sidski/helseveileder_webscraper
Archived
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

✨ signatures is now scraped!

Browse source 
Co-authored-by: haraldnilsen <harald_998@hotmail.com>
Signed-off-by: Sindre Kjelsrud <kjelsrudsindre@gmail.com>
This commit is contained in:
Sindre Kjelsrud 2024-01-08 14:15:49 +01:00
parent 0da7504104
commit 7247576022
Signed by untrusted user who does not match committer: sidski
GPG key ID: D2BBDF3EDE6BA9A6
1 changed files with 16 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
main.py
View file

@ -48,10 +48,25 @@ def fetch_all_info(url):
# Extracting the question and answer
sporsmal = html.css_first('div.article-text').text()
# Check if the element exists before accessing its text
signatur_div = html.css_first('div.signatur')
signatur = ""
if signatur_div:
signaturTxt = signatur_div.text()
# Remove "Med vennlig hilsen" or "Vennlig hilsen"
signaturTxt = signaturTxt.replace("Med vennlig hilsen", "").replace("Vennlig hilsen", "").strip()
# Check if the text is empty after removal
if signaturTxt:
signatur = signaturTxt
else:
signatur = "Null signatur"
else:
signatur = "Null signatur"
# Create array of results
#result = [sporsmal, svar, signatur]
return sporsmal
return signatur
studenterspor_url = "https://www.studenterspor.no/ajax_handler.php"
urls = fetch_question_url(studenterspor_url)