diff options
Diffstat (limited to 'searx/engines/youtube_noapi.py')
| -rw-r--r-- | searx/engines/youtube_noapi.py | 75 |
1 files changed, 38 insertions, 37 deletions
diff --git a/searx/engines/youtube_noapi.py b/searx/engines/youtube_noapi.py index 9f01841f6..49d0ae604 100644 --- a/searx/engines/youtube_noapi.py +++ b/searx/engines/youtube_noapi.py @@ -8,7 +8,8 @@ # @stable no # @parse url, title, content, publishedDate, thumbnail, embedded -from lxml import html +from functools import reduce +from json import loads from searx.engines.xpath import extract_text from searx.utils import list_get from searx.url_utils import quote_plus @@ -29,25 +30,11 @@ time_range_dict = {'day': 'Ag', 'year': 'BQ'} embedded_url = '<iframe width="540" height="304" ' +\ - 'data-src="//www.youtube-nocookie.com/embed/{videoid}" ' +\ + 'data-src="https://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"]' - - -# returns extract_text on the first result selected by the xpath or None -def extract_text_from_dom(result, xpath): - r = result.xpath(xpath) - if len(r) > 0: - return extract_text(r[0]) - return None - # do search-request def request(query, params): @@ -63,27 +50,41 @@ def request(query, params): def response(resp): results = [] - dom = html.fromstring(resp.text) - - # parse results - for result in dom.xpath(results_xpath): - videoid = list_get(result.xpath('@data-context-item-id'), 0) - if videoid is not None: - url = base_youtube_url + videoid - thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg' - - title = extract_text_from_dom(result, title_xpath) or videoid - content = extract_text_from_dom(result, content_xpath) - - embedded = embedded_url.format(videoid=videoid) - - # append result - results.append({'url': url, - 'title': title, - 'content': content, - 'template': 'videos.html', - 'embedded': embedded, - 'thumbnail': thumbnail}) + results_data = resp.text[resp.text.find('ytInitialData'):] + results_data = results_data[results_data.find('{'):results_data.find(';\n')] + + results_json = loads(results_data) if results_data else {} + sections = results_json.get('contents', {})\ + .get('twoColumnSearchResultsRenderer', {})\ + .get('primaryContents', {})\ + .get('sectionListRenderer', {})\ + .get('contents', []) + + for section in sections: + for video_container in section.get('itemSectionRenderer', {}).get('contents', []): + video = video_container.get('videoRenderer', {}) + videoid = video.get('videoId') + if videoid is not None: + url = base_youtube_url + videoid + thumbnail = 'https://i.ytimg.com/vi/' + videoid + '/hqdefault.jpg' + title = get_text_from_json(video.get('title', {})) + content = get_text_from_json(video.get('descriptionSnippet', {})) + 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 + + +def get_text_from_json(element): + if 'runs' in element: + return reduce(lambda a, b: a + b.get('text', ''), element.get('runs'), '') + else: + return element.get('simpleText', '') |