heckyel/libretube
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tipuesearch_content.json: update filter only articles and improved JSON API

Browse Source
This commit is contained in:
Jesús 2020-06-10 16:11:18 -05:00
parent ed201535a3
commit 9d22ec021f
No known key found for this signature in database
GPG Key ID: F6EE7BC59A315766
2 changed files with 76 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
content/pages/buscar.php.md
View File

@ -62,9 +62,9 @@ if (isset($_GET['q'])) {
$keywords = explode(' ', $keywords); $keywords = explode(' ', $keywords);
$found_results = []; $found_results = [];
foreach ($web_content["pages"] as $page) { foreach ($web_content["videos"] as $page) {
$score = 0; $score = 0;
$page['text'] = htmlentities($page['text']); $page['description'] = htmlentities($page['description']);
foreach ($keywords as $word) { foreach ($keywords as $word) {
if (preg_match("/$word/i", $page['url'])) { if (preg_match("/$word/i", $page['url'])) {
@ -78,16 +78,16 @@ if (isset($_GET['q'])) {
} }
// It replaces uppercase matches with lowercase matches, but it's fine for now. // It replaces uppercase matches with lowercase matches, but it's fine for now.
if ($stop_words_ignored == 1) { if ($stop_words_ignored == 1) {
$page['text'] = preg_replace("/$word/i", $word, $page['text'], -1, $match_count); $page['description'] = preg_replace("/$word/i", $word, $page['description'], -1, $match_count);
} else { } else {
$page['text'] = preg_replace("/$word/i", '<span class="tipue_search_content_bold highlighted">' . $word . '</span>', $page['text'], -1, $match_count); $page['description'] = preg_replace("/$word/i", '<span class="tipue_search_content_bold highlighted">' . $word . '</span>', $page['description'], -1, $match_count);
} }
if ($match_count > 0) { if ($match_count > 0) {
$score += 10 * $match_count; $score += 10 * $match_count;
} }
} }
if ($score != 0) { if ($score != 0) {
$found_results[] = ['score' => $score, 'title' => $page['title'], 'url' => $page['url'], 'text' => $page['text']]; $found_results[] = ['score' => $score, 'title' => $page['title'], 'url' => $page['url'], 'description' => $page['description']];
} }
} }
@ -123,7 +123,7 @@ if (isset($_GET['q'])) {
printf('<div class="tipue_search_content_title"><a class="is-cyan" href="%s">%s</a></div>', $found_result['url'], $found_result['title']); printf('<div class="tipue_search_content_title"><a class="is-cyan" href="%s">%s</a></div>', $found_result['url'], $found_result['title']);
printf('<div class="tipue_search_content_url"><a href="%s">%s</a></div>', $found_result['url'], $found_result['url']); printf('<div class="tipue_search_content_url"><a href="%s">%s</a></div>', $found_result['url'], $found_result['url']);
$description_words = explode(' ', $found_result['text']); $description_words = explode(' ', $found_result['description']);
$description_words_count = count($description_words); $description_words_count = count($description_words);
$first_match = false; $first_match = false;
for ($i = 0; $i < $description_words_count; $i++) { for ($i = 0; $i < $description_words_count; $i++) {

99
plugins/tipue-search/tipue_search.py
View File

@ -32,66 +32,107 @@ class Tipue_Search_JSON_Generator(object):
self.siteurl = settings.get('SITEURL') self.siteurl = settings.get('SITEURL')
self.relative_urls = settings.get('RELATIVE_URLS') self.relative_urls = settings.get('RELATIVE_URLS')
self.tpages = settings.get('TEMPLATE_PAGES') self.tpages = settings.get('TEMPLATE_PAGES')
self.tstatic = settings.get('THEME_STATIC_DIR')
self.output_path = output_path self.output_path = output_path
self.json_nodes = [] self.json_nodes = []
def create_json_node(self, page): def create_json_node(self, article):
if getattr(page, 'status', 'published') != 'published': if getattr(article, 'status', 'published') != 'published':
return return
soup_title = BeautifulSoup(page.title.replace('&nbsp;', ' '), 'html.parser') soup_title = BeautifulSoup(article.title.replace('&nbsp;', ' '), 'html.parser')
page_title = soup_title.get_text(' ', strip=True).replace('“', '"').replace('”', '"').replace('’', "'").replace('^', '&#94;') video_title = soup_title.get_text(' ', strip=True).replace('“', '"').replace('”', '"').replace('’', "'").replace('^', '&#94;')
soup_text = BeautifulSoup(page.content, 'html.parser') soup_text = BeautifulSoup(article.content, 'html.parser')
page_text = soup_text.get_text(' ', strip=True).replace('“', '"').replace('”', '"').replace('’', "'").replace('', ' ').replace('^', '&#94;') video_text = soup_text.get_text(' ', strip=True).replace('“', '"').replace('”', '"').replace('’', "'").replace('', ' ').replace('^', '&#94;')
page_text = ' '.join(page_text.split()) video_text = ' '.join(video_text.split())
page_category = page.category.name if getattr(page, 'category', 'None') != 'None' else '' if self.relative_urls:
image_url = '.'
else:
image_url = self.siteurl
page_url = '.' # thumbnail
if page.url: video_image = article.image if getattr(
page_url = page.url if self.relative_urls else (self.siteurl + '/' + page.url) article, 'image', 'None') != 'None' else ''
node = {'title': page_title, url_image = "%s/%s/../wp-content/uploads/article/poster/%s" % (
'text': page_text, image_url, self.tstatic, video_image
'tags': page_category, )
'url': page_url}
# publish
video_publish = article.date.strftime("%a, %d %B, %Y") if getattr(
article, 'date', 'None') != 'None' else ''
# author
video_author = str(article.author) if getattr(
article, 'author', 'None') != 'None' else ''
# time
video_time = article.time if getattr(
article, 'time', 'None') != 'None' else ''
video_url = '.'
if article.url:
video_url = article.url if self.relative_urls else (
self.siteurl + '/' + article.url)
video_src = article.og_video if getattr(
article, 'og_video', 'None') != 'None' else ''
video_category = article.category.name if getattr(
article, 'category', 'None') != 'None' else ''
node = {'title': video_title,
'description': video_text,
'videoThumbnail': url_image,
'formatStreams': {
'url': video_src,
},
'author': video_author,
'publishedText': video_publish,
'time': video_time,
'tags': video_category,
'url': video_url}
self.json_nodes.append(node) self.json_nodes.append(node)
def create_tpage_node(self, srclink): def create_tpage_node(self, srclink):
srcfile = open(os.path.join(self.output_path, self.tpages[srclink]), encoding='utf-8') srcfile = open(os.path.join(self.output_path,
self.tpages[srclink]),
encoding='utf-8')
soup = BeautifulSoup(srcfile, 'html.parser') soup = BeautifulSoup(srcfile, 'html.parser')
page_title = soup.title.string if soup.title is not None else '' video_title = soup.title.string if soup.title is not None else ''
page_text = soup.get_text() video_text = soup.get_text()
# Should set default category? # Should set default category?
page_category = '' video_category = ''
page_url = urljoin(self.siteurl, self.tpages[srclink]) video_url = urljoin(self.siteurl, self.tpages[srclink])
node = {'title': page_title, node = {'title': video_title,
'text': page_text, 'text': video_text,
'tags': page_category, 'tags': video_category,
'url': page_url} 'url': video_url}
self.json_nodes.append(node) self.json_nodes.append(node)
def generate_output(self, writer): def generate_output(self, writer):
path = os.path.join(self.output_path, 'tipuesearch_content.json') path = os.path.join(self.output_path, 'tipuesearch_content.json')
pages = self.context['pages'] + self.context['articles'] articles = self.context['articles']
for article in self.context['articles']: for article in self.context['articles']:
pages += article.translations articles += article.translations
for srclink in self.tpages: for srclink in self.tpages:
self.create_tpage_node(srclink) self.create_tpage_node(srclink)
for page in pages: for article in articles:
self.create_json_node(page) self.create_json_node(article)
root_node = {'pages': self.json_nodes}
root_node = {'videos': self.json_nodes}
with open(path, 'w', encoding='utf-8') as fd: with open(path, 'w', encoding='utf-8') as fd:
json.dump(root_node, fd, separators=(',', ':'), ensure_ascii=False) json.dump(root_node, fd, separators=(',', ':'), ensure_ascii=False)