def getAKLeg():
house, senate = map(
lambda body: BeautifulSoup(
urlopen('http://house.legis.state.ak.us/').read()
).find(
'div', {'id': 'tab1-2'}
).find(
'ul', {'class': 'people-holder'}
).find(
'ul', {'class': 'item'}
).find_all('li'),
('house', 'senate')
)
dictList = []
for body, table in zip(('House', 'Senate'), (house, senate)):
for item in table:
repInfo = {}
repInfo['Name'] = unidecode(
item.find('strong', {'class': 'name'}).string
).strip()
link = item.find('a')
repInfo['Website'] = link.get('href')
dl = item.find('dl')
district = re.search(
r'District:\s*(\w+)', dl.get_text(), re.DOTALL
).group(1)
repInfo['District'] = 'AK State {0} District {1}'.format(
body, district
)
repInfo['Party'] = re.search(
r'Party:\s*(\w+)', dl.get_text(), re.DOTALL
).group(1)
repInfo['Phone'] = re.search(
r'Phone:\s*([0-9-]+)', dl.get_text(), re.DOTALL
).group(1)
repInfo['Email'] = dl.find('a').get('href').replace('mailto:', '')
member_soup = BeautifulSoup(urlopen(repInfo['Website']).read())
repInfo['Address'] = multiline_strip(
re.search(
r'Session Contact(.+99801)',
member_soup.find_all('div', {'class': 'bioleft'})[1].get_text(),
re.DOTALL
).group(1)
)
print str(repInfo) + '\n'
dictList.append(repInfo)
return dictList
def get_house_rep(soup):
member_info = soup.find('div', {'class': 'member-info'})
number = re.search(
r'District (\d+)', str(member_info)
).group(1)
district = 'TX State House District %s' % number
# TX House member names are in "Last, First" format:
def rewrite_name(string):
search = re.search('Rep. (.+?)(?:, (?!Jr.))(.+)', string)
if search is None:
return None
first, last = search.group(2).strip(), search.group(1).strip()
return unidecode(first + ' ' + last).strip()
name = rewrite_name(member_info.find('h2').get_text())
phone = re.search(
r'\([0-9]{3}\)\s[0-9]{3}-[0-9]{4}',
str(member_info)
).group()
address = multiline_strip(
re.search(
r'Capitol Address:(.+?787\d{2})',
str(member_info),
re.DOTALL
).group(1)
)
return {
'District': district,
'Name': name,
'Phone': phone,
'Address': address
}