diff options
Diffstat (limited to 'searx/engines/vimeo.py')
| -rw-r--r-- | searx/engines/vimeo.py | 26 |
1 files changed, 14 insertions, 12 deletions
diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py index c66c4148a..39033c591 100644 --- a/searx/engines/vimeo.py +++ b/searx/engines/vimeo.py @@ -1,4 +1,4 @@ -## Vimeo (Videos) +# Vimeo (Videos) # # @website https://vimeo.com/ # @provide-api yes (http://developer.vimeo.com/api), @@ -7,14 +7,14 @@ # @using-api no (TODO, rewrite to api) # @results HTML (using search portal) # @stable no (HTML can change) -# @parse url, title, publishedDate, thumbnail +# @parse url, title, publishedDate, thumbnail, embedded # # @todo rewrite to api # @todo set content-parameter with correct data from urllib import urlencode -from HTMLParser import HTMLParser from lxml import html +from HTMLParser import HTMLParser from searx.engines.xpath import extract_text from dateutil import parser @@ -23,26 +23,26 @@ categories = ['videos'] paging = True # search-url -base_url = 'https://vimeo.com' +base_url = 'http://vimeo.com' search_url = base_url + '/search/page:{pageno}?{query}' # specific xpath variables +results_xpath = '//div[@id="browse_content"]/ol/li' url_xpath = './a/@href' +title_xpath = './a/div[@class="data"]/p[@class="title"]' content_xpath = './a/img/@src' -title_xpath = './a/div[@class="data"]/p[@class="title"]/text()' -results_xpath = '//div[@id="browse_content"]/ol/li' publishedDate_xpath = './/p[@class="meta"]//attribute::datetime' +embedded_url = '<iframe data-src="//player.vimeo.com/video{videoid}" ' +\ + 'width="540" height="304" frameborder="0" ' +\ + 'webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>' + # do search-request def request(query, params): params['url'] = search_url.format(pageno=params['pageno'], query=urlencode({'q': query})) - # TODO required? - params['cookies']['__utma'] =\ - '00000000.000#0000000.0000000000.0000000000.0000000000.0' - return params @@ -51,16 +51,17 @@ def response(resp): results = [] dom = html.fromstring(resp.text) - p = HTMLParser() # parse results for result in dom.xpath(results_xpath): - url = base_url + result.xpath(url_xpath)[0] + videoid = result.xpath(url_xpath)[0] + url = base_url + videoid title = p.unescape(extract_text(result.xpath(title_xpath))) thumbnail = extract_text(result.xpath(content_xpath)[0]) publishedDate = parser.parse(extract_text( result.xpath(publishedDate_xpath)[0])) + embedded = embedded_url.format(videoid=videoid) # append result results.append({'url': url, @@ -68,6 +69,7 @@ def response(resp): 'content': '', 'template': 'videos.html', 'publishedDate': publishedDate, + 'embedded': embedded, 'thumbnail': thumbnail}) # return results |