writer.writerow(
["Title", "Authors", "Pdf", "Presentation", "Volume_Name", "Notes"])
for p in page_lines:
#get the track
if is_centered(p):
print("New track name:", track)
track = is_centered(p)
continue
raw_text = unspace(p.get_text())
pdf = None
title = None
if has_pdf(p):
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 ":"
if pdf:
title = get_title(p)
except:
continue
vol = 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", "Notes"])
for p in page_lines:
#get the track
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 = p.text.split("--")[0]
title = unspace(title)
except:
continue
try:
authors = p.text.split("--")[1]
except:
for i in range(len(page_lines) - 1):
p = page_lines[i]
p1 = page_lines[i + 1]
#get the track
if is_subtitle(p):
print("assigne", track)
track = is_subtitle(p)
writer.writerow([track])
continue
raw_text = p.get_text().replace("\n", " ")
pdf = None
#Skip presention line
if has_pdf(p) and "presentation" not in p.text:
pdf = has_pdf(p)
print(pdf)
presentation = None
if "presentation" in p1.text:
presentation = has_pdf(p1)
if not pdf:
continue
l_1 = p1.get_text()
authors = re.split("\d+", p1.get_text())[0]
print(authors)
authors = namify(authors)
title = get_title(p)
p1 = page_lines[i + 1]
splitter = ":"
line = unspace(p.text)
sliced_line = line.split(splitter)
try:
left = splitter.join(sliced_line[:-1])
right = sliced_line[-1]
except:
print(sliced_line)
continue
raw_text = p.get_text().replace("\n", " ")
pdf = None
if has_pdf(p):
pdf = has_pdf(p)
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:
["Title", "Authors", "Pdf", "Presentation", "Volume_Name", "Notes"])
for i in range(len(page_lines) - 2):
j = 1
p = page_lines[i]
p1 = page_lines[i + 1]
if is_centered(p1):
track = is_centered(p1)
#writer.writerow([vol])
continue
if has_bold(p1):
authors = remove_parenthesised(p1.get_text())
authors = namify(authors)
print(authors)
else:
continue
if has_pdf:
pdf = has_pdf(p)
title = p.text
# while len(p1.text.strip()) <= 3:
# p1 = page_lines[i+j]
# j = j+1
pdf = urljoin(URL, pdf)
title = unspace(title)
line = [title, authors, pdf, presentation, vol, track]
writer.writerow(line)
j = 2
p1 = p2
else:
continue
if authors==None:
continue
title=p1.text
track=None
if "abstract" in title:
track= "abstract"
title=remove_parenthesised(title)
while len(p1.text.strip()) <= 3:
p1 = page_lines[i+j]
j = j+1
try:
pages = extract_pages(p)
except:
pass
pdf=has_pdf(p1)
pdf = urljoin(URL, pdf)
print(authors)
authors=remove_parenthesised(authors)
authors = namify(authors)
title = unspace(title)
line = [title, authors, pdf, presentation, vol,pages, track]
writer.writerow(line)
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","Notes"])
for i in range(len(page_lines)-1):
track=None
p = page_lines[i]
p1 = page_lines[i+1]
if "abstract" in p1.text:
track="abstract, full text not available"
if "presentation" in p1.text:
presentation = has_pdf(p1,1)
presentation = urljoin(URL, presentation)
try:
pdf = has_pdf(p1)
if pdf==None:
continue
except:
continue
#print(p1)
authors = namify(p1.text.split("–")[0])
pdf = urljoin(URL, pdf)
if pdf==URL:
pdf=None
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
writer.writerow([
"Title", "Authors", "Pdf", "Presentation", "Volume_Name", "Pages",
"Notes"
])
for i in range(len(page_lines) - 2):
j = 1
p = page_lines[i]
p1 = page_lines[i + 1]
raw_text = p.get_text().replace("\n", " ")
print(raw_text)
pdf = None
if has_pdf(p) and "abstract" not in p.text:
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:
if "abstract" in p.text:
title = remove_parenthesised(p.text)
pdf = has_pdf(p)
j = 1
p = page_lines[i]
p1 = page_lines[i + 1]
p0 = page_lines[i - 1]
if is_subtitle(p):
track = is_subtitle(p)
track = unspace(track)
#writer.writerow([vol])
continue
authors = None
if finish_by_digit(p):
authors = p.text
else:
continue
title = p0.get_text()
pdf = None
pdf = has_pdf(p0)
if pdf:
title = get_title(p0)
pdf = urljoin(URL, pdf)
if pdf == URL:
pdf = None
authors = namify(authors)
title = unspace(remove_digit(unspace(title)))
print(repr(title))
line = [title, authors, pdf, presentation, vol, track]
writer.writerow(line)
