pages = None
pdf = None
presentation = None
title = []
pages_in_pdf = None
with open(FILE_NAME + ".tsv", 'w') as f:
writer = csv.writer(f,
delimiter='\t',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
writer.writerow([
"Title", "Authors", "Pdf", "Presentation", "Volume_Name", "Pages",
"pages in pdf", "Notes"
])
for i in range(len(page_lines)):
p = page_lines[i]
authors = None
title = p
pages = extract_pages(title)
title = remove_page(title)
title = unspace(title).strip(".")
title = unspace(title)
print(pages_in_pdf)
pages_in_pdf = int(pages) + 4
line = [
title, authors, pdf, presentation, vol, pages, pages_in_pdf, track
]
writer.writerow(line)
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
else:
continue
if "abstract" in p:
track = "abstract, full paper not available"
presentation = None
authors = p.text.split(":")[-1]
authors=remove_parenthesised(authors)
authors= authors.replace("- presentation","")
authors=remove_page(authors)
authors = namify(authors)
if len(authors) <= 2 and title == None:
continue
try:
title = ":".join(p.text.split(":")[:-1])
except:
continue
try:
title = unspace(title)
#pages= extract_pages(p)
title= title.split("pp.")[0].replace("…","")
except:
pass
continue
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
title = get_title(p)
#print(pdf)
else:
continue
presentation = None
authors = right
authors = remove_parenthesised(authors)
print(authors)
if len(authors) <= 3 and title == None:
continue
try:
pages = extract_pages(authors)
except:
pass
authors = remove_page(authors).replace(";", "")
authors = namify(authors)
try:
title = unspace(title)
except:
pass
line = [title, authors, pdf, presentation, vol, pages, track]
writer.writerow(line)