pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
title=get_title(p)
presentation = None
if "presentation" in p.text:
presentation = has_pdf(p)
presentation = urljoin(URL, presentation)
title_authors=p.get_text().split('–')
if not pdf:
try:
title=title_authors.split[0]
except:
pass
authors=has_italic(p)
if not authors:
try:
authors=title_authors[1].split('[')[0]
except:
pass
if authors:
authors=namify(authors)
if not authors and not title and not pdf:
continue
line = [title, authors, pdf,presentation, track, raw_text]
print(line)
writer.writerow(line)
raw_text = unspace(p.get_text())
pdf = None
#Skip presention line
if has_pdf(p) and "presentation" not in p.text:
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
presentation = None
if "presentation" in p.text:
presentation = has_pdf(p)
presentation = urljoin(URL, presentation)
try:
title = re.split(":", p.get_text())[1]
title= re.split("--", title)[0]
title = namify(title)
except:
continue
print(has_italic(p))
if not has_italic(p):
continue
authors=has_italic(p)
authors=namify(authors)
#authors=re.split(":", p.get_text())[0]
line = [title, authors, pdf,presentation, track, raw_text]
writer.writerow(line)
pdf = has_pdf(p)
print(pdf)
title = get_title(p)
if has_pdf(p1):
title2 = get_title(p1)
title = title + " " + title2
p2 = page_lines[i + 2]
j = 2
p1 = p2
if not pdf:
continue
while len(p1.text.strip()) <= 3:
p1 = page_lines[i + j]
j = j + 1
try:
pages = extract_pages(p)
except:
pass
pdf = urljoin(URL, pdf)
authors = remove_parenthesised(p1.get_text())
authors = namify(authors)
if has_italic(p1) == None:
authors = None
title = unspace(title)
line = [title, authors, pdf, presentation, vol, pages, track]
writer.writerow(line)
raw_text = unspace(p.get_text())
pdf = None
if has_pdf(p) and "presentation" not in p.text:
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
presentation = None
if "presentation" in p.text:
presentation = has_pdf(p)
presentation = urljoin(URL, presentation)
try:
# Remove the first text before ":"
title = re.split(":", p.get_text())[1:]
title = ":".join(title)
title = re.split("--", title)[0]
title = unspace(title)
except:
continue
if not has_italic(p):
continue
authors = has_italic(p)
authors = namify(authors)
line = [title, authors, pdf, presentation, track, raw_text]
writer.writerow(line)
print(pdf)
title = get_title(p)
if has_pdf(p1):
title2 = get_title(p1)
title = title + " " + title2
p2 = page_lines[i + 2]
j = 2
p1 = p2
if not pdf:
continue
while len(p1.text.strip()) <= 3:
p1 = page_lines[i + j]
j = j + 1
try:
pages = extract_pages(p)
except:
pass
pdf = urljoin(URL, pdf)
if has_italic(p1):
authors = p1.get_text().split(",")[0]
else:
continue
authors = namify(authors)
title = unspace(title)
line = [title, authors, pdf, presentation, vol, pages, track]
writer.writerow(line)
raw_text = unspace(p.get_text())
pdf = None
authors = None
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
else:
continue
presentation = None
try:
# Remove the first text before ":"
title = get_title(p)
except:
continue
if has_italic(p):
authors = has_italic(p)
else:
authors = has_italic(p1)
if authors:
authors = remove_parenthesised(authors)
authors = namify(authors)
if not authors and title == None:
continue
try:
pages = extract_pages(p)
except:
try:
pages = extract_pages(p1)
except:
pass
track = has_bold(p)
continue
raw_text = unspace(p.get_text())
pdf = None
authors = None
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
presentation = None
try:
# Remove the first text before ":"
title = has_italic(p)
title = unspace(title)
except:
continue
try:
authors = p.text.split("–")[1]
except:
pass
if authors:
authors = remove_parenthesised(authors)
authors = namify(authors)
if not authors and title == None:
continue
line = [title, authors, pdf, presentation, vol, track]
writer.writerow(line)