def scrape_session(self, chamber, session, special=0): url = bill_list_url(chamber, session, special) with self.urlopen(url) as page: page = lxml.html.fromstring(page) page.make_links_absolute(url) for link in page.xpath('//a[contains(@href, "billinfo")]'): self.parse_bill(chamber, session, special, link)
def scrape_session(self, chamber, session, special=0): session_url = bill_list_url(chamber, session, special) with self.urlopen(session_url) as bill_list_page: bill_list_page = BeautifulSoup(bill_list_page) bill_link_re = "body=%s&type=(B|R)&bn=\d+" % bill_abbr(chamber) for link in bill_list_page.findAll(href=re.compile(bill_link_re)): self.parse_bill(chamber, session, special, link)