nlp = spacy.load("en_core_web_sm")
track = None
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:
authors = None
#get the track
if has_bold(p):
print("New track name:", track)
track = has_bold(p)
continue
raw_text = unspace(p.get_text())
pdf = None
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
presentation = None
try:
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:
if is_centered(p):
track = is_centered(p)
#writer.writerow([vol])
continue
if has_bold(p):
authors = remove_parenthesised(p.b.get_text())
authors = namify(authors)
print(authors)
else:
continue
if has_pdf:
pdf = has_pdf(p)
title = get_title(p)
if title:
title = unspace(title)
pdf = urljoin(URL, pdf)
line = [title, authors, pdf, presentation, vol, track]
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
writer.writerow(
["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)
"Volume_Name", "Pages", "Abstract", "Notes"])
for i in range(len(page_lines)-2):
title=[]
j = 1
p = page_lines[i]
pj = page_lines[i+j]
if has_pp(p):
pages=extract_pages(p)
else:
continue
while has_bold(pj):
title+=pj.text
j=j+1
pj = page_lines[i+j]
title=unspace("".join(title))
print(title)
authors=namify(pj.text)
while "Abstract" not in pj.text:
j=j+1
pj = page_lines[i+j]
j=j+1
pj = page_lines[i+j]
abstract=pj.text