diff options
| author | Thomas Pointhuber <thomas.pointhuber@gmx.at> | 2015-01-09 21:25:13 +0100 |
|---|---|---|
| committer | Thomas Pointhuber <thomas.pointhuber@gmx.at> | 2015-01-09 21:30:09 +0100 |
| commit | 400b54191c590663f0cfe91045f70a5d9223aa19 (patch) | |
| tree | 08c71466ac8fbaf69872f114847baec762f5bd81 /searx/engines/twitter.py | |
| parent | af8dac93a8acff5042b7b399c38e348f0bdc32ad (diff) | |
| parent | c8be128e97479ea6c871c4b6fbf014fa8136e708 (diff) | |
Merge branch 'master' of https://github.com/asciimoo/searx into code_results
Conflicts:
searx/engines/searchcode_code.py
searx/engines/searchcode_doc.py
searx/static/oscar/js/searx.min.js
searx/templates/oscar/result_templates/default.html
searx/templates/oscar/result_templates/images.html
searx/templates/oscar/result_templates/map.html
searx/templates/oscar/result_templates/torrent.html
searx/templates/oscar/result_templates/videos.html
Diffstat (limited to 'searx/engines/twitter.py')
| -rw-r--r-- | searx/engines/twitter.py | 27 |
1 files changed, 19 insertions, 8 deletions
diff --git a/searx/engines/twitter.py b/searx/engines/twitter.py index 0689150c8..bd9a8c2fc 100644 --- a/searx/engines/twitter.py +++ b/searx/engines/twitter.py @@ -1,6 +1,6 @@ ## Twitter (Social media) # -# @website https://www.bing.com/news +# @website https://twitter.com/ # @provide-api yes (https://dev.twitter.com/docs/using-search) # # @using-api no @@ -14,6 +14,7 @@ from urlparse import urljoin from urllib import urlencode from lxml import html from cgi import escape +from datetime import datetime # engine dependent config categories = ['social media'] @@ -27,7 +28,8 @@ search_url = base_url+'search?' results_xpath = '//li[@data-item-type="tweet"]' link_xpath = './/small[@class="time"]//a' title_xpath = './/span[@class="username js-action-profile-name"]//text()' -content_xpath = './/p[@class="js-tweet-text tweet-text"]//text()' +content_xpath = './/p[@class="js-tweet-text tweet-text"]' +timestamp_xpath = './/span[contains(@class,"_timestamp")]' # do search-request @@ -52,12 +54,21 @@ def response(resp): link = tweet.xpath(link_xpath)[0] url = urljoin(base_url, link.attrib.get('href')) title = ''.join(tweet.xpath(title_xpath)) - content = escape(''.join(tweet.xpath(content_xpath))) - - # append result - results.append({'url': url, - 'title': title, - 'content': content}) + content = escape(html.tostring(tweet.xpath(content_xpath)[0], method='text', encoding='UTF-8').decode("utf-8")) + pubdate = tweet.xpath(timestamp_xpath) + if len(pubdate) > 0: + timestamp = float(pubdate[0].attrib.get('data-time')) + publishedDate = datetime.fromtimestamp(timestamp, None) + # append result + results.append({'url': url, + 'title': title, + 'content': content, + 'publishedDate': publishedDate}) + else: + # append result + results.append({'url': url, + 'title': title, + 'content': content}) # return results return results |