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:
p1 = page_lines[i + j]
j = j + 1
try:
pages = extract_pages(left)
except:
pass
pdf = urljoin(URL, pdf)
authors = remove_parenthesised(p1.get_text())
authors = namify(authors)
title = unspace(title)
line = [title, authors, pdf, presentation, vol, pages, track]
writer.writerow(line)
])
for i in range(len(page_lines) - 3):
j = 1
p = page_lines[i]
p1 = page_lines[i + 1]
raw_text = p.get_text().replace("\n", " ")
pdf = None
title = p.text
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 = p1.text
authors = ",".join(authors.split(",")[:-1])
authors = remove_parenthesised(authors)
authors = ",".join(authors.split(",")[:-1])
authors = namify(authors)
title = unspace(title)
line = [title, authors, pdf, presentation, vol, pages, track]
writer.writerow(line)
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)
raw_text = unspace(p.get_text())
pdf = None
title = None
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
else:
continue
presentation = None
authors = p.text.split(":")[0]
authors = namify(authors)
if len(authors) <= 2 and title == None:
continue
try:
title = get_title(p)
except:
continue
try:
title = unspace(title)
#title = remove_parenthesised(title)
pages = extract_pages(p.text.split(";")[1])
#itle= title.split("pp.")[0].replace("…","")
except:
pass
line = [title, authors, pdf, presentation, vol, pages, track]
writer.writerow(line)
raw_text = unspace(p.get_text())
pdf = None
title = None
if has_pdf(p):
pdf = has_pdf(p)
pdf = urljoin(URL, pdf)
#print(pdf)
else:
pass
presentation = None
try:
authors = p.text.split("--")[1]
except:
continue
try:
pages = extract_pages(authors)
except:
pass
authors = remove_parenthesised(authors)
authors = remove_page(authors)
authors = namify(authors)
if len(authors) <= 2 and title == None:
continue
try:
title = p.text.split("--")[0]
except:
continue
try:
"Title", "Authors", "Pdf", "Presentation", "Volume_Name", "Pages",
"Pages_in_pdf", "Notes"
])
for i in range(len(page_lines)):
p = page_lines[i]
p1 = page_lines[i + 1]
authors_title = p.split("\"")
try:
title = unspace(authors_title[1])
authors = authors_title[0]
except:
continue
authors = unspace(authors)
authors = namify(authors)
pages = extract_pages(p1)
print(pages)
try:
pages = extract_pages(pages)
except:
pass
pages_in_pdf = str(int(pages) + 5)
if len(title) < 4:
continue
line = [
title, authors, pdf, presentation, vol, pages, pages_in_pdf, track
]
writer.writerow(line)
