def parse_knesset_laws_page(self,soup):
name_tag = soup.findAll(lambda tag: tag.name == 'a' and tag.has_key('href') and tag['href'].find(".pdf")>=0)
for tag in name_tag:
pdf_link = self.pdf_url + tag['href']
booklet = re.search(r"/(\d+)/",tag['href']).groups(1)[0]
if int(booklet) <= self.min_booklet:
return False
pdf_data = parse_knesset_bill_pdf.parse(pdf_link)
for j in range(len(pdf_data)): # sometime there is more than 1 law in a pdf
title = pdf_data[j]['title']
m = re.findall('[^\(\)]*\((.*?)\)[^\(\)]',title)
try:
comment = m[-1].strip().replace('\n','').replace(' ',' ')
law = title[:title.find(comment)-1]
except:
comment = None
law = title.replace(',','')
try:
correction = m[-2].strip().replace('\n','').replace(' ',' ')
law = title[:title.find(correction)-1]
except:
correction = None
correction = fix_dash(correction)
law = law.strip().replace('\n','').replace(' ',' ')
if law.find("הצעת ".decode("utf8"))==0:
law = law[5:]
self.laws_data.append({'booklet':booklet,'link':pdf_link, 'law':law, 'correction':correction,
'comment':comment, 'original_ids':pdf_data[j]['original_ids'],'date':pdf_data[j]['date']})
return True
def parse_pdf(self,pdf_url):
return parse_knesset_bill_pdf.parse(pdf_url)
def parse_pdf(self,pdf_url):
return parse_knesset_bill_pdf.parse(pdf_url)
