From 68364df342e4ba09ca3faf95d938285ea646bd68 Mon Sep 17 00:00:00 2001 From: pw3t Date: Sun, 5 Jan 2014 22:10:46 +0100 Subject: [PATCH 1/2] [enh] 1st version of vimeo search engine (need improvments) --- searx/engines/vimeo.py | 48 ++++++++++++++++++++++++++++++++++++++++++ searx/webapp.py | 2 +- 2 files changed, 49 insertions(+), 1 deletion(-) create mode 100644 searx/engines/vimeo.py diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py new file mode 100644 index 000000000..3a6ac96e9 --- /dev/null +++ b/searx/engines/vimeo.py @@ -0,0 +1,48 @@ +from urllib import urlencode +from HTMLParser import HTMLParser +from xpath import * + +categories = ['dev'] + +search_url = 'http://vimeo.com/search?{query}' + +Cookie = { + 'vuid':'918282893.1027205400' + , 'ab_bs':'%7B%223%22%3A279%7D' + , '__utma':'18302654.101#6140782.1388942090.1388942090.1388942090.1' + , '__utmb':'18302654.1.10.1388942090' + , '__utmc':'18302654' + , '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)' + , '__utml':'search' +} + +#'vuid=918282893.1027205400& ab_bs=%7B%223%22%3A279%7D& player="scaling=1&volume=1"& __utma=18302654.101#6140782.1388942090.1388942090.1388942090.1& __utmb=18302654.1.10.1388942090& __utmc=18302654& __utmz=18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)& __utmli=search' + +def request(query, params): + params['url'] = search_url.format(query=urlencode({'q' :query})) + print params['url'] + params['cookies'] = Cookie + return params + + +def response(resp): + results = [] + + dom = html.fromstring(resp.text) + + if results_xpath: + for result in dom.xpath(results_xpath): + url = extract_url(result.xpath(url_xpath)) + + title = extract_text(result.xpath(title_xpath)[0 ]) + content = extract_text(result.xpath(content_xpath)[0]) + results.append({'url': url, 'title': title, 'content': content}) + else: + for url, title, content in zip( + map(extract_url, dom.xpath(url_xpath)), \ + map(extract_text, dom.xpath(title_xpath)), \ + map(extract_text, dom.xpath(content_xpath)), \ + ): + results.append({'url': url, 'title': title, 'content': content}) + + return results diff --git a/searx/webapp.py b/searx/webapp.py index 2d48f2323..9905bce37 100644 --- a/searx/webapp.py +++ b/searx/webapp.py @@ -107,7 +107,7 @@ def index(): if len(result['url']) > 74: result['pretty_url'] = result['url'][:35] + '[..]' + result['url'][-35:] else: - result['pretty_url'] = result['url'] + result['pretty_url'] = result['url'] if request_data.get('format') == 'json': return Response(json.dumps({'query': query, 'results': results}), mimetype='application/json') From 1950e697d6bd6efe184e1f2db0ed71267a284682 Mon Sep 17 00:00:00 2001 From: pw3t Date: Mon, 6 Jan 2014 22:15:46 +0100 Subject: [PATCH 2/2] [enh] Improved vimeo search engines, and add the configuration in the sample --- engines.cfg_sample | 7 ++++++ searx/engines/vimeo.py | 48 +++++++++++++++++------------------------- 2 files changed, 26 insertions(+), 29 deletions(-) diff --git a/engines.cfg_sample b/engines.cfg_sample index 05593cea4..b19632dc2 100644 --- a/engines.cfg_sample +++ b/engines.cfg_sample @@ -86,3 +86,10 @@ engine = dailymotion locale = en_US categories = videos +[vimeo] +engine = vimeo +categories = videos +results_xpath = //div[@id="browse_content"]/ol/li +url_xpath=./a/@href +title_xpath=./a/div[@class="data"]/p[@class="title"]/text() +content_xpath=./a/img/@src diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py index 3a6ac96e9..486c76d40 100644 --- a/searx/engines/vimeo.py +++ b/searx/engines/vimeo.py @@ -1,48 +1,38 @@ from urllib import urlencode from HTMLParser import HTMLParser -from xpath import * +from xpath import extract_text +from lxml import html -categories = ['dev'] - -search_url = 'http://vimeo.com/search?{query}' +base_url = 'http://vimeo.com' +search_url = base_url + '/search?{query}' +# the cookie set by vime contains all the following values, but only __utma seems to be requiered Cookie = { - 'vuid':'918282893.1027205400' - , 'ab_bs':'%7B%223%22%3A279%7D' - , '__utma':'18302654.101#6140782.1388942090.1388942090.1388942090.1' - , '__utmb':'18302654.1.10.1388942090' - , '__utmc':'18302654' - , '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)' - , '__utml':'search' + #'vuid':'918282893.1027205400' + # 'ab_bs':'%7B%223%22%3A279%7D' + '__utma':'00000000.000#0000000.0000000000.0000000000.0000000000.0' + # '__utmb':'18302654.1.10.1388942090' + #, '__utmc':'18302654' + #, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)' + #, '__utml':'search' } -#'vuid=918282893.1027205400& ab_bs=%7B%223%22%3A279%7D& player="scaling=1&volume=1"& __utma=18302654.101#6140782.1388942090.1388942090.1388942090.1& __utmb=18302654.1.10.1388942090& __utmc=18302654& __utmz=18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)& __utmli=search' - def request(query, params): params['url'] = search_url.format(query=urlencode({'q' :query})) print params['url'] params['cookies'] = Cookie return params - def response(resp): results = [] - dom = html.fromstring(resp.text) + + p = HTMLParser() - if results_xpath: - for result in dom.xpath(results_xpath): - url = extract_url(result.xpath(url_xpath)) - - title = extract_text(result.xpath(title_xpath)[0 ]) - content = extract_text(result.xpath(content_xpath)[0]) - results.append({'url': url, 'title': title, 'content': content}) - else: - for url, title, content in zip( - map(extract_url, dom.xpath(url_xpath)), \ - map(extract_text, dom.xpath(title_xpath)), \ - map(extract_text, dom.xpath(content_xpath)), \ - ): - results.append({'url': url, 'title': title, 'content': content}) + for result in dom.xpath(results_xpath): + url = base_url + result.xpath(url_xpath)[0] + title = p.unescape(extract_text(result.xpath(title_xpath))) + content = ' '.format(url, title, extract_text(result.xpath(content_xpath)[0])) + results.append({'url': url, 'title': title, 'content': content}) return results