diff options
author | Adam Tauber <asciimoo@gmail.com> | 2014-06-27 17:25:16 +0200 |
---|---|---|
committer | Adam Tauber <asciimoo@gmail.com> | 2014-06-27 17:25:16 +0200 |
commit | 8b0cb686d5fa1fe34667e313b86cadfbb235ca79 (patch) | |
tree | 628b383df97817efa0f81d6a22e59d03279f1525 /searx/engines/generalfile.py | |
parent | 96c8b20a045f62205a3b9a03113086f0fcfbc579 (diff) | |
download | searxng-8b0cb686d5fa1fe34667e313b86cadfbb235ca79.tar.gz searxng-8b0cb686d5fa1fe34667e313b86cadfbb235ca79.zip |
[enh] general-file.com engine added
Diffstat (limited to 'searx/engines/generalfile.py')
-rw-r--r-- | searx/engines/generalfile.py | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/searx/engines/generalfile.py b/searx/engines/generalfile.py new file mode 100644 index 000000000..d249c00c7 --- /dev/null +++ b/searx/engines/generalfile.py @@ -0,0 +1,35 @@ +from lxml import html + + +base_url = 'http://www.general-file.com' +search_url = base_url + '/files-{letter}/{query}/{pageno}' + +result_xpath = '//table[@class="block-file"]' +title_xpath = './/h2/a//text()' +url_xpath = './/h2/a/@href' +content_xpath = './/p//text()' + +paging = True + + +def request(query, params): + params['url'] = search_url.format(query=query, + letter=query[0], + pageno=params['pageno']) + return params + + +def response(resp): + + results = [] + dom = html.fromstring(resp.text) + for result in dom.xpath(result_xpath): + url = result.xpath(url_xpath)[0] + # skip fast download links + if not url.startswith('/'): + continue + results.append({'url': base_url + url, + 'title': ''.join(result.xpath(title_xpath)), + 'content': ''.join(result.xpath(content_xpath))}) + + return results |