diff options
| author | Pydo <pydo@tutanota.com> | 2016-10-01 10:46:18 -0400 |
|---|---|---|
| committer | Pydo <pydo@tutanota.com> | 2016-10-01 10:46:18 -0400 |
| commit | 55a5b686ed6dc0b9a6bfc45e0eaf1f70e24f2aea (patch) | |
| tree | 96e953057dd3fc29681039f7ac5b282dac189ee8 /searx/engines/dictzone.py | |
| parent | 6f87bf2a1c76f1b94ad2119df7fb938c2307e370 (diff) | |
| parent | 295fc9ce96d8cca9c6c4776a00e5fb0942eb6f4d (diff) | |
Merge branch 'master' of https://github.com/asciimoo/searx into feature/seedpeer-engine-integration
Resolved conflict searx/settings.yml
Diffstat (limited to 'searx/engines/dictzone.py')
| -rw-r--r-- | searx/engines/dictzone.py | 69 |
1 files changed, 69 insertions, 0 deletions
diff --git a/searx/engines/dictzone.py b/searx/engines/dictzone.py new file mode 100644 index 000000000..9765d5f60 --- /dev/null +++ b/searx/engines/dictzone.py @@ -0,0 +1,69 @@ +""" + Dictzone + + @website https://dictzone.com/ + @provide-api no + @using-api no + @results HTML (using search portal) + @stable no (HTML can change) + @parse url, title, content +""" + +import re +from urlparse import urljoin +from lxml import html +from cgi import escape +from searx.utils import is_valid_lang + +categories = ['general'] +url = u'http://dictzone.com/{from_lang}-{to_lang}-dictionary/{query}' +weight = 100 + +parser_re = re.compile(u'.*?([a-z]+)-([a-z]+) ([^ ]+)$', re.I) +results_xpath = './/table[@id="r"]/tr' + + +def request(query, params): + m = parser_re.match(unicode(query, 'utf8')) + if not m: + return params + + from_lang, to_lang, query = m.groups() + + from_lang = is_valid_lang(from_lang) + to_lang = is_valid_lang(to_lang) + + if not from_lang or not to_lang: + return params + + params['url'] = url.format(from_lang=from_lang[2], + to_lang=to_lang[2], + query=query) + + return params + + +def response(resp): + results = [] + + dom = html.fromstring(resp.text) + + for k, result in enumerate(dom.xpath(results_xpath)[1:]): + try: + from_result, to_results_raw = result.xpath('./td') + except: + continue + + to_results = [] + for to_result in to_results_raw.xpath('./p/a'): + t = to_result.text_content() + if t.strip(): + to_results.append(to_result.text_content()) + + results.append({ + 'url': urljoin(resp.url, '?%d' % k), + 'title': escape(from_result.text_content()), + 'content': escape('; '.join(to_results)) + }) + + return results |