From b2492c94f422e18cb8954ec983134f4fa5c7cdc0 Mon Sep 17 00:00:00 2001 From: asciimoo Date: Mon, 20 Jan 2014 02:31:20 +0100 Subject: [PATCH] [fix] pep/flake8 compatibility --- searx/engines/__init__.py | 2 +- searx/engines/currency_convert.py | 8 ++++--- searx/engines/dailymotion.py | 7 ++++-- searx/engines/deviantart.py | 8 +++++-- searx/engines/duckduckgo.py | 12 +++++----- searx/engines/duckduckgo_definitions.py | 12 +++++----- searx/engines/filecrop.py | 25 ++++++++++++++------- searx/engines/flickr.py | 10 +++++++-- searx/engines/github.py | 7 ++++-- searx/engines/google_images.py | 10 +++++++-- searx/engines/json_engine.py | 20 ++++++++++++----- searx/engines/mediawiki.py | 8 +++---- searx/engines/piratebay.py | 27 +++++++++++++++-------- searx/engines/soundcloud.py | 7 ++++-- searx/engines/stackoverflow.py | 4 +++- searx/engines/startpage.py | 6 ++--- searx/engines/twitter.py | 11 +++++++--- searx/engines/vimeo.py | 27 +++++++++++++---------- searx/engines/xpath.py | 26 ++++++++++++---------- searx/engines/yacy.py | 6 +++-- searx/engines/youtube.py | 14 ++++++------ searx/utils.py | 20 ++++++++++++----- searx/webapp.py | 29 ++++++++++++++++--------- 23 files changed, 197 insertions(+), 109 deletions(-) diff --git a/searx/engines/__init__.py b/searx/engines/__init__.py index 626372189..bc7b3b3bc 100644 --- a/searx/engines/__init__.py +++ b/searx/engines/__init__.py @@ -66,7 +66,7 @@ for engine_data in settings['engines']: for engine_attr in dir(engine): if engine_attr.startswith('_'): continue - if getattr(engine, engine_attr) == None: + if getattr(engine, engine_attr) is None: print '[E] Engine config error: Missing attribute "{0}.{1}"'.format(engine.name, engine_attr) # noqa sys.exit(1) engines[engine.name] = engine diff --git a/searx/engines/currency_convert.py b/searx/engines/currency_convert.py index f08a01e00..ce6b3b854 100644 --- a/searx/engines/currency_convert.py +++ b/searx/engines/currency_convert.py @@ -5,7 +5,7 @@ categories = [] url = 'http://finance.yahoo.com/d/quotes.csv?e=.csv&f=sl1d1t1&s={query}=X' weight = 100 -parser_re = re.compile(r'^\W*(\d+(?:\.\d+)?)\W*([a-z]{3})\W*(?:in)?\W*([a-z]{3})\W*$', re.I) +parser_re = re.compile(r'^\W*(\d+(?:\.\d+)?)\W*([a-z]{3})\W*(?:in)?\W*([a-z]{3})\W*$', re.I) # noqa def request(query, params): @@ -46,9 +46,11 @@ def response(resp): resp.search_params['ammount'] * conversion_rate ) - content = '1 {0} is {1} {2}'.format(resp.search_params['from'], conversion_rate, resp.search_params['to']) + content = '1 {0} is {1} {2}'.format(resp.search_params['from'], + conversion_rate, + resp.search_params['to']) now_date = datetime.now().strftime('%Y%m%d') - url = 'http://finance.yahoo.com/currency/converter-results/{0}/{1}-{2}-to-{3}.html' + url = 'http://finance.yahoo.com/currency/converter-results/{0}/{1}-{2}-to-{3}.html' # noqa url = url.format( now_date, resp.search_params['ammount'], diff --git a/searx/engines/dailymotion.py b/searx/engines/dailymotion.py index 7e0c922a9..510dbbfae 100644 --- a/searx/engines/dailymotion.py +++ b/searx/engines/dailymotion.py @@ -6,7 +6,10 @@ categories = ['videos'] locale = 'en_US' # see http://www.dailymotion.com/doc/api/obj-video.html -search_url = 'https://api.dailymotion.com/videos?fields=title,description,duration,url,thumbnail_360_url&sort=relevance&limit=25&page=1&{query}' +search_url = 'https://api.dailymotion.com/videos?fields=title,description,duration,url,thumbnail_360_url&sort=relevance&limit=25&page=1&{query}' # noqa + +# TODO use video result template +content_tpl = '
' def request(query, params): @@ -25,7 +28,7 @@ def response(resp): title = res['title'] url = res['url'] if res['thumbnail_360_url']: - content = '
'.format(url, res['thumbnail_360_url']) + content = content_tpl.format(url, res['thumbnail_360_url']) else: content = '' if res['description']: diff --git a/searx/engines/deviantart.py b/searx/engines/deviantart.py index 9a4a8abde..94a94bf16 100644 --- a/searx/engines/deviantart.py +++ b/searx/engines/deviantart.py @@ -7,6 +7,7 @@ categories = ['images'] base_url = 'https://www.deviantart.com/' search_url = base_url+'search?' + def request(query, params): global search_url params['url'] = search_url + urlencode({'q': query}) @@ -22,8 +23,11 @@ def response(resp): for result in dom.xpath('//div[contains(@class, "tt-a tt-fh")]'): link = result.xpath('.//a[contains(@class, "thumb")]')[0] url = urljoin(base_url, link.attrib.get('href')) - title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') + title_links = result.xpath('.//span[@class="details"]//a[contains(@class, "t")]') # noqa title = ''.join(title_links[0].xpath('.//text()')) img_src = link.xpath('.//img')[0].attrib['src'] - results.append({'url': url, 'title': title, 'img_src': img_src, 'template': 'images.html'}) + results.append({'url': url, + 'title': title, + 'img_src': img_src, + 'template': 'images.html'}) return results diff --git a/searx/engines/duckduckgo.py b/searx/engines/duckduckgo.py index 4bf770972..7cae87d95 100644 --- a/searx/engines/duckduckgo.py +++ b/searx/engines/duckduckgo.py @@ -6,8 +6,11 @@ url = 'https://duckduckgo.com/' search_url = url + 'd.js?{query}&p=1&s=0' locale = 'us-en' + def request(query, params): - params['url'] = search_url.format(query=urlencode({'q': query, 'l': locale})) + q = urlencode({'q': query, + 'l': locale}) + params['url'] = search_url.format(query=q) return params @@ -17,8 +20,7 @@ def response(resp): for r in search_res: if not r.get('t'): continue - results.append({'title': r['t'] - ,'content': html_to_text(r['a']) - ,'url': r['u'] - }) + results.append({'title': r['t'], + 'content': html_to_text(r['a']), + 'url': r['u']}) return results diff --git a/searx/engines/duckduckgo_definitions.py b/searx/engines/duckduckgo_definitions.py index 7b3950b85..3037aae53 100644 --- a/searx/engines/duckduckgo_definitions.py +++ b/searx/engines/duckduckgo_definitions.py @@ -3,8 +3,9 @@ from urllib import urlencode url = 'http://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1' + def request(query, params): - params['url'] = url.format(query=urlencode({'q': query})) + params['url'] = url.format(query=urlencode({'q': query})) return params @@ -13,11 +14,10 @@ def response(resp): results = [] if 'Definition' in search_res: if search_res.get('AbstractURL'): - res = {'title' : search_res.get('Heading', '') - ,'content' : search_res.get('Definition', '') - ,'url' : search_res.get('AbstractURL', '') - ,'class' : 'definition_result' - } + res = {'title': search_res.get('Heading', ''), + 'content': search_res.get('Definition', ''), + 'url': search_res.get('AbstractURL', ''), + 'class': 'definition_result'} results.append(res) return results diff --git a/searx/engines/filecrop.py b/searx/engines/filecrop.py index 52426b84a..81340e601 100644 --- a/searx/engines/filecrop.py +++ b/searx/engines/filecrop.py @@ -2,7 +2,8 @@ from urllib import urlencode from HTMLParser import HTMLParser url = 'http://www.filecrop.com/' -search_url = url + '/search.php?{query}&size_i=0&size_f=100000000&engine_r=1&engine_d=1&engine_e=1&engine_4=1&engine_m=1' +search_url = url + '/search.php?{query}&size_i=0&size_f=100000000&engine_r=1&engine_d=1&engine_e=1&engine_4=1&engine_m=1' # noqa + class FilecropResultParser(HTMLParser): def __init__(self): @@ -18,22 +19,28 @@ class FilecropResultParser(HTMLParser): def handle_starttag(self, tag, attrs): if tag == 'tr': - if ('bgcolor', '#edeff5') in attrs or ('bgcolor', '#ffffff') in attrs: + if ('bgcolor', '#edeff5') in attrs or\ + ('bgcolor', '#ffffff') in attrs: self.__start_processing = True if not self.__start_processing: return if tag == 'label': - self.result['title'] = [attr[1] for attr in attrs if attr[0] == 'title'][0] - elif tag == 'a' and ('rel', 'nofollow') in attrs and ('class', 'sourcelink') in attrs: + self.result['title'] = [attr[1] for attr in attrs + if attr[0] == 'title'][0] + elif tag == 'a' and ('rel', 'nofollow') in attrs\ + and ('class', 'sourcelink') in attrs: if 'content' in self.result: - self.result['content'] += [attr[1] for attr in attrs if attr[0] == 'title'][0] + self.result['content'] += [attr[1] for attr in attrs + if attr[0] == 'title'][0] else: - self.result['content'] = [attr[1] for attr in attrs if attr[0] == 'title'][0] + self.result['content'] = [attr[1] for attr in attrs + if attr[0] == 'title'][0] self.result['content'] += ' ' elif tag == 'a': - self.result['url'] = url + [attr[1] for attr in attrs if attr[0] == 'href'][0] + self.result['url'] = url + [attr[1] for attr in attrs + if attr[0] == 'href'][0] def handle_endtag(self, tag): if self.__start_processing is False: @@ -60,10 +67,12 @@ class FilecropResultParser(HTMLParser): self.data_counter += 1 + def request(query, params): - params['url'] = search_url.format(query=urlencode({'w' :query})) + params['url'] = search_url.format(query=urlencode({'w': query})) return params + def response(resp): parser = FilecropResultParser() parser.feed(resp.text) diff --git a/searx/engines/flickr.py b/searx/engines/flickr.py index a9832856d..d9554b99a 100644 --- a/searx/engines/flickr.py +++ b/searx/engines/flickr.py @@ -8,21 +8,27 @@ categories = ['images'] url = 'https://secure.flickr.com/' search_url = url+'search/?{query}' +results_xpath = '//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]' # noqa + def request(query, params): params['url'] = search_url.format(query=urlencode({'q': query})) return params + def response(resp): global base_url results = [] dom = html.fromstring(resp.text) - for result in dom.xpath('//div[@id="thumbnails"]//a[@class="rapidnofollow photo-click" and @data-track="photo-click"]'): + for result in dom.xpath(results_xpath): href = urljoin(url, result.attrib.get('href')) img = result.xpath('.//img')[0] title = img.attrib.get('alt', '') img_src = img.attrib.get('data-defer-src') if not img_src: continue - results.append({'url': href, 'title': title, 'img_src': img_src, 'template': 'images.html'}) + results.append({'url': href, + 'title': title, + 'img_src': img_src, + 'template': 'images.html'}) return results diff --git a/searx/engines/github.py b/searx/engines/github.py index b4baea6e8..be2cfe7c5 100644 --- a/searx/engines/github.py +++ b/searx/engines/github.py @@ -4,12 +4,15 @@ from cgi import escape categories = ['it'] -search_url = 'https://api.github.com/search/repositories?sort=stars&order=desc&{query}' +search_url = 'https://api.github.com/search/repositories?sort=stars&order=desc&{query}' # noqa + +accept_header = 'application/vnd.github.preview.text-match+json' + def request(query, params): global search_url params['url'] = search_url.format(query=urlencode({'q': query})) - params['headers']['Accept'] = 'application/vnd.github.preview.text-match+json' + params['headers']['Accept'] = accept_header return params diff --git a/searx/engines/google_images.py b/searx/engines/google_images.py index d828a9c4b..57e749265 100644 --- a/searx/engines/google_images.py +++ b/searx/engines/google_images.py @@ -6,12 +6,14 @@ from json import loads categories = ['images'] url = 'https://ajax.googleapis.com/' -search_url = url + 'ajax/services/search/images?v=1.0&start=0&rsz=large&safe=off&filter=off&{query}' +search_url = url + 'ajax/services/search/images?v=1.0&start=0&rsz=large&safe=off&filter=off&{query}' # noqa + def request(query, params): params['url'] = search_url.format(query=urlencode({'q': query})) return params + def response(resp): results = [] search_res = loads(resp.text) @@ -24,5 +26,9 @@ def response(resp): title = result['title'] if not result['url']: continue - results.append({'url': href, 'title': title, 'content': '', 'img_src': result['url'], 'template': 'images.html'}) + results.append({'url': href, + 'title': title, + 'content': '', + 'img_src': result['url'], + 'template': 'images.html'}) return results diff --git a/searx/engines/json_engine.py b/searx/engines/json_engine.py index 0386d53f7..e7cc808bb 100644 --- a/searx/engines/json_engine.py +++ b/searx/engines/json_engine.py @@ -2,12 +2,13 @@ from urllib import urlencode from json import loads from collections import Iterable -search_url = None -url_query = None +search_url = None +url_query = None content_query = None -title_query = None +title_query = None #suggestion_xpath = '' + def iterate(iterable): if type(iterable) == dict: it = iterable.iteritems() @@ -17,11 +18,15 @@ def iterate(iterable): for index, value in it: yield str(index), value + def is_iterable(obj): - if type(obj) == str: return False - if type(obj) == unicode: return False + if type(obj) == str: + return False + if type(obj) == unicode: + return False return isinstance(obj, Iterable) + def parse(query): q = [] for part in query.split('/'): @@ -31,6 +36,7 @@ def parse(query): q.append(part) return q + def do_query(data, q): ret = [] if not len(q): @@ -38,7 +44,7 @@ def do_query(data, q): qkey = q[0] - for key,value in iterate(data): + for key, value in iterate(data): if len(q) == 1: if key == qkey: @@ -54,11 +60,13 @@ def do_query(data, q): ret.extend(do_query(value, q)) return ret + def query(data, query_string): q = parse(query_string) return do_query(data, q) + def request(query, params): query = urlencode({'q': query})[2:] params['url'] = search_url.format(query=query) diff --git a/searx/engines/mediawiki.py b/searx/engines/mediawiki.py index 00ad0f106..bc4aab6df 100644 --- a/searx/engines/mediawiki.py +++ b/searx/engines/mediawiki.py @@ -3,10 +3,12 @@ from urllib import urlencode, quote url = 'https://en.wikipedia.org/' +search_url = url + 'w/api.php?action=query&list=search&{query}&srprop=timestamp&format=json' # noqa + number_of_results = 10 + def request(query, params): - search_url = url + 'w/api.php?action=query&list=search&{query}&srprop=timestamp&format=json' params['url'] = search_url.format(query=urlencode({'srsearch': query})) return params @@ -14,7 +16,5 @@ def request(query, params): def response(resp): search_results = loads(resp.text) res = search_results.get('query', {}).get('search', []) - - return [{'url': url + 'wiki/' + quote(result['title'].replace(' ', '_').encode('utf-8')), + return [{'url': url + 'wiki/' + quote(result['title'].replace(' ', '_').encode('utf-8')), # noqa 'title': result['title']} for result in res[:int(number_of_results)]] - diff --git a/searx/engines/piratebay.py b/searx/engines/piratebay.py index 9cf410106..7319b49c1 100644 --- a/searx/engines/piratebay.py +++ b/searx/engines/piratebay.py @@ -7,13 +7,18 @@ categories = ['videos', 'music'] url = 'https://thepiratebay.se/' search_url = url + 'search/{search_term}/0/99/{search_type}' -search_types = {'videos': '200' - ,'music' : '100' - ,'files' : '0' - } +search_types = {'videos': '200', + 'music': '100', + 'files': '0'} + +magnet_xpath = './/a[@title="Download this torrent using magnet"]' +content_xpath = './/font[@class="detDesc"]//text()' + def request(query, params): - params['url'] = search_url.format(search_term=quote(query), search_type=search_types.get(params['category'])) + search_type = search_types.get(params['category']) + params['url'] = search_url.format(search_term=quote(query), + search_type=search_type) return params @@ -27,10 +32,14 @@ def response(resp): link = result.xpath('.//div[@class="detName"]//a')[0] href = urljoin(url, link.attrib.get('href')) title = ' '.join(link.xpath('.//text()')) - content = escape(' '.join(result.xpath('.//font[@class="detDesc"]//text()'))) + content = escape(' '.join(result.xpath(content_xpath))) seed, leech = result.xpath('.//td[@align="right"]/text()')[:2] - magnetlink = result.xpath('.//a[@title="Download this torrent using magnet"]')[0] - results.append({'url': href, 'title': title, 'content': content, - 'seed': seed, 'leech': leech, 'magnetlink': magnetlink.attrib['href'], + magnetlink = result.xpath(magnet_xpath)[0] + results.append({'url': href, + 'title': title, + 'content': content, + 'seed': seed, + 'leech': leech, + 'magnetlink': magnetlink.attrib['href'], 'template': 'torrent.html'}) return results diff --git a/searx/engines/soundcloud.py b/searx/engines/soundcloud.py index 50414f153..b1930b2ee 100644 --- a/searx/engines/soundcloud.py +++ b/searx/engines/soundcloud.py @@ -5,7 +5,8 @@ categories = ['music'] guest_client_id = 'b45b1aa10f1ac2941910a7f0d10f8e28' url = 'https://api.soundcloud.com/' -search_url = url + 'search?{query}&facet=model&limit=20&offset=0&linked_partitioning=1&client_id='+guest_client_id +search_url = url + 'search?{query}&facet=model&limit=20&offset=0&linked_partitioning=1&client_id='+guest_client_id # noqa + def request(query, params): global search_url @@ -21,5 +22,7 @@ def response(resp): if result['kind'] in ('track', 'playlist'): title = result['title'] content = result['description'] - results.append({'url': result['permalink_url'], 'title': title, 'content': content}) + results.append({'url': result['permalink_url'], + 'title': title, + 'content': content}) return results diff --git a/searx/engines/stackoverflow.py b/searx/engines/stackoverflow.py index 9ee89bc6e..35230600f 100644 --- a/searx/engines/stackoverflow.py +++ b/searx/engines/stackoverflow.py @@ -7,6 +7,8 @@ categories = ['it'] url = 'http://stackoverflow.com/' search_url = url+'search?' +result_xpath = './/div[@class="excerpt"]//text()' + def request(query, params): params['url'] = search_url + urlencode({'q': query}) @@ -20,6 +22,6 @@ def response(resp): link = result.xpath('.//div[@class="result-link"]//a')[0] href = urljoin(url, link.attrib.get('href')) title = escape(' '.join(link.xpath('.//text()'))) - content = escape(' '.join(result.xpath('.//div[@class="excerpt"]//text()'))) + content = escape(' '.join(result.xpath(result_xpath))) results.append({'url': href, 'title': title, 'content': content}) return results diff --git a/searx/engines/startpage.py b/searx/engines/startpage.py index 87c091e2d..d6d7cf44d 100644 --- a/searx/engines/startpage.py +++ b/searx/engines/startpage.py @@ -1,11 +1,10 @@ from urllib import urlencode from lxml import html -from urlparse import urlparse -from cgi import escape base_url = 'https://startpage.com/' search_url = base_url+'do/search' + def request(query, params): global search_url query = urlencode({'q': query})[2:] @@ -20,11 +19,10 @@ def response(resp): results = [] dom = html.fromstring(resp.content) # ads xpath //div[@id="results"]/div[@id="sponsored"]//div[@class="result"] - # not ads : div[@class="result"] are the direct childs of div[@id="results"] + # not ads: div[@class="result"] are the direct childs of div[@id="results"] for result in dom.xpath('//div[@id="results"]/div[@class="result"]'): link = result.xpath('.//h3/a')[0] url = link.attrib.get('href') - parsed_url = urlparse(url) title = link.text_content() content = result.xpath('./p[@class="desc"]')[0].text_content() results.append({'url': url, 'title': title, 'content': content}) diff --git a/searx/engines/twitter.py b/searx/engines/twitter.py index f9d9e26ad..23393ac4d 100644 --- a/searx/engines/twitter.py +++ b/searx/engines/twitter.py @@ -7,6 +7,9 @@ categories = ['social media'] base_url = 'https://twitter.com/' search_url = base_url+'search?' +title_xpath = './/span[@class="username js-action-profile-name"]//text()' +content_xpath = './/p[@class="js-tweet-text tweet-text"]//text()' + def request(query, params): global search_url @@ -21,7 +24,9 @@ def response(resp): for tweet in dom.xpath('//li[@data-item-type="tweet"]'): link = tweet.xpath('.//small[@class="time"]//a')[0] url = urljoin(base_url, link.attrib.get('href')) - title = ''.join(tweet.xpath('.//span[@class="username js-action-profile-name"]//text()')) - content = escape(''.join(tweet.xpath('.//p[@class="js-tweet-text tweet-text"]//text()'))) - results.append({'url': url, 'title': title, 'content': content}) + title = ''.join(tweet.xpath(title_xpath)) + content = escape(''.join(tweet.xpath(content_xpath))) + results.append({'url': url, + 'title': title, + 'content': content}) return results diff --git a/searx/engines/vimeo.py b/searx/engines/vimeo.py index 35bc3d50a..924497a99 100644 --- a/searx/engines/vimeo.py +++ b/searx/engines/vimeo.py @@ -5,27 +5,31 @@ from lxml import html base_url = 'http://vimeo.com' search_url = base_url + '/search?{query}' -url_xpath = None +url_xpath = None content_xpath = None -title_xpath = None +title_xpath = None results_xpath = '' +content_tpl = ' ' -# the cookie set by vimeo contains all the following values, but only __utma seems to be requiered +# the cookie set by vimeo contains all the following values, +# but only __utma seems to be requiered cookie = { #'vuid':'918282893.1027205400' # 'ab_bs':'%7B%223%22%3A279%7D' - '__utma':'00000000.000#0000000.0000000000.0000000000.0000000000.0' + '__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)' + #, '__utmz':'18#302654.1388942090.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)' # noqa #, '__utml':'search' } + def request(query, params): - params['url'] = search_url.format(query=urlencode({'q' :query})) + params['url'] = search_url.format(query=urlencode({'q': query})) params['cookies'] = cookie return params + def response(resp): results = [] dom = html.fromstring(resp.text) @@ -36,10 +40,9 @@ def response(resp): url = base_url + result.xpath(url_xpath)[0] title = p.unescape(extract_text(result.xpath(title_xpath))) thumbnail = extract_text(result.xpath(content_xpath)[0]) - content = ' '.format(url, title, thumbnail) - results.append({'url': url - , 'title': title - , 'content': content - , 'template':'videos.html' - , 'thumbnail': thumbnail}) + results.append({'url': url, + 'title': title, + 'content': content_tpl.format(url, title, thumbnail), + 'template': 'videos.html', + 'thumbnail': thumbnail}) return results diff --git a/searx/engines/xpath.py b/searx/engines/xpath.py index 5e2c3c38b..a7d24e2a2 100644 --- a/searx/engines/xpath.py +++ b/searx/engines/xpath.py @@ -1,21 +1,24 @@ from lxml import html from urllib import urlencode, unquote from urlparse import urlparse, urljoin -from cgi import escape from lxml.etree import _ElementStringResult -search_url = None -url_xpath = None +search_url = None +url_xpath = None content_xpath = None -title_xpath = None +title_xpath = None suggestion_xpath = '' results_xpath = '' + ''' if xpath_results is list, extract the text from each result and concat the list -if xpath_results is a xml element, extract all the text node from it ( text_content() method from lxml ) +if xpath_results is a xml element, extract all the text node from it + ( text_content() method from lxml ) if xpath_results is a string element, then it's already done ''' + + def extract_text(xpath_results): if type(xpath_results) == list: # it's list of result : concat everything using recursive call @@ -60,7 +63,8 @@ def normalize_url(url): url += '/' # FIXME : hack for yahoo - if parsed_url.hostname == 'search.yahoo.com' and parsed_url.path.startswith('/r'): + if parsed_url.hostname == 'search.yahoo.com'\ + and parsed_url.path.startswith('/r'): p = parsed_url.path mark = p.find('/**') if mark != -1: @@ -82,15 +86,15 @@ def response(resp): 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 ]) + 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)), \ - ): + 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}) if not suggestion_xpath: diff --git a/searx/engines/yacy.py b/searx/engines/yacy.py index c93ac522f..a4a41ac3b 100644 --- a/searx/engines/yacy.py +++ b/searx/engines/yacy.py @@ -4,10 +4,12 @@ from urllib import urlencode url = 'http://localhost:8090' search_url = '/yacysearch.json?{query}&maximumRecords=10' + def request(query, params): - params['url'] = url + search_url.format(query=urlencode({'query':query})) + params['url'] = url + search_url.format(query=urlencode({'query': query})) return params + def response(resp): raw_search_results = loads(resp.text) @@ -25,7 +27,7 @@ def response(resp): tmp_result['content'] = '' if len(result['description']): - tmp_result['content'] += result['description'] +"
" + tmp_result['content'] += result['description'] + "
" if len(result['pubDate']): tmp_result['content'] += result['pubDate'] + "
" diff --git a/searx/engines/youtube.py b/searx/engines/youtube.py index cefdb6536..62884702f 100644 --- a/searx/engines/youtube.py +++ b/searx/engines/youtube.py @@ -5,6 +5,7 @@ categories = ['videos'] search_url = 'https://gdata.youtube.com/feeds/api/videos?alt=json&{query}' + def request(query, params): params['url'] = search_url.format(query=urlencode({'q': query})) return params @@ -30,17 +31,16 @@ def response(resp): thumbnail = '' if len(result['media$group']['media$thumbnail']): thumbnail = result['media$group']['media$thumbnail'][0]['url'] - content += ''.format(url, thumbnail) + content += ''.format(url, thumbnail) # noqa if len(content): content += '
' + result['content']['$t'] else: content = result['content']['$t'] - results.append({'url': url - , 'title': title - , 'content': content - , 'template':'videos.html' - , 'thumbnail':thumbnail}) + results.append({'url': url, + 'title': title, + 'content': content, + 'template': 'videos.html', + 'thumbnail': thumbnail}) return results - diff --git a/searx/utils.py b/searx/utils.py index 4b8cb615c..af8ce952e 100644 --- a/searx/utils.py +++ b/searx/utils.py @@ -1,14 +1,15 @@ from HTMLParser import HTMLParser #import htmlentitydefs import csv -import codecs +from codecs import getincrementalencoder import cStringIO import re def gen_useragent(): # TODO - return "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0" + ua = "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0" + return ua def highlight_content(content, query): @@ -46,7 +47,10 @@ class HTMLTextExtractor(HTMLParser): self.result.append(d) def handle_charref(self, number): - codepoint = int(number[1:], 16) if number[0] in (u'x', u'X') else int(number) + if number[0] in (u'x', u'X'): + codepoint = int(number[1:], 16) + else: + codepoint = int(number) self.result.append(unichr(codepoint)) def handle_entityref(self, name): @@ -75,10 +79,16 @@ class UnicodeWriter: self.queue = cStringIO.StringIO() self.writer = csv.writer(self.queue, dialect=dialect, **kwds) self.stream = f - self.encoder = codecs.getincrementalencoder(encoding)() + self.encoder = getincrementalencoder(encoding)() def writerow(self, row): - self.writer.writerow([(s.encode("utf-8").strip() if type(s) == str or type(s) == unicode else str(s)) for s in row]) + unicode_row = [] + for col in row: + if type(col) == str or type(col) == unicode: + unicode_row.append(col.encode('utf-8').strip()) + else: + unicode_row.append(col) + self.writer.writerow(unicode_row) # Fetch UTF-8 output from the queue ... data = self.queue.getvalue() data = data.decode("utf-8") diff --git a/searx/webapp.py b/searx/webapp.py index a8902f635..9cefb3712 100644 --- a/searx/webapp.py +++ b/searx/webapp.py @@ -18,7 +18,8 @@ along with searx. If not, see < http://www.gnu.org/licenses/ >. ''' from searx import settings -from flask import Flask, request, render_template, url_for, Response, make_response, redirect +from flask import Flask, request, render_template +from flask import url_for, Response, make_response, redirect from searx.engines import search, categories, engines, get_engines_stats import json import cStringIO @@ -70,7 +71,8 @@ def get_base_url(): def render(template_name, **kwargs): global categories kwargs['categories'] = ['general'] - kwargs['categories'].extend(x for x in sorted(categories.keys()) if x != 'general') + kwargs['categories'].extend(x for x in + sorted(categories.keys()) if x != 'general') if not 'selected_categories' in kwargs: kwargs['selected_categories'] = [] cookie_categories = request.cookies.get('categories', '').split(',') @@ -114,7 +116,8 @@ def index(): continue selected_categories.append(category) if not len(selected_categories): - cookie_categories = request.cookies.get('categories', '').split(',') + cookie_categories = request.cookies.get('categories', '') + cookie_categories = cookie_categories.split(',') for ccateg in cookie_categories: if ccateg in categories: selected_categories.append(ccateg) @@ -122,7 +125,9 @@ def index(): selected_categories = ['general'] for categ in selected_categories: - selected_engines.extend({'category': categ, 'name': x.name} for x in categories[categ]) + selected_engines.extend({'category': categ, + 'name': x.name} + for x in categories[categ]) results, suggestions = search(query, request, selected_engines) @@ -137,7 +142,8 @@ def index(): result['content'] = html_to_text(result['content']).strip() result['title'] = html_to_text(result['title']).strip() if len(result['url']) > 74: - result['pretty_url'] = result['url'][:35] + '[..]' + result['url'][-35:] + url_parts = result['url'][:35], result['url'][-35:] + result['pretty_url'] = '{0}[...]{1}'.format(*url_parts) else: result['pretty_url'] = result['url'] @@ -146,7 +152,8 @@ def index(): result['favicon'] = engine if request_data.get('format') == 'json': - return Response(json.dumps({'query': query, 'results': results}), mimetype='application/json') + return Response(json.dumps({'query': query, 'results': results}), + mimetype='application/json') elif request_data.get('format') == 'csv': csv = UnicodeWriter(cStringIO.StringIO()) keys = ('title', 'url', 'content', 'host', 'engine', 'score') @@ -157,7 +164,8 @@ def index(): csv.writerow([row.get(key, '') for key in keys]) csv.stream.seek(0) response = Response(csv.stream.read(), mimetype='application/csv') - response.headers.add('Content-Disposition', 'attachment;Filename=searx_-_{0}.csv'.format('_'.join(query.split()))) + content_disp = 'attachment;Filename=searx_-_{0}.csv'.format(query) + response.headers.add('Content-Disposition', content_disp) return response elif request_data.get('format') == 'rss': response_rss = render( @@ -240,15 +248,16 @@ def opensearch(): base_url = get_base_url() ret = opensearch_xml.format(method=method, host=base_url) resp = Response(response=ret, - status=200, - mimetype="application/xml") + status=200, + mimetype="application/xml") return resp @app.route('/favicon.ico') def favicon(): return send_from_directory(os.path.join(app.root_path, 'static/img'), - 'favicon.png', mimetype='image/vnd.microsoft.icon') + 'favicon.png', + mimetype='image/vnd.microsoft.icon') def run():