def verify_id(url):
"""Verify the Id and public-domain status for the book"""
(link_type, link) = get_link_and_type(url)
if link_type == 'wildcard':
if '(*)' not in link[0]:
return 1
try:
r = requests.head(re.sub('\(\*\)', str(link[1]), link[0]))
except:
return 1
if r.status_code == 404:
return 1
if r.status_code != 200:
return 10
if 'image' not in r.headers['content-type']:
return 1
elif link_type == 'pdf':
try:
r = requests.head(link)
except:
return 10
if r.status_code == 404:
return 1
if r.status_code != 200:
return 10
if 'pdf' not in r.headers['content-type']:
return 1
else:
return 1
return 0
def get_pdf_link(tld, soup):
pdf_url = OAI_metadata_content("citation_pdf_url", soup)
pdf_links = False
if pdf_url == "":
links = soup.findAll('a')
for link in links:
if not link.has_key('href'):
continue
if '.pdf' in link.get('href'):
if pdf_links == True and link.get('href') != pdf_url:
return False
pdf_links = True
pdf_url = link.get('href')
else:
continue
if pdf_links != True:
return False
if pdf_url[0]== '/':
pdf_url = tld + pdf_url
pdf_head = requests.head(pdf_url)
if 'content-length' in pdf_head.headers.keys():
content_length = pdf_head.headers['content-length']
if int(content_length) < 1000:
return False
else:
return pdf_url
else:
return False