Merge pull request #346 from Cqoicebordel/youtube

Adds engines : Youtube with or without API and multiple Qwant

3 files changed, 253 insertions, 0 deletions

diff --git a/searx/engines/qwant.py b/searx/engines/qwant.py
new file mode 100644
index 000000000..872bd4e95
--- /dev/null
+++ b/searx/engines/qwant.py
@@ -0,0 +1,98 @@
+"""
+ Qwant (Web, Images, News, Social)
+
+ @website     https://qwant.com/
+ @provide-api not officially (https://api.qwant.com/api/search/)
+
+ @using-api   yes
+ @results     JSON
+ @stable      yes
+ @parse       url, title, content
+"""
+
+from urllib import urlencode
+from json import loads
+from datetime import datetime
+
+# engine dependent config
+categories = None
+paging = True
+language_support = True
+
+category_to_keyword = {'general': 'web',
+                       'images': 'images',
+                       'news': 'news',
+                       'social media': 'social'}
+
+# search-url
+url = 'https://api.qwant.com/api/search/{keyword}?count=10&offset={offset}&f=&{query}'
+
+
+# do search-request
+def request(query, params):
+    offset = (params['pageno'] - 1) * 10
+
+    if categories[0] and categories[0] in category_to_keyword:
+
+        params['url'] = url.format(keyword=category_to_keyword[categories[0]],
+                                   query=urlencode({'q': query}),
+                                   offset=offset)
+    else:
+        params['url'] = url.format(keyword='web',
+                                   query=urlencode({'q': query}),
+                                   offset=offset)
+
+    # add language tag if specified
+    if params['language'] != 'all':
+        params['url'] += '&locale=' + params['language'].lower()
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    search_results = loads(resp.text)
+
+    # return empty array if there are no results
+    if 'data' not in search_results:
+        return []
+
+    data = search_results.get('data', {})
+
+    res = data.get('result', {})
+
+    # parse results
+    for result in res.get('items', {}):
+
+        title = result['title']
+        res_url = result['url']
+        content = result['desc']
+
+        if category_to_keyword.get(categories[0], '') == 'web':
+            results.append({'title': title,
+                            'content': content,
+                            'url': res_url})
+
+        elif category_to_keyword.get(categories[0], '') == 'images':
+            thumbnail_src = result['thumbnail']
+            img_src = result['media']
+            results.append({'template': 'images.html',
+                            'url': res_url,
+                            'title': title,
+                            'content': '',
+                            'thumbnail_src': thumbnail_src,
+                            'img_src': img_src})
+
+        elif (category_to_keyword.get(categories[0], '') == 'news' or
+              category_to_keyword.get(categories[0], '') == 'social'):
+            published_date = datetime.fromtimestamp(result['date'], None)
+
+            results.append({'url': res_url,
+                            'title': title,
+                            'publishedDate': published_date,
+                            'content': content})
+
+    # return results
+    return results
diff --git a/searx/engines/youtube_api.py b/searx/engines/youtube_api.py
new file mode 100644
index 000000000..8fd939a25
--- /dev/null
+++ b/searx/engines/youtube_api.py
@@ -0,0 +1,83 @@
+# Youtube (Videos)
+#
+# @website     https://www.youtube.com/
+# @provide-api yes (https://developers.google.com/apis-explorer/#p/youtube/v3/youtube.search.list)
+#
+# @using-api   yes
+# @results     JSON
+# @stable      yes
+# @parse       url, title, content, publishedDate, thumbnail, embedded
+
+from json import loads
+from urllib import urlencode
+from dateutil import parser
+
+# engine dependent config
+categories = ['videos', 'music']
+paging = False
+language_support = True
+api_key = None
+
+# search-url
+base_url = 'https://www.googleapis.com/youtube/v3/search'
+search_url = base_url + '?part=snippet&{query}&maxResults=20&key={api_key}'
+
+embedded_url = '<iframe width="540" height="304" ' +\
+    'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\
+    'frameborder="0" allowfullscreen></iframe>'
+
+base_youtube_url = 'https://www.youtube.com/watch?v='
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(query=urlencode({'q': query}),
+                                      api_key=api_key)
+
+    # add language tag if specified
+    if params['language'] != 'all':
+        params['url'] += '&relevanceLanguage=' + params['language'].split('_')[0]
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    search_results = loads(resp.text)
+
+    # return empty array if there are no results
+    if 'items' not in search_results:
+        return []
+
+    # parse results
+    for result in search_results['items']:
+        videoid = result['id']['videoId']
+
+        title = result['snippet']['title']
+        content = ''
+        thumbnail = ''
+
+        pubdate = result['snippet']['publishedAt']
+        publishedDate = parser.parse(pubdate)
+
+        thumbnail = result['snippet']['thumbnails']['high']['url']
+
+        content = result['snippet']['description']
+
+        url = base_youtube_url + videoid
+
+        embedded = embedded_url.format(videoid=videoid)
+
+        # append result
+        results.append({'url': url,
+                        'title': title,
+                        'content': content,
+                        'template': 'videos.html',
+                        'publishedDate': publishedDate,
+                        'embedded': embedded,
+                        'thumbnail': thumbnail})
+
+    # return results
+    return results
diff --git a/searx/engines/youtube_noapi.py b/searx/engines/youtube_noapi.py
new file mode 100644
index 000000000..f78e43f0f
--- /dev/null
+++ b/searx/engines/youtube_noapi.py
@@ -0,0 +1,72 @@
+# Youtube (Videos)
+#
+# @website     https://www.youtube.com/
+# @provide-api yes (https://developers.google.com/apis-explorer/#p/youtube/v3/youtube.search.list)
+#
+# @using-api   no
+# @results     HTML
+# @stable      no
+# @parse       url, title, content, publishedDate, thumbnail, embedded
+
+from urllib import quote_plus
+from lxml import html
+from searx.engines.xpath import extract_text
+
+# engine dependent config
+categories = ['videos', 'music']
+paging = True
+language_support = False
+
+# search-url
+base_url = 'https://www.youtube.com/results'
+search_url = base_url + '?search_query={query}&page={page}'
+
+embedded_url = '<iframe width="540" height="304" ' +\
+    'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\
+    'frameborder="0" allowfullscreen></iframe>'
+
+base_youtube_url = 'https://www.youtube.com/watch?v='
+
+# specific xpath variables
+results_xpath = "//ol/li/div[contains(@class, 'yt-lockup yt-lockup-tile yt-lockup-video vve-check')]"
+url_xpath = './/h3/a/@href'
+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"]'
+
+
+# do search-request
+def request(query, params):
+    params['url'] = search_url.format(query=quote_plus(query),
+                                      page=params['pageno'])
+
+    return params
+
+
+# get response from search-request
+def response(resp):
+    results = []
+
+    dom = html.fromstring(resp.text)
+
+    # 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})
+
+    # return results
+    return results