def parse_cosponsors_from_bill(self, bill, url):
with self.urlopen(url) as bill_page:
bill_page = lxml.html.fromstring(bill_page)
sponsors_text = find_nodes_with_matching_text(
bill_page, '//p/span', r'\s*INTRODUCED.*')
if len(sponsors_text) == 0:
# probably its withdrawn
return
sponsors_text = sponsors_text[0].text_content()
sponsors = clean_text(sponsors_text).split(',')
if len(
sponsors
) > 1: # if there are several comma separated entries, list them.
# the sponsor and the cosponsor were already got from the previous page, so ignore those:
sponsors = sponsors[2::]
for part in sponsors:
parts = re.split(r' (?i)and ', part)
for sponsor in parts:
cosponsor_name = clean_text(sponsor)
if cosponsor_name != "":
cosponsor_name = cosponsor_name.replace(
u'\u00a0', " ") # epic hax
for name in re.split(r'\s+AND\s+', cosponsor_name):
# for name in cosponsor_name.split("AND"):
name = name.strip()
if name:
bill.add_sponsor('cosponsor', name)
def parse_cosponsors_from_bill(self, bill, url):
bill_page = self.urlopen(url)
bill_page = lxml.html.fromstring(bill_page)
sponsors_text = find_nodes_with_matching_text(
bill_page, '//p/span', r'\s*INTRODUCED.*')
if len(sponsors_text) == 0:
# probably its withdrawn
return
sponsors_text = sponsors_text[0].text_content()
sponsors = clean_text(sponsors_text).split(',')
# if there are several comma separated entries, list them.
if len(sponsors) > 1:
# the sponsor and the cosponsor were already got from the previous
# page, so ignore those:
sponsors = sponsors[2::]
for part in sponsors:
parts = re.split(r' (?i)and ', part)
for sponsor in parts:
cosponsor_name = clean_text(sponsor)
if cosponsor_name != "":
cosponsor_name = cosponsor_name.replace(
u'\u00a0', " ") # epic hax
for name in re.split(r'\s+AND\s+', cosponsor_name):
# for name in cosponsor_name.split("AND"):
name = name.strip()
if name:
bill.add_sponsor('cosponsor', name)
def parse_cosponsors_from_bill(self, bill, url):
with self.urlopen(url) as bill_page:
bill_page = lxml.html.fromstring(bill_page)
sponsors_text = find_nodes_with_matching_text(bill_page,'//p/span',r'\s*INTRODUCED.*')
if len(sponsors_text) == 0:
# probably its withdrawn
return
sponsors_text = sponsors_text[0].text_content()
sponsors = clean_text(sponsors_text).split(',')
if len(sponsors) > 1: # if there are several comma separated entries, list them.
# the sponsor and the cosponsor were already got from the previous page, so ignore those:
sponsors = sponsors[2::]
for part in sponsors:
parts = re.split(r' (?i)and ',part)
for sponsor in parts:
bill.add_sponsor('cosponsor', clean_text(sponsor))