def set_user_from_climate_feedback_user_scrap(user, path, store=None):
if store is None:
store = {}
result = requests.get('https://climatefeedback.org{}'.format(path))
soup = BeautifulSoup(result.text, 'html.parser')
info = soup.find("div", class_="med-body")
user.affiliation = situation_line.split(",")[1]
user.external_thumb_url = soup.find("img", class_="avatar")['src']
user.title = situation_line.split(",")[0]
name = info.find("h2", class_="noborder").text
first_name = None
last_name = name
if ' ' in name:
name_chunks = name.split(' ')
first_name = name_chunks[0]
last_name = name_chunks[1:]
paragraphs = info.find_all("p")
situation_line = paragraphs[0].text
user.firstName = first_name
user.lastName = last_name
expertise_line = paragraphs[1].text
if 'Expertise:' in expertise_line:
expertise = expertise_line.split('Expertise: ')[1]
else:
expertise = None
user.expertise = expertise
orcid = info.find("a", href=re.compile("https://orcid.org/(.*)"))
if orcid:
user.orcidId = orcid['href'].split('https://orcid.org/')[1]
website = info.find("a", text="Website")
if website:
user.websiteUrl = website['href']
publication_image = info.find("img", alt="publication")
if publication_image:
publication_anchors = publication_image.parent.find_all("a")
for publication_anchor in publication_anchors:
publication_dict = {
"tags": "isValidatedAsPeerPublication",
"url": publication_anchor['href']
}
publication = Publication.query.filter_by(url=data['url'])\
.first()
if not publication:
publication = Article(**publication_dict)
publication.populate_from_dict(
resolve_with_url(publication.url))
UserArticle(article=publication, user=user)