def handle_list_item(self, item):
photo_url = item.xpath('./img/@src')[0]
url = item.xpath('.//h5/a/@href')[0]
name_text = item.xpath('.//h5/a/b/text()')[0]
name_match = re.match(r'^(.+)\(([0-9]{2}[AB]), ([A-Z]+)\)$', name_text)
name = name_match.group(1).strip()
district = name_match.group(2).lstrip('0').upper()
party_text = name_match.group(3)
party = PARTIES[party_text]
info_texts = [x.strip() for x in item.xpath(
'./div/text()[normalize-space()]'
) if x.strip()]
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
email_text = item.xpath('.//a/@href')[1].replace('mailto:', '').strip()
if validate_email_address(email_text):
email = email_text
rep = Person(name=name, district=district, party=party,
primary_org='lower', role='Representative',
image=photo_url)
rep.add_link(url)
rep.add_contact_detail(type='address', value=address, note='capitol')
rep.add_contact_detail(type='voice', value=phone, note='capitol')
rep.add_contact_detail(type='email', value=email, note='capitol')
rep.add_source(self.url)
yield rep
def _extract_email(self, doc):
xpath = '//div[@class="districtheadleft"]' \
+ '/b[contains(text(), "Email:")]' \
+ '/../following-sibling::div' \
+ '/script/text()'
script = doc.xpath(xpath)[0]
line = filter(lambda line: '+ "@" +' in line, script.split('\r\n'))[0]
parts = re.findall(r'"(.+?)"', line)
email = ''.join(parts)
return email if validate_email_address(email) else None
def _extract_email(self, doc):
xpath = '//div[@class="districtheadleft"]' \
+ '/b[contains(text(), "Email:")]' \
+ '/../following-sibling::div' \
+ '/script/text()'
script = doc.xpath(xpath)[0]
line = filter(
lambda line: '+ "@" +' in line,
script.split('\r\n'))[0]
parts = re.findall(r'"(.+?)"', line)
email = ''.join(parts)
return email if validate_email_address(email) else None
def _get_rep_email(self, district):
# Get the email address from an input on the contact page
url = "https://www.okhouse.gov/Members/Contact.aspx?District=" + district
page = self.curl_lxmlize(url)
try:
email_node = page.get_element_by_id("txtMemberEmail")
email = email_node.value
except KeyError:
email = None
if email and not validate_email_address(email):
email = None
return email
def handle_list_item(self, item):
photo_url = item.xpath('./td[1]/a/img/@src')[0]
info_nodes = item.xpath('./td[2]/p/a')
name_text = info_nodes[0].xpath('./b/text()')[0]
url = info_nodes[0].get('href')
name_match = re.match(r'^(.+)\(([0-9]{2}[AB]), ([A-Z]+)\)$', name_text)
name = name_match.group(1).strip()
district = name_match.group(2).lstrip('0').upper()
party_text = name_match.group(3)
party = PARTIES[party_text]
info_texts = [
x.strip() for x in item.xpath(
'./td[2]/p/text()[normalize-space() and preceding-sibling::br]'
) if x.strip()
]
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
email_node = info_nodes[1]
email_text = email_node.text
email_text = email_text.replace('Email: ', '').strip()
if validate_email_address(email_text):
email = email_text
rep = Person(name=name,
district=district,
party=party,
primary_org='lower',
role='Representative',
image=photo_url)
rep.add_link(url)
rep.add_contact_detail(type='address', value=address, note='capitol')
rep.add_contact_detail(type='voice', value=phone, note='capitol')
rep.add_contact_detail(type='email', value=email, note='capitol')
rep.add_source(self.url)
yield rep
def handle_list_item(self, item):
photo_url = item.xpath("./img/@src")[0]
url = item.xpath(".//h5/a/@href")[0]
name_text = item.xpath(".//h5/a/b/text()")[0]
name_match = re.match(r"^(.+)\(([0-9]{2}[AB]), ([A-Z]+)\)$", name_text)
name = name_match.group(1).strip()
district = name_match.group(2).lstrip("0").upper()
party_text = name_match.group(3)
party = PARTIES[party_text]
info_texts = [
x.strip()
for x in item.xpath("./div/text()[normalize-space()]")
if x.strip()
]
address = "\n".join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
email_text = item.xpath(".//a/@href")[1].replace("mailto:", "").strip()
if validate_email_address(email_text):
email = email_text
rep = Person(
name=name,
district=district,
party=party,
primary_org="lower",
role="Representative",
image=photo_url,
)
rep.add_link(url)
rep.add_contact_detail(type="address", value=address, note="capitol")
rep.add_contact_detail(type="voice", value=phone, note="capitol")
rep.add_contact_detail(type="email", value=email, note="capitol")
rep.add_source(self.url)
yield rep
def handle_list_item(self, item):
photo_url = item.xpath('./td[1]/a/img/@src')[0]
info_nodes = item.xpath('./td[2]/p/a')
name_text = info_nodes[0].xpath('./b/text()')[0]
url = info_nodes[0].get('href')
name_match = re.match(r'^(.+)\(([0-9]{2}[AB]), ([A-Z]+)\)$', name_text)
name = name_match.group(1).strip()
district = name_match.group(2).lstrip('0').upper()
party_text = name_match.group(3)
party = PARTIES[party_text]
info_texts = [x.strip() for x in item.xpath(
'./td[2]/p/text()[normalize-space() and preceding-sibling::br]'
) if x.strip()]
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
email_node = info_nodes[1]
email_text = email_node.text
email_text = email_text.replace('Email: ', '').strip()
if validate_email_address(email_text):
email = email_text
rep = Person(name=name, district=district, party=party,
primary_org='lower', role='Representative',
image=photo_url)
rep.add_link(url)
rep.add_contact_detail(type='address', value=address)
rep.add_contact_detail(type='voice', value=phone)
rep.add_contact_detail(type='email', value=email)
rep.add_source(self.url)
yield rep
def _scrape_lower_chamber(self, term):
url = 'http://www.house.leg.state.mn.us/members/hmem.asp'
page = self.lxmlize(url)
legislator_nodes = self.get_nodes(
page,
'//div[@id="hide_show_alpha_all"]/table/tr/td/table/tr')
for legislator_node in legislator_nodes:
photo_url = self.get_node(
legislator_node,
'./td[1]/a/img/@src')
info_nodes = self.get_nodes(
legislator_node,
'./td[2]/p/a')
name_text = self.get_node(
info_nodes[0],
'./b/text()')
name_match = re.search(r'^.+\(', name_text)
name = name_match.group(0)
name = name.replace('(', '').strip()
district_match = re.search(r'\([0-9]{2}[A-Z]', name_text)
district_text = district_match.group(0)
district = district_text.replace('(', '').lstrip('0').strip()
party_match = re.search(r'[A-Z]+\)$', name_text)
party_text = party_match.group(0)
party_text = party_text.replace(')', '').strip()
party = self._parties[party_text]
info_texts = self.get_nodes(
legislator_node,
'./td[2]/p/text()[normalize-space() and preceding-sibling'
'::br]')
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
email_node = info_nodes[1]
email_text = email_node.text
email_text = email_text.replace('Email: ', '').strip()
if validate_email_address(email_text):
email = email_text
legislator = Legislator(
term=term,
chamber='lower',
district=district,
full_name=name,
party=party,
email=email,
photo_url=photo_url,
)
legislator.add_source(url)
legislator.add_office(
type='capitol',
name="Capitol Office",
address=address,
phone=phone,
email=email,
)
self.save_legislator(legislator)
def _scrape_lower_chamber(self, term):
url = 'http://www.house.leg.state.mn.us/members/hmem.asp'
page = self.lxmlize(url)
legislator_nodes = self.get_nodes(
page,
'//div[@id="hide_show_alpha_all"]/table/tr/td/table/tr')
for legislator_node in legislator_nodes:
photo_url = self.get_node(
legislator_node,
'./td[1]/a/img/@src')
info_nodes = self.get_nodes(
legislator_node,
'./td[2]/p/a')
name_text = self.get_node(
info_nodes[0],
'./b/text()')
name_match = re.search(r'^.+\(', name_text)
name = name_match.group(0)
name = name.replace('(', '').strip()
district_match = re.search(r'\([0-9]{2}[A-Z]', name_text)
district_text = district_match.group(0)
district = district_text.replace('(', '').lstrip('0').strip()
party_match = re.search(r'[A-Z]+\)$', name_text)
party_text = party_match.group(0)
party_text = party_text.replace(')', '').strip()
party = self._parties[party_text]
info_texts = self.get_nodes(
legislator_node,
'./td[2]/p/text()[normalize-space() and preceding-sibling'
'::br]')
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
email_node = info_nodes[1]
email_text = email_node.text
email_text = email_text.replace('Email: ', '').strip()
if validate_email_address(email_text):
email = email_text
legislator = Legislator(
term=term,
chamber='lower',
district=district,
full_name=name,
party=party,
email=email,
photo_url=photo_url,
)
legislator.add_source(url)
legislator.add_office(
type='capitol',
name="Capitol Office",
address=address,
phone=phone,
email=email,
)
self.save_legislator(legislator)
def scrape_lower_chamber(self, term):
url = 'http://www.house.leg.state.mn.us/members/hmem.asp'
page = self.lxmlize(url)
legislator_nodes = self.get_nodes(
page,
'//div[@id="hide_show_alpha_all"]/table/tr/td/table/tr')
need_special_email_case = False
for legislator_node in legislator_nodes:
photo_url = self.get_node(
legislator_node,
'./td[1]/a/img/@src')
info_nodes = self.get_nodes(
legislator_node,
'./td[2]/p/a')
name_text = self.get_node(
info_nodes[0],
'./b/text()')
name_match = re.search(r'^.+\(', name_text)
name = name_match.group(0)
name = name.replace('(', '').strip()
district_match = re.search(r'\([0-9]{2}[A-Z]', name_text)
district_text = district_match.group(0)
district = district_text.replace('(', '').lstrip('0').strip()
party_match = re.search(r'[A-Z]+\)$', name_text)
party_text = party_match.group(0)
party_text = party_text.replace(')', '').strip()
party = self._parties[party_text]
info_texts = self.get_nodes(
legislator_node,
'./td[2]/p/text()[normalize-space() and preceding-sibling'
'::br]')
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if self._validate_phone_number(phone_text):
phone = phone_text
# E-mail markup is screwed-up and inconsistent.
try:
email_node = info_nodes[1]
email_text = email_node.text
except IndexError:
# Primarily for Dan Fabian.
email_node = info_texts[3]
need_special_email_case = True
email_text = email_text.replace('Email: ', '').strip()
if validate_email_address(email_text):
email = email_text
legislator = Legislator(
term=term,
chamber='lower',
district=district,
full_name=name,
party=party,
email=email,
photo_url=photo_url,
)
legislator.add_source(url)
legislator.add_office(
type='capitol',
name="Capitol Office",
address=address,
phone=phone,
email=email,
)
self.save_legislator(legislator)
if not need_special_email_case:
self.logger.warning('Special e-mail handling no longer required.')
def _scrape_lower_chamber(self, term):
url = 'http://www.house.leg.state.mn.us/members/hmem.asp'
page = self.lxmlize(url)
legislator_nodes = self.get_nodes(
page, '//div[@id="hide_show_alpha_all"]/table/tr/td/table/tr')
need_special_email_case = False
for legislator_node in legislator_nodes:
photo_url = self.get_node(legislator_node, './td[1]/a/img/@src')
info_nodes = self.get_nodes(legislator_node, './td[2]/p/a')
name_text = self.get_node(info_nodes[0], './b/text()')
name_match = re.search(r'^.+\(', name_text)
name = name_match.group(0)
name = name.replace('(', '').strip()
district_match = re.search(r'\([0-9]{2}[A-Z]', name_text)
district_text = district_match.group(0)
district = district_text.replace('(', '').lstrip('0').strip()
party_match = re.search(r'[A-Z]+\)$', name_text)
party_text = party_match.group(0)
party_text = party_text.replace(')', '').strip()
party = self._parties[party_text]
info_texts = self.get_nodes(
legislator_node,
'./td[2]/p/text()[normalize-space() and preceding-sibling'
'::br]')
address = '\n'.join((info_texts[0], info_texts[1]))
phone_text = info_texts[2]
if validate_phone_number(phone_text):
phone = phone_text
# E-mail markup is screwed-up and inconsistent.
try:
email_node = info_nodes[1]
email_text = email_node.text
except IndexError:
# Primarily for Dan Fabian.
email_node = info_texts[3]
need_special_email_case = True
email_text = email_text.replace('Email: ', '').strip()
if validate_email_address(email_text):
email = email_text
legislator = Legislator(
term=term,
chamber='lower',
district=district,
full_name=name,
party=party,
email=email,
photo_url=photo_url,
)
legislator.add_source(url)
legislator.add_office(
type='capitol',
name="Capitol Office",
address=address,
phone=phone,
email=email,
)
self.save_legislator(legislator)
if not need_special_email_case:
self.logger.warning('Special e-mail handling no longer required.')
