|
@@ -1,35 +1,60 @@
|
|
|
|
+## General Files (Files)
|
|
|
|
+#
|
|
|
|
+# @website http://www.general-files.org
|
|
|
|
+# @provide-api no (nothing found)
|
|
|
|
+#
|
|
|
|
+# @using-api no (because nothing found)
|
|
|
|
+# @results HTML (using search portal)
|
|
|
|
+# @stable no (HTML can change)
|
|
|
|
+# @parse url, title, content
|
|
|
|
+#
|
|
|
|
+# @todo detect torrents?
|
|
|
|
+
|
|
from lxml import html
|
|
from lxml import html
|
|
|
|
|
|
|
|
+# engine dependent config
|
|
|
|
+categories = ['files']
|
|
|
|
+paging = True
|
|
|
|
|
|
|
|
+# search-url
|
|
base_url = 'http://www.general-file.com'
|
|
base_url = 'http://www.general-file.com'
|
|
search_url = base_url + '/files-{letter}/{query}/{pageno}'
|
|
search_url = base_url + '/files-{letter}/{query}/{pageno}'
|
|
|
|
|
|
|
|
+# specific xpath variables
|
|
result_xpath = '//table[@class="block-file"]'
|
|
result_xpath = '//table[@class="block-file"]'
|
|
title_xpath = './/h2/a//text()'
|
|
title_xpath = './/h2/a//text()'
|
|
url_xpath = './/h2/a/@href'
|
|
url_xpath = './/h2/a/@href'
|
|
content_xpath = './/p//text()'
|
|
content_xpath = './/p//text()'
|
|
|
|
|
|
-paging = True
|
|
|
|
-
|
|
|
|
|
|
|
|
|
|
+# do search-request
|
|
def request(query, params):
|
|
def request(query, params):
|
|
|
|
+
|
|
params['url'] = search_url.format(query=query,
|
|
params['url'] = search_url.format(query=query,
|
|
letter=query[0],
|
|
letter=query[0],
|
|
pageno=params['pageno'])
|
|
pageno=params['pageno'])
|
|
|
|
+
|
|
return params
|
|
return params
|
|
|
|
|
|
|
|
|
|
|
|
+# get response from search-request
|
|
def response(resp):
|
|
def response(resp):
|
|
-
|
|
|
|
results = []
|
|
results = []
|
|
|
|
+
|
|
dom = html.fromstring(resp.text)
|
|
dom = html.fromstring(resp.text)
|
|
|
|
+
|
|
|
|
+ # parse results
|
|
for result in dom.xpath(result_xpath):
|
|
for result in dom.xpath(result_xpath):
|
|
url = result.xpath(url_xpath)[0]
|
|
url = result.xpath(url_xpath)[0]
|
|
|
|
+
|
|
# skip fast download links
|
|
# skip fast download links
|
|
if not url.startswith('/'):
|
|
if not url.startswith('/'):
|
|
continue
|
|
continue
|
|
|
|
+
|
|
|
|
+ # append result
|
|
results.append({'url': base_url + url,
|
|
results.append({'url': base_url + url,
|
|
'title': ''.join(result.xpath(title_xpath)),
|
|
'title': ''.join(result.xpath(title_xpath)),
|
|
'content': ''.join(result.xpath(content_xpath))})
|
|
'content': ''.join(result.xpath(content_xpath))})
|
|
|
|
|
|
|
|
+ # return results
|
|
return results
|
|
return results
|