mirrors/searxng
1
0
Fork 0
mirror of https://github.com/searxng/searxng.git synced 2024-12-23 09:46:31 +00:00
Code Issues Projects Releases Wiki Activity

[fix] remove searx/engines/filecrop.py (dead code)

Browse source
This commit is contained in:
Alexandre Flament 2020-12-04 16:48:15 +01:00
parent 0226ae69d3
commit 244e812f37
1 changed files with 0 additions and 85 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

85
searx/engines/filecrop.py
View file

@ -1,85 +0,0 @@
from html.parser import HTMLParser
from urllib.parse import urlencode
url = 'http://www.filecrop.com/'
search_url = url + '/search.php?{query}&size_i=0&size_f=100000000&engine_r=1&engine_d=1&engine_e=1&engine_4=1&engine_m=1&pos={index}' # noqa
paging = True
class FilecropResultParser(HTMLParser): # pylint: disable=W0223 # (see https://bugs.python.org/issue31844)
def __init__(self):
HTMLParser.__init__(self)
self.__start_processing = False
self.results = []
self.result = {}
self.tr_counter = 0
self.data_counter = 0
def handle_starttag(self, tag, attrs):
if tag == 'tr':
if ('bgcolor', '#edeff5') in attrs or\
('bgcolor', '#ffffff') in attrs:
self.__start_processing = True
if not self.__start_processing:
return
if tag == 'label':
self.result['title'] = [attr[1] for attr in attrs
if attr[0] == 'title'][0]
elif tag == 'a' and ('rel', 'nofollow') in attrs\
and ('class', 'sourcelink') in attrs:
if 'content' in self.result:
self.result['content'] += [attr[1] for attr in attrs
if attr[0] == 'title'][0]
else:
self.result['content'] = [attr[1] for attr in attrs
if attr[0] == 'title'][0]
self.result['content'] += ' '
elif tag == 'a':
self.result['url'] = url + [attr[1] for attr in attrs
if attr[0] == 'href'][0]
def handle_endtag(self, tag):
if self.__start_processing is False:
return
if tag == 'tr':
self.tr_counter += 1
if self.tr_counter == 2:
self.__start_processing = False
self.tr_counter = 0
self.data_counter = 0
self.results.append(self.result)
self.result = {}
def handle_data(self, data):
if not self.__start_processing:
return
if 'content' in self.result:
self.result['content'] += data + ' '
else:
self.result['content'] = data + ' '
self.data_counter += 1
def request(query, params):
index = 1 + (params['pageno'] - 1) * 30
params['url'] = search_url.format(query=urlencode({'w': query}), index=index)
return params
def response(resp):
parser = FilecropResultParser()
parser.feed(resp.text)
return parser.results