From 5569465daff7761fc24e086e40e26c66ea1b221e Mon Sep 17 00:00:00 2001 From: Martin Rotter Date: Thu, 20 May 2021 10:14:11 +0200 Subject: [PATCH] scraper --- resources/scripts/scrapers/wiki-qotd.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/resources/scripts/scrapers/wiki-qotd.py b/resources/scripts/scrapers/wiki-qotd.py index cb4c9d3e6..0cc2db17a 100755 --- a/resources/scripts/scrapers/wiki-qotd.py +++ b/resources/scripts/scrapers/wiki-qotd.py @@ -22,9 +22,14 @@ for lst in lists: quote_link = "https://en.wikiquote.org" + quote_link quote_author = last_link.get_text() - quote_text = lst.find("li").decode_contents() - quote_heading = (quote_text[:75] + '...') if len(quote_text) > 75 else quote_text - quote_text = "" + quote_text + "" + + if not quote_author: + continue + + quote_text = "" + lst.find("li").decode_contents() + "" + quote_heading = lst.find("li") + quote_heading = (quote_heading.get_text()[:75] + '...') if len(quote_heading) > 75 else quote_heading.get_text() + quote_heading = quote_heading.split(" ~")[0] items.append("{{\"title\": {title}, \"authors\": [{{\"name\": {author}}}], \"content_html\": {html}, \"url\": {url}, \"date_published\": {date}}}".format( title = json.dumps(quote_heading),