From ffcec383b7355c6ca8b60da8579a43019d7d7e6b Mon Sep 17 00:00:00 2001 From: dalf Date: Sun, 7 Dec 2014 16:36:20 +0100 Subject: [PATCH] [fix] pep8 : duckduckgo_definitions and wikidata engines --- searx/engines/duckduckgo_definitions.py | 77 ++++++---- searx/engines/wikidata.py | 181 ++++++++++++++++-------- 2 files changed, 168 insertions(+), 90 deletions(-) diff --git a/searx/engines/duckduckgo_definitions.py b/searx/engines/duckduckgo_definitions.py index c008f22f7..8f81d2c8e 100644 --- a/searx/engines/duckduckgo_definitions.py +++ b/searx/engines/duckduckgo_definitions.py @@ -3,21 +3,25 @@ from urllib import urlencode from lxml import html from searx.engines.xpath import extract_text -url = 'https://api.duckduckgo.com/?{query}&format=json&pretty=0&no_redirect=1&d=1' +url = 'https://api.duckduckgo.com/'\ + + '?{query}&format=json&pretty=0&no_redirect=1&d=1' + def result_to_text(url, text, htmlResult): # TODO : remove result ending with "Meaning" or "Category" dom = html.fromstring(htmlResult) a = dom.xpath('//a') - if len(a)>=1: + if len(a) >= 1: return extract_text(a[0]) else: return text + def html_to_text(htmlFragment): dom = html.fromstring(htmlFragment) return extract_text(dom) + def request(query, params): # TODO add kl={locale} params['url'] = url.format(query=urlencode({'q': query})) @@ -38,16 +42,15 @@ def response(resp): # add answer if there is one answer = search_res.get('Answer', '') if answer != '': - results.append({ 'answer' : html_to_text(answer) }) + results.append({'answer': html_to_text(answer)}) # add infobox if 'Definition' in search_res: - content = content + search_res.get('Definition', '') + content = content + search_res.get('Definition', '') if 'Abstract' in search_res: content = content + search_res.get('Abstract', '') - # image image = search_res.get('Image', '') image = None if image == '' else image @@ -55,29 +58,35 @@ def response(resp): # attributes if 'Infobox' in search_res: infobox = search_res.get('Infobox', None) - if 'content' in infobox: + if 'content' in infobox: for info in infobox.get('content'): - attributes.append({'label': info.get('label'), 'value': info.get('value')}) + attributes.append({'label': info.get('label'), + 'value': info.get('value')}) # urls for ddg_result in search_res.get('Results', []): if 'FirstURL' in ddg_result: firstURL = ddg_result.get('FirstURL', '') text = ddg_result.get('Text', '') - urls.append({'title':text, 'url':firstURL}) - results.append({'title':heading, 'url': firstURL}) + urls.append({'title': text, 'url': firstURL}) + results.append({'title': heading, 'url': firstURL}) # related topics for ddg_result in search_res.get('RelatedTopics', None): if 'FirstURL' in ddg_result: - suggestion = result_to_text(ddg_result.get('FirstURL', None), ddg_result.get('Text', None), ddg_result.get('Result', None)) + suggestion = result_to_text(ddg_result.get('FirstURL', None), + ddg_result.get('Text', None), + ddg_result.get('Result', None)) if suggestion != heading: results.append({'suggestion': suggestion}) elif 'Topics' in ddg_result: suggestions = [] - relatedTopics.append({ 'name' : ddg_result.get('Name', ''), 'suggestions': suggestions }) + relatedTopics.append({'name': ddg_result.get('Name', ''), + 'suggestions': suggestions}) for topic_result in ddg_result.get('Topics', []): - suggestion = result_to_text(topic_result.get('FirstURL', None), topic_result.get('Text', None), topic_result.get('Result', None)) + suggestion = result_to_text(topic_result.get('FirstURL', None), + topic_result.get('Text', None), + topic_result.get('Result', None)) if suggestion != heading: suggestions.append(suggestion) @@ -86,21 +95,26 @@ def response(resp): if abstractURL != '': # add as result ? problem always in english infobox_id = abstractURL - urls.append({'title': search_res.get('AbstractSource'), 'url': abstractURL}) + urls.append({'title': search_res.get('AbstractSource'), + 'url': abstractURL}) # definition definitionURL = search_res.get('DefinitionURL', '') if definitionURL != '': # add as result ? as answer ? problem always in english infobox_id = definitionURL - urls.append({'title': search_res.get('DefinitionSource'), 'url': definitionURL}) + urls.append({'title': search_res.get('DefinitionSource'), + 'url': definitionURL}) # entity entity = search_res.get('Entity', None) - # TODO continent / country / department / location / waterfall / mountain range : link to map search, get weather, near by locations + # TODO continent / country / department / location / waterfall / + # mountain range : + # link to map search, get weather, near by locations # TODO musician : link to music search # TODO concert tour : ?? - # TODO film / actor / television / media franchise : links to IMDB / rottentomatoes (or scrap result) + # TODO film / actor / television / media franchise : + # links to IMDB / rottentomatoes (or scrap result) # TODO music : link tu musicbrainz / last.fm # TODO book : ?? # TODO artist / playwright : ?? @@ -114,24 +128,25 @@ def response(resp): # TODO programming language : ?? # TODO file format : ?? - if len(heading)>0: + if len(heading) > 0: # TODO get infobox.meta.value where .label='article_title' - if image==None and len(attributes)==0 and len(urls)==1 and len(relatedTopics)==0 and len(content)==0: + if image is None and len(attributes) == 0 and len(urls) == 1 and\ + len(relatedTopics) == 0 and len(content) == 0: results.append({ - 'url': urls[0]['url'], - 'title': heading, - 'content': content - }) + 'url': urls[0]['url'], + 'title': heading, + 'content': content + }) else: results.append({ - 'infobox': heading, - 'id': infobox_id, - 'entity': entity, - 'content': content, - 'img_src' : image, - 'attributes': attributes, - 'urls': urls, - 'relatedTopics': relatedTopics - }) + 'infobox': heading, + 'id': infobox_id, + 'entity': entity, + 'content': content, + 'img_src': image, + 'attributes': attributes, + 'urls': urls, + 'relatedTopics': relatedTopics + }) return results diff --git a/searx/engines/wikidata.py b/searx/engines/wikidata.py index 7877e1198..ab799e6ce 100644 --- a/searx/engines/wikidata.py +++ b/searx/engines/wikidata.py @@ -2,13 +2,25 @@ import json from requests import get from urllib import urlencode -resultCount=1 -urlSearch = 'https://www.wikidata.org/w/api.php?action=query&list=search&format=json&srnamespace=0&srprop=sectiontitle&{query}' -urlDetail = 'https://www.wikidata.org/w/api.php?action=wbgetentities&format=json&props=labels%7Cinfo%7Csitelinks%7Csitelinks%2Furls%7Cdescriptions%7Cclaims&{query}' -urlMap = 'https://www.openstreetmap.org/?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M' +result_count = 1 +wikidata_host = 'https://www.wikidata.org' +wikidata_api = wikidata_host + '/w/api.php' +url_search = wikidata_api \ + + '?action=query&list=search&format=json'\ + + '&srnamespace=0&srprop=sectiontitle&{query}' +url_detail = wikidata_api\ + + '?action=wbgetentities&format=json'\ + + '&props=labels%7Cinfo%7Csitelinks'\ + + '%7Csitelinks%2Furls%7Cdescriptions%7Cclaims'\ + + '&{query}' +url_map = 'https://www.openstreetmap.org/'\ + + '?lat={latitude}&lon={longitude}&zoom={zoom}&layers=M' + def request(query, params): - params['url'] = urlSearch.format(query=urlencode({'srsearch': query, 'srlimit': resultCount})) + params['url'] = url_search.format( + query=urlencode({'srsearch': query, + 'srlimit': result_count})) return params @@ -23,7 +35,8 @@ def response(resp): language = resp.search_params['language'].split('_')[0] if language == 'all': language = 'en' - url = urlDetail.format(query=urlencode({'ids': '|'.join(wikidata_ids), 'languages': language + '|en'})) + url = url_detail.format(query=urlencode({'ids': '|'.join(wikidata_ids), + 'languages': language + '|en'})) htmlresponse = get(url) jsonresponse = json.loads(htmlresponse.content) @@ -32,6 +45,7 @@ def response(resp): return results + def getDetail(jsonresponse, wikidata_id, language): results = [] urls = [] @@ -40,60 +54,103 @@ def getDetail(jsonresponse, wikidata_id, language): result = jsonresponse.get('entities', {}).get(wikidata_id, {}) title = result.get('labels', {}).get(language, {}).get('value', None) - if title == None: + if title is None: title = result.get('labels', {}).get('en', {}).get('value', None) - if title == None: + if title is None: return results - description = result.get('descriptions', {}).get(language, {}).get('value', None) - if description == None: - description = result.get('descriptions', {}).get('en', {}).get('value', '') + description = result\ + .get('descriptions', {})\ + .get(language, {})\ + .get('value', None) + + if description is None: + description = result\ + .get('descriptions', {})\ + .get('en', {})\ + .get('value', '') claims = result.get('claims', {}) official_website = get_string(claims, 'P856', None) - if official_website != None: - urls.append({ 'title' : 'Official site', 'url': official_website }) - results.append({ 'title': title, 'url' : official_website }) + if official_website is not None: + urls.append({'title': 'Official site', 'url': official_website}) + results.append({'title': title, 'url': official_website}) wikipedia_link_count = 0 if language != 'en': - wikipedia_link_count += add_url(urls, 'Wikipedia (' + language + ')', get_wikilink(result, language + 'wiki')) + wikipedia_link_count += add_url(urls, + 'Wikipedia (' + language + ')', + get_wikilink(result, language + + 'wiki')) wikipedia_en_link = get_wikilink(result, 'enwiki') - wikipedia_link_count += add_url(urls, 'Wikipedia (en)', wikipedia_en_link) + wikipedia_link_count += add_url(urls, + 'Wikipedia (en)', + wikipedia_en_link) if wikipedia_link_count == 0: misc_language = get_wiki_firstlanguage(result, 'wiki') - if misc_language != None: - add_url(urls, 'Wikipedia (' + misc_language + ')', get_wikilink(result, misc_language + 'wiki')) + if misc_language is not None: + add_url(urls, + 'Wikipedia (' + misc_language + ')', + get_wikilink(result, misc_language + 'wiki')) if language != 'en': - add_url(urls, 'Wiki voyage (' + language + ')', get_wikilink(result, language + 'wikivoyage')) - add_url(urls, 'Wiki voyage (en)', get_wikilink(result, 'enwikivoyage')) + add_url(urls, + 'Wiki voyage (' + language + ')', + get_wikilink(result, language + 'wikivoyage')) + + add_url(urls, + 'Wiki voyage (en)', + get_wikilink(result, 'enwikivoyage')) if language != 'en': - add_url(urls, 'Wikiquote (' + language + ')', get_wikilink(result, language + 'wikiquote')) - add_url(urls, 'Wikiquote (en)', get_wikilink(result, 'enwikiquote')) + add_url(urls, + 'Wikiquote (' + language + ')', + get_wikilink(result, language + 'wikiquote')) - add_url(urls, 'Commons wiki', get_wikilink(result, 'commonswiki')) + add_url(urls, + 'Wikiquote (en)', + get_wikilink(result, 'enwikiquote')) - add_url(urls, 'Location', get_geolink(claims, 'P625', None)) + add_url(urls, + 'Commons wiki', + get_wikilink(result, 'commonswiki')) - add_url(urls, 'Wikidata', 'https://www.wikidata.org/wiki/' + wikidata_id + '?uselang='+ language) + add_url(urls, + 'Location', + get_geolink(claims, 'P625', None)) + + add_url(urls, + 'Wikidata', + 'https://www.wikidata.org/wiki/' + + wikidata_id + '?uselang=' + language) musicbrainz_work_id = get_string(claims, 'P435') - if musicbrainz_work_id != None: - add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/work/' + musicbrainz_work_id) + if musicbrainz_work_id is not None: + add_url(urls, + 'MusicBrainz', + 'http://musicbrainz.org/work/' + + musicbrainz_work_id) musicbrainz_artist_id = get_string(claims, 'P434') - if musicbrainz_artist_id != None: - add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/artist/' + musicbrainz_artist_id) + if musicbrainz_artist_id is not None: + add_url(urls, + 'MusicBrainz', + 'http://musicbrainz.org/artist/' + + musicbrainz_artist_id) musicbrainz_release_group_id = get_string(claims, 'P436') - if musicbrainz_release_group_id != None: - add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/release-group/' + musicbrainz_release_group_id) + if musicbrainz_release_group_id is not None: + add_url(urls, + 'MusicBrainz', + 'http://musicbrainz.org/release-group/' + + musicbrainz_release_group_id) musicbrainz_label_id = get_string(claims, 'P966') - if musicbrainz_label_id != None: - add_url(urls, 'MusicBrainz', 'http://musicbrainz.org/label/' + musicbrainz_label_id) + if musicbrainz_label_id is not None: + add_url(urls, + 'MusicBrainz', + 'http://musicbrainz.org/label/' + + musicbrainz_label_id) # musicbrainz_area_id = get_string(claims, 'P982') # P1407 MusicBrainz series ID @@ -102,42 +159,43 @@ def getDetail(jsonresponse, wikidata_id, language): # P1407 MusicBrainz series ID postal_code = get_string(claims, 'P281', None) - if postal_code != None: - attributes.append({'label' : 'Postal code(s)', 'value' : postal_code}) + if postal_code is not None: + attributes.append({'label': 'Postal code(s)', 'value': postal_code}) date_of_birth = get_time(claims, 'P569', None) - if date_of_birth != None: - attributes.append({'label' : 'Date of birth', 'value' : date_of_birth}) + if date_of_birth is not None: + attributes.append({'label': 'Date of birth', 'value': date_of_birth}) date_of_death = get_time(claims, 'P570', None) - if date_of_death != None: - attributes.append({'label' : 'Date of death', 'value' : date_of_death}) + if date_of_death is not None: + attributes.append({'label': 'Date of death', 'value': date_of_death}) - if len(attributes)==0 and len(urls)==2 and len(description)==0: + if len(attributes) == 0 and len(urls) == 2 and len(description) == 0: results.append({ - 'url': urls[0]['url'], - 'title': title, - 'content': description - }) + 'url': urls[0]['url'], + 'title': title, + 'content': description + }) else: results.append({ - 'infobox' : title, - 'id' : wikipedia_en_link, - 'content' : description, - 'attributes' : attributes, - 'urls' : urls - }) + 'infobox': title, + 'id': wikipedia_en_link, + 'content': description, + 'attributes': attributes, + 'urls': urls + }) return results def add_url(urls, title, url): - if url != None: - urls.append({'title' : title, 'url' : url}) + if url is not None: + urls.append({'title': title, 'url': url}) return 1 else: return 0 + def get_mainsnak(claims, propertyName): propValue = claims.get(propertyName, {}) if len(propValue) == 0: @@ -157,7 +215,7 @@ def get_string(claims, propertyName, defaultValue=None): mainsnak = e.get('mainsnak', {}) datavalue = mainsnak.get('datavalue', {}) - if datavalue != None: + if datavalue is not None: result.append(datavalue.get('value', '')) if len(result) == 0: @@ -177,7 +235,7 @@ def get_time(claims, propertyName, defaultValue=None): mainsnak = e.get('mainsnak', {}) datavalue = mainsnak.get('datavalue', {}) - if datavalue != None: + if datavalue is not None: value = datavalue.get('value', '') result.append(value.get('time', '')) @@ -190,7 +248,7 @@ def get_time(claims, propertyName, defaultValue=None): def get_geolink(claims, propertyName, defaultValue=''): mainsnak = get_mainsnak(claims, propertyName) - if mainsnak == None: + if mainsnak is None: return defaultValue datatype = mainsnak.get('datatype', '') @@ -209,21 +267,25 @@ def get_geolink(claims, propertyName, defaultValue=''): # 1 --> 6 # 0.016666666666667 --> 9 # 0.00027777777777778 --> 19 - # wolframalpha : quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}} + # wolframalpha : + # quadratic fit { {13, 5}, {1, 6}, {0.0166666, 9}, {0.0002777777,19}} # 14.1186-8.8322 x+0.625447 x^2 if precision < 0.0003: zoom = 19 else: zoom = int(15 - precision*8.8322 + precision*precision*0.625447) - url = urlMap.replace('{latitude}', str(value.get('latitude',0))).replace('{longitude}', str(value.get('longitude',0))).replace('{zoom}', str(zoom)) + url = url_map\ + .replace('{latitude}', str(value.get('latitude', 0)))\ + .replace('{longitude}', str(value.get('longitude', 0)))\ + .replace('{zoom}', str(zoom)) return url def get_wikilink(result, wikiid): url = result.get('sitelinks', {}).get(wikiid, {}).get('url', None) - if url == None: + if url is None: return url elif url.startswith('http://'): url = url.replace('http://', 'https://') @@ -231,8 +293,9 @@ def get_wikilink(result, wikiid): url = 'https:' + url return url + def get_wiki_firstlanguage(result, wikipatternid): for k in result.get('sitelinks', {}).keys(): - if k.endswith(wikipatternid) and len(k)==(2+len(wikipatternid)): + if k.endswith(wikipatternid) and len(k) == (2+len(wikipatternid)): return k[0:2] return None