix relative url to the search engine
-        url = urljoin(search_url, url)
-
-    # fix relative urls that fall through the crack
-    if '://' not in url:
-        url = urljoin(search_url, url)
-
-    # normalize url
-    url = normalize_url(url)
-
-    return url
-
-
-def normalize_url(url):
-    parsed_url = urlparse(url)
-
-    # add a / at this end of the url if there is no path
-    if not parsed_url.netloc:
-        raise Exception('Cannot parse url')
-    if not parsed_url.path:
-        url += '/'
-
-    # FIXME : hack for yahoo
-    if parsed_url.hostname == 'search.yahoo.com'\
-       and parsed_url.path.startswith('/r'):
-        p = parsed_url.path
-        mark = p.find('/**')
-        if mark != -1:
-            return unquote(p[mark + 3:]).decode()
-
-    return url
-
-
 def request(query, params):
     query = urlencode({'q': query})[2:]