def get_soup_impressum(website_links_list):
impressumlist = [
"impressum", "legal", "imprint", "disclaimer", "kontakt", "contact"
]
for impressum in impressumlist:
for link in website_links_list:
if impressum in link.lower():
print(link)
soup = get_soup(link)
return soup
break
return None
def get_soup_northdata(firma):
base_url = "https://www.northdata.de/"
name_split = firma.split(" ")
name_split_string = [""]
for i in range(0, len(name_split)):
name_split_string[0] = str(name_split_string[0]) + str(
name_split[i]) + "+"
name_split_string[0] = name_split_string[0][:-1]
search_url = str(base_url) + str(name_split_string[0])
# print(search_url)
soup = get_soup(search_url)
soup = test_northdata(soup)
return soup
def GetLinks(url):
RawLinks = []
soup = get_soup(url)
links_html = soup.find_all('a')
for link_html in links_html:
link = str(link_html.get('href'))
if len(link) >= 4:
if url[-1] == "/":
url = url[:-1]
if 'http' not in link:
link = url + link
RawLinks.append(link)
RawLinks = list(set(RawLinks))
#print(RawLinks)
return RawLinks