def scrape_house(self):
committees_pages = committees_url('lower')
link = committees_pages['permanent']
with self.lxml_context(link) as perm_committees_pages:
a_elements = perm_committees_pages.cssselect('a')
committee_elements = a_elements[1:-7]
self.scrape_house_committee_data(committee_elements, link)
link = committees_pages['special']
with self.lxml_context(link) as special_committees_pages:
a_elements = special_committees_pages.cssselect('a')
committee_elements = a_elements[1:10]
self.scrape_house_committee_data(committee_elements, link)
def scrape_house(self):
committees_pages = committees_url('lower')
link = committees_pages['permanent']
with self.lxml_context(link) as perm_committees_pages:
a_elements = perm_committees_pages.cssselect('a')
committee_elements = a_elements[1:-7]
self.scrape_house_committee_data(committee_elements, link)
link = committees_pages['special']
with self.lxml_context(link) as special_committees_pages:
a_elements = special_committees_pages.cssselect('a')
committee_elements = a_elements[1:10]
self.scrape_house_committee_data(committee_elements, link)
def scrape_senate(self):
committees_pages = committees_url('upper')
link = committees_pages['permanent']
with self.lxml_context(link) as perm_committees_page:
td_elements = perm_committees_page.cssselect('td')
self.scrape_senate_comittee_data(td_elements[129:201], link)
link = committees_pages['special']
with self.lxml_context(link) as special_committees_page:
td_elements = special_committees_page.cssselect('td')
self.scrape_senate_comittee_data(td_elements[129:138], link)
link = committees_pages['joint']
with self.lxml_context(link) as joint_committees_page:
td_elements = joint_committees_page.cssselect('td')
self.scrape_senate_comittee_data(td_elements[129:156], link)
def scrape_senate(self):
committees_pages = committees_url('upper')
link = committees_pages['permanent']
with self.lxml_context(link) as perm_committees_page:
td_elements = perm_committees_page.cssselect('td')
self.scrape_senate_comittee_data(td_elements[129:201], link)
link = committees_pages['special']
with self.lxml_context(link) as special_committees_page:
td_elements = special_committees_page.cssselect('td')
self.scrape_senate_comittee_data(td_elements[129:138], link)
link = committees_pages['joint']
with self.lxml_context(link) as joint_committees_page:
td_elements = joint_committees_page.cssselect('td')
self.scrape_senate_comittee_data(td_elements[129:156], link)