def extract_claim_and_review(self, parsed_claim_review_page: BeautifulSoup,
url: str) -> List[Claim]:
claim = Claim()
claim.set_url(url)
claim.set_source("checkyourfact")
# title
title = parsed_claim_review_page.find('article').find("h1")
claim.set_title(title.text.replace("FACT CHECK: ", ""))
url_date = url.replace("https://checkyourfact.com/",
"").replace("/", " ").split(" ")
claim.set_date(url_date[0] + "-" + url_date[1] + "-" + url_date[2])
# author & author_url
if parsed_claim_review_page.select('detail > article > author'):
for author in parsed_claim_review_page.select(
'detail > article > author'):
if (hasattr(author, "data-slug")):
author_str = author.text.split("|")[0].strip().split(
"\n")[0]
claim.author = author_str
claim.author_url = "https://checkyourfact.com/author/" + author[
'data-slug']
break
# body
body = parsed_claim_review_page.find("article")
claim.set_body(body.get_text())
# related links
div_tag = parsed_claim_review_page.find("article")
related_links = []
for link in div_tag.findAll('a', href=True):
related_links.append(link['href'])
claim.set_refered_links(related_links)
claim.set_claim(claim.title)
# rating
rating = find_by_text(parsed_claim_review_page, "Verdict", "span")
if rating:
rating_text = rating[0].text.split(":")[-1].strip()
claim.set_rating(rating_text)
else:
pass
tags = []
for tag in parsed_claim_review_page.findAll(
'meta', {"property": "article:tag"}):
tags.append(tag["content"])
claim.set_tags(", ".join(tags))
if len(claim.rating) == 0:
return []
else:
return [claim]
def extract_claim_and_review(self, parsed_claim_review_page: BeautifulSoup,
url: str) -> List[Claim]:
claim = Claim()
claim.set_url(url)
claim.set_source("checkyourfact")
# title
title = parsed_claim_review_page.find('article').find("h1")
claim.set_title(title.text.replace("FACT CHECK: ", ""))
url_date = url.replace("https://checkyourfact.com/",
"").replace("/", " ").split(" ")
claim.set_date(url_date[0] + "-" + url_date[1] + "-" + url_date[2])
# body
body = parsed_claim_review_page.find("article")
claim.set_body(body.get_text())
# related links
div_tag = parsed_claim_review_page.find("article")
related_links = []
for link in div_tag.findAll('a', href=True):
related_links.append(link['href'])
claim.set_refered_links(related_links)
claim.set_claim(claim.title)
# rating
rating = find_by_text(parsed_claim_review_page, "Verdict", "span")
if rating:
rating_text = rating[0].text.split(":")[-1].strip()
claim.set_alternate_name(rating_text)
else:
pass
tags = []
for tag in parsed_claim_review_page.findAll(
'meta', {"property": "article:tag"}):
tags.append(tag["content"])
claim.set_tags(", ".join(tags))
if len(claim.alternate_name) == 0:
return []
else:
return [claim]