logo

searx

Unnamed repository; edit this file 'description' to name the repository.
commit: 4e0f079a8ca5b5ef14c8d7cb9e3330682e37bc50
parent: 8ce604385901ddfe15ef030188970cbb9b807c6a
Author: Dalf <alex@al-f.net>
Date:   Wed,  3 Jun 2015 10:12:30 +0200

[fix] youtube_noapi : don't crash when there is no content

Diffstat:

searx/engines/youtube_noapi.py | 50+++++++++++++++++++++++++++++++++-----------------
1 file changed, 33 insertions(+), 17 deletions(-)

diff --git a/searx/engines/youtube_noapi.py b/searx/engines/youtube_noapi.py @@ -34,6 +34,22 @@ title_xpath = './/div[@class="yt-lockup-content"]/h3/a' content_xpath = './/div[@class="yt-lockup-content"]/div[@class="yt-lockup-description yt-ui-ellipsis yt-ui-ellipsis-2"]' +# get element in list or default value +def list_get(a_list, index, default=None): + if len(a_list) > index: + return a_list[index] + else: + return default + + +# returns extract_text on the first result selected by the xpath or None +def extract_text_from_dom(result, xpath): + r = result.xpath(xpath) + if len(r) > 0: + return extract_text(r[0]) + return None + + # do search-request def request(query, params): params['url'] = search_url.format(query=quote_plus(query), @@ -50,23 +66,23 @@ def response(resp): # parse results for result in dom.xpath(results_xpath): - videoid = result.xpath('@data-context-item-id')[0] - - url = base_youtube_url + videoid - thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg' - - title = extract_text(result.xpath(title_xpath)[0]) - content = extract_text(result.xpath(content_xpath)[0]) - - embedded = embedded_url.format(videoid=videoid) - - # append result - results.append({'url': url, - 'title': title, - 'content': content, - 'template': 'videos.html', - 'embedded': embedded, - 'thumbnail': thumbnail}) + videoid = list_get(result.xpath('@data-context-item-id'), 0) + if videoid is not None: + url = base_youtube_url + videoid + thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg' + + title = extract_text_from_dom(result, title_xpath) or videoid + content = extract_text_from_dom(result, content_xpath) + + embedded = embedded_url.format(videoid=videoid) + + # append result + results.append({'url': url, + 'title': title, + 'content': content, + 'template': 'videos.html', + 'embedded': embedded, + 'thumbnail': thumbnail}) # return results return results