def get_people(self):
response = urlopen(COUNCIL_CSV_URL)
cr = DictReader(response)
for councillor in cr:
name = '%s %s' % (councillor['First name'], councillor['Last name'])
role = councillor['Elected office']
if role == 'Mayor':
district = 'Ottawa'
else:
district = councillor['District name']
# Correct typos. The City has been notified of the errors.
if district == u'Knoxdale Merivale':
district = u'Knoxdale-Merivale'
if district == u'Rideau Vanier':
district = u'Rideau-Vanier'
if district == u'Orleans':
district = u'Orléans'
email = councillor['Email']
address = ', '.join([councillor['Address line 1'],
councillor['Address line 2'],
councillor['Locality'],
councillor['Postal code'],
councillor['Province']])
phone = councillor['Phone']
photo_url = councillor['Photo URL']
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_CSV_URL)
p.add_contact('email', email, None)
p.add_contact('address', address, 'legislature')
p.add_contact('voice', phone, 'legislature')
p.image = photo_url
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//table/tbody/tr/td')
for councillor in councillors:
text = councillor.xpath('.//strong/text()')[0]
name = text.split(',')[0].replace('Name:', '').strip()
if 'Mayor' in text and not 'Deputy Mayor' in text:
role = 'Mayor'
district = 'Fredericton'
else:
district = re.findall(r'(Ward:.*)(?=Address:)', councillor.text_content())[0].replace(':', '').strip()
district = re.search('\((.+?)(?: Area)?\)', district).group(1)
role = 'Councillor'
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.image = councillor.xpath('.//img/@src')[0]
address = re.findall(r'(?<=Address:).*(?=Home:)', councillor.text_content())[0].strip()
p.add_contact('address', address, 'legislature')
phone = re.findall(r'(?<=Home: \().*(?=Fax:)', councillor.text_content())[0]
phone = re.sub(r'(?<=[0-9])(\)\D{1,2})(?=[0-9])', '-', phone).split()[0]
p.add_contact('voice', phone, 'residence')
phone = re.findall(r'(?<=Office: \().*(?=Fax:)', councillor.text_content())
if phone:
phone = phone[0].replace(') ', '-')
p.add_contact('voice', phone, 'legislature')
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//div[@id="content"]//tr')
for i, councillor in enumerate(councillors):
if 'Maire' in councillor.text_content():
name = councillor.xpath('./td')[1].text_content()
district = 'Sainte-Anne-de-Bellevue'
role = 'Maire'
else:
name = councillor.xpath('./td')[1].text_content()
district = 'District ' + re.findall(
r'\d',
councillor.xpath('./td')[0].text_content())[0]
role = 'Conseiller'
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
email = councillor.xpath('.//a')
if email:
email = email[0].attrib['href'].replace('mailto:', '')
p.add_contact('email', email, None)
yield p
def scrape_mayor(self):
page = lxmlize(MAYOR_PAGE, 'iso-8859-1')
name = page.xpath(
'//div[@class="articletitle"]/h1')[0].text_content().replace(
'Mayor', '')
p = Legislator(name=name, post_id='Summerside', role='Mayor')
p.add_source(MAYOR_PAGE)
p.image = page.xpath(
'//div[@class="articlebody-inside"]/p/img/@src')[0].replace(
'..', '')
info = page.xpath('//div[@class="articlebody-inside"]/p')
phone = re.findall(r'to (.*)', info[1].text_content())[0]
address = info[3].text_content().replace(
'by mail: ', '') + ' ' + info[4].text_content()
email = info[5].xpath(
'.//a[contains(@href, "mailto:")]')[0].text_content()
p.add_contact('voice', phone, 'legislature')
p.add_contact('address', address, 'legislature')
p.add_contact('email', email, None)
return p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//div[@id="WebPartWPQ1"]/table/tbody/tr[1]')
for councillor in councillors:
node = councillor.xpath(".//td[1]//strong//strong//strong//strong") or councillor.xpath(".//td[1]//strong")
text = node[0].text_content()
name = text.strip().replace("Deputy ", "").replace("Warden ", "").replace("Mayor", "")
role = text.replace(name, "").strip()
if not role:
role = "Councillor"
if "," in name:
name = name.split(",")[0].strip()
district = councillor.xpath('.//td[1]//p[contains(text(),",")]/text()')[0].split(",")[1].strip()
district = re.sub(r"\A(?:City|Municipality|Town|Township|Village) of\b| Township\Z", "", district)
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.image = councillor.xpath(".//td[1]//img/@src")[0]
info = councillor.xpath(".//td[2]")[0].text_content()
residential_info = re.findall(r"(?<=Residence:)(.*)(?=Municipal Office:)", info, flags=re.DOTALL)[0]
self.get_contacts(residential_info, "residence", p)
municipal_info = re.findall(r"(?<=Municipal Office:)(.*)", info, flags=re.DOTALL)[0]
self.get_contacts(municipal_info, "legislature", p)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//ul[@class="subNav top"]/li/ul//li/a')
for councillor in councillors:
name = councillor.text_content()
url = councillor.attrib['href']
page = lxmlize(url)
if councillor == councillors[0]:
district = 'Ajax'
role = 'Mayor'
else:
district = re.findall(r'Ward.*', page.xpath('//div[@id="printAreaContent"]//h1')[0].text_content())[0].strip()
role = page.xpath('//div[@id="printAreaContent"]//h1')[0].text_content()
role = re.findall('((Regional)? ?(Councillor))', role)[0][0]
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.image = page.xpath('//div[@class="intQuicklinksPhoto"]/img/@src')[0]
contact_info = page.xpath('//table[@class="datatable"][1]//tr')[1:]
for line in contact_info:
contact_type = line.xpath('./td')[0].text_content().strip()
contact = line.xpath('./td')[1].text_content().strip()
if re.match(r'(Phone)|(Fax)|(Email)', contact_type):
contact_type = CONTACT_DETAIL_TYPE_MAP[contact_type]
p.add_contact(contact_type, contact, None if contact_type == 'email' else 'legislature')
else:
p.add_link(contact, None)
yield p
def scrape_mayor(url):
page = lxmlize(url)
name = page.xpath('//tr/td/p')[-1]
name = name.text_content().replace('Mayor', '')
image = page.xpath('//div[@class="sask_ArticleBody"]//img/@src')[0]
contact_url = page.xpath(
'//a[contains(text(), "Contact the Mayor")]/@href')[0]
page = lxmlize(contact_url)
address = ' '.join(
page.xpath(
'//div[@id="ctl00_PlaceHolderMain_RichHtmlField1__ControlWrapper_RichHtmlField"]/p[4]/text()'
)[1:])
phone = page.xpath(
'//div[@id="ctl00_PlaceHolderMain_RichHtmlField1__ControlWrapper_RichHtmlField"]/p[5]/span/text()'
)[0].replace('(', '').replace(') ', '-')
fax = page.xpath(
'//div[@id="ctl00_PlaceHolderMain_RichHtmlField1__ControlWrapper_RichHtmlField"]/p[6]/span/text()'
)[0].replace('(', '').replace(') ', '-')
p = Legislator(name=name, post_id='Saskatoon', role='Mayor')
p.add_source(url)
p.image = image
p.add_contact('address', address, 'legislature')
p.add_contact('voice', phone, 'legislature')
p.add_contact('fax', fax, 'legislature')
return p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//div[@class="article-content"]//td[@class="ms-rteTableOddCol-0"]')
yield scrape_mayor(councillors[0])
for councillor in councillors[1:]:
if not councillor.xpath('.//a'):
continue
name = councillor.xpath('.//a')[0].text_content().strip()
district = councillor.xpath('.//a')[1].text_content()
url = councillor.xpath('.//a/@href')[0]
page = lxmlize(url)
p = Legislator(name=name, post_id=district, role='Conseiller')
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.image = councillor.xpath('./preceding-sibling::td//img/@src')[-1]
contacts = page.xpath('.//td[@class="ms-rteTableOddCol-0"]//text()')
for contact in contacts:
if re.findall(r'[0-9]', contact):
phone = contact.strip().replace(' ', '-')
p.add_contact('voice', phone, 'legislature')
get_links(p, page.xpath('.//td[@class="ms-rteTableOddCol-0"]')[0])
email = page.xpath(
'string(//a[contains(@href, "mailto:")]/@href)')[len('mailto:'):]
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//div[@align="center" and not(@class="background")]//td/p')
for councillor in councillors:
if not councillor.text_content().strip():
continue
name = councillor.xpath('./font/b/text()')
if not name:
name = councillor.xpath('./font/text()')
if 'e-mail' in name[0]:
name = councillor.xpath('./b/font/text()')
name = name[0]
role = 'Councillor'
if 'Mayor' in name:
name = name.replace('Mayor', '')
role = 'Mayor'
p = Legislator(name=name, post_id="LaSalle", role=role)
p.add_source(COUNCIL_PAGE)
photo_url = councillor.xpath('./parent::td//img/@src')[0]
p.image = photo_url
email = councillor.xpath('.//a[contains(@href, "mailto:")]/text()')[0]
p.add_contact('email', email, None)
phone = re.findall(r'(?<=phone:)(.*)(?=home)', councillor.text_content(), flags=re.DOTALL)
if phone:
p.add_contact('voice', phone[0].strip(), 'legislature')
home_phone = re.findall(r'(?<=home phone:)(.*)', councillor.text_content(), flags=re.DOTALL)[0]
p.add_contact('voice', home_phone.strip(), 'residence')
yield p
def get_people(self):
page = lxmlize(
COUNCIL_PAGE,
user_agent=
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)')
councillors = page.xpath('//table[last()]//tr/td[1]//strong')
for i, councillor in enumerate(councillors):
name = councillor.text_content().strip()
if not name:
continue
if 'maire' in name:
name = name.split('maire')[1].strip()
district = u'Montréal-Est'
else:
district = councillor.xpath(
'./ancestor::td/following-sibling::td//strong'
)[-1].text_content()
district = 'District %s' % re.sub('\D+', '', district)
email = councillor.xpath(
'./ancestor::tr/following-sibling::tr//a[contains(@href, "mailto:")]'
)[0].text_content().strip()
role = 'Maire' if i == 0 else 'Conseiller'
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE, 'iso-8859-1')
general_contacts = page.xpath('//p[@class="large_title"]/following-sibling::p/text()')
general_phone = general_contacts[0]
general_fax = general_contacts[1]
councillors = page.xpath('//tr/td/p/strong')
councillors = [councillor for councillor in councillors if not "@" in councillor.text_content()]
for councillor in councillors:
if 'Mayor' in councillor.text_content():
name = councillor.text_content().replace('Mayor', '')
district = 'Dollard-Des Ormeaux'
role = 'Maire'
else:
name = re.split(r'[0-9]', councillor.text_content())[1]
district = 'District ' + re.findall(r'[0-9]', councillor.text_content())[0]
role = 'Conseiller'
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.image = councillor.xpath('./parent::p/parent::td/parent::tr/preceding-sibling::tr//img/@src')[0]
email = councillor.xpath('./parent::p/following-sibling::p//a[contains(@href, "mailto:")]')
if email:
p.add_contact('email', email[0].text_content(), None)
p.add_contact('voice', general_phone, 'legislature')
p.add_contact('fax', general_fax, 'legislature')
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
mayor_url = page.xpath('//a[contains(text(), "Mayor")]/@href')[0]
yield self.scrape_mayor(mayor_url)
councillors_url = page.xpath('//a[contains(text(), "Councillors")]/@href')[0]
cpage = lxmlize(councillors_url)
councillor_rows = cpage.xpath('//tr[td//img]')[:-1]
for councillor_row in councillor_rows:
img_cell, info_cell = tuple(councillor_row)
name = info_cell.xpath(
'string(.//span[contains(text(), "Councillor")])')[len('Councillor '):]
district = info_cell.xpath('string(.//p[contains(text(), "District")])')
email = info_cell.xpath('string(.//a[contains(@href, "mailto:")])')
if not email:
email = info_cell.xpath('string(.//strong[contains(text(), "E-mail")]/following-sibling::text())')
phone = info_cell.xpath(
'string(.//p[contains(.//text(), "Telephone:")])').split(':')[1]
img_url_rel = img_cell.xpath('string(//img/@href)')
img_url = urljoin(councillors_url, img_url_rel)
p = Legislator(name=name, post_id=district, role='Conseiller')
p.add_source(COUNCIL_PAGE)
p.add_source(councillors_url)
p.add_contact('email', email, None)
p.add_contact('voice', phone, 'legislature')
p.image = img_url
yield p
def get_people(self):
member_parties = dict(process_parties(lxmlize(PARTY_PAGE)))
page = lxmlize(COUNCIL_PAGE)
for row in page.xpath('//table[not(@id="footer")]/tr')[1:]:
name, district, _, email = [
cell.xpath('string(.)').replace(u'\xa0', u' ') for cell in row
]
phone = row[2].xpath('string(text()[1])')
try:
photo_page_url = row[0].xpath('./a/@href')[0]
except IndexError:
continue # there is a vacant district
photo_page = lxmlize(photo_page_url)
photo_url = photo_page.xpath('string(//table//img/@src)')
district = district.replace(' - ', u'—') # m-dash
party = get_party(member_parties[name.strip()])
p = Legislator(name=name,
post_id=district,
role='MHA',
party=party,
image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_source(photo_page_url)
p.add_contact('email', email, None)
# TODO: either fix phone regex or tweak phone value
p.add_contact('voice', phone, 'legislature')
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
member_cells = page.xpath(
'//div[@class="views-field views-field-field-picture"]/'
'parent::td')
for cell in member_cells:
name = cell[1].text_content().replace(' .', '. ') # typo on page
riding = cell[2].text_content()
if 'Mackenzie Delta' in riding:
riding = 'Mackenzie-Delta'
detail_url = cell[0].xpath('string(.//a/@href)')
detail_page = lxmlize(detail_url)
photo_url = detail_page.xpath(
'string(//div[@class="field-item even"]/img/@src)')
email = detail_page.xpath('string(//a[contains(@href, "mailto:")])')
contact_text = detail_page.xpath(
'string(//div[@property="content:encoded"]/p[1])')
phone = re.search(r'P(hone)?: ([-0-9]+)', contact_text).group(2)
p = Legislator(name=name, post_id=riding, role='MLA', image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_source(detail_url)
p.add_contact('email', email, None)
p.add_contact('voice', phone, 'legislature')
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
table = page.cssselect('table')[0]
rows = table.cssselect('tr')[1:]
assert len(rows) == 27 # There should be 27 districts
for row in rows:
districtnumcell, districtcell, membercell, dummy2 = row.cssselect(
'td')
district_name = districtcell.cssselect(
'a')[0].text_content().strip()
district = district_name.replace(' - ', '-')
name = (membercell.cssselect('a')[0].text_content().replace(
'Hon. ', '').replace(' (LIB)', '').replace(' (PC)',
'').strip())
url = membercell.cssselect('a')[0].get('href')
email, phone, photo_url = scrape_extended_info(url)
p = Legislator(name=name,
post_id=district,
role='MLA',
image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
p.add_contact('voice', phone, 'legislature')
yield p
def scrape_mayor(self, url):
infos_page = lxmlize(url)
infos = infos_page.xpath('//div[@class="item-page"]')[0]
name = ' '.join(infos.xpath('p[2]/text()')[0].split(' ')[2:4])
lname = name.lower()
email = lname.split(' ')[0][0] + lname.split(
' ')[1] + '@langleycity.ca'
photo_url = infos.xpath('p[1]/img/@src')[0]
p = Legislator(name=name,
post_id='Langley',
role='Mayor',
image=photo_url)
p.add_source(url)
p.add_contact('email', email, None)
personal_infos = infos.xpath('p[last()]/text()')
phone = re.findall(r'Phone(:?) (.*)', '\n'.join(personal_infos))[0][1]
address = re.findall(r'Address: (.*) Phone',
' '.join(personal_infos))[0]
p.add_contact('address', address, 'office')
p.add_contact('voice', phone, 'office')
return p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//div[@class="img_four"][1]/div[1]')
councillors = councillors + page.xpath(
'//div[@class="img_four"][2]/div')
for councillor_elem in councillors:
name, position = councillor_elem.xpath('string(./p/strong)').split(
',')
position = position.strip()
if ' ' in position:
position, post_id = position.split(' ', 1)
post_id = post_number(post_id)
else:
post_id = 'Wellesley'
addr = '\n'.join(
addr_str.strip()
for addr_str in councillor_elem.xpath('./p/text()')).strip()
phone = councillor_elem.xpath(
'string(.//a[starts-with(@href, "tel:")])')
email = councillor_elem.xpath(
'string(.//a[starts-with(@href, "mailto:")])')
image = councillor_elem.xpath('string(.//img[1]/@src)')
p = Legislator(name=name,
post_id=post_id,
role=position,
image=image)
p.add_source(COUNCIL_PAGE)
p.add_contact('address', addr, 'legislature')
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def mayor_data(url):
page = lxmlize(url)
# TODO: Consider getting photo. It's on a separate page.
name_text = page.xpath('//p[contains(text(), "Worship Mayor")]/text()')[0]
name = ' '.join(name_text.split()[3:]) # TODO: probably too brittle
email = page.xpath('//a[contains(@href, "mailto")]/text()')[0]
p = Legislator(name=name, post_id='Mississauga', role='Mayor')
p.add_source(url)
p.add_contact('email', email, None)
return p
def mayor_data(url):
page = lxmlize(url)
# TODO: Consider getting photo. It's on a separate page.
name_text = page.xpath('//p[contains(text(), "Worship Mayor")]/text()')[0]
name = ' '.join(name_text.split()[3:]) # TODO: probably too brittle
email = page.xpath('//a[contains(@href, "mailto")]/text()')[0]
p = Legislator(name=name, post_id='Mississauga', role='Mayor')
p.add_source(url)
p.add_contact('email', email, None)
return p
def scrape_mayor(url):
page = lxmlize(url)
name = page.xpath('//div[@id="printAreaContent"]/h1/strong/text()')[0].replace('Mayor', '').strip()
address = page.xpath('//strong[contains(text(), "mail")]/parent::p/text()')[1].replace(':', '').strip()
phone = page.xpath('//strong[contains(text(), "phone")]/parent::p/text()')[1].split()[1]
p = Legislator(name=name, post_id='Caledon', role='Mayor')
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.image = page.xpath('//h2[contains(text(), "About me")]/img/@src')[0]
p.add_contact('address', address, 'legislature')
p.add_contact('voice', phone, 'legislature')
return p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillor_trs = [
tr for tr in page.xpath('//table//tr[1]') if len(tr) == 2
][:-1]
for councillor_tr in councillor_trs:
desc = [
text.strip()
for text in councillor_tr.xpath('.//text()[normalize-space()]')
if text.strip()
]
if len(desc) == 3:
role = 'Maire'
district = u'Saint-Jérôme'
else:
role = 'Conseiller'
district = desc[0].replace(u'numéro ', '')
name = desc[-3]
phone = desc[-2]
email = desc[-1]
image = councillor_tr.xpath('string(.//img/@src)')[0]
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.image = image
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillor_links = page.xpath('//li[@id="pageid2117"]/ul/li/a')[2:10]
for link in councillor_links:
if not link.text.startswith('Councillor'):
continue
url = link.attrib['href']
page = lxmlize(url)
mail_link = page.xpath('//a[@title]')[0]
name = mail_link.attrib['title']
email = mail_link.attrib['href'][len('mailto:'):]
photo_url = page.xpath(
'string(//div[@class="pageContent"]//img[@align="right"]/@src)'
)
p = Legislator(name=name,
post_id='Abbotsford',
role='Councillor',
image=photo_url)
p.add_source(url)
p.add_contact('email', email, None)
yield p
page = lxmlize(MAYOR_URL)
name = page.xpath('string(//h1)').split(' ', 1)[1]
photo_url = page.xpath('string(//img[@hspace=10]/@src)')
# email is hidden behind a form
p = Legislator(name=name,
post_id='Abbotsford',
role='Mayor',
image=photo_url)
p.add_source(MAYOR_URL)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillor_links = page.xpath('//li[@id="pageid2117"]/ul/li/a')[2:10]
for link in councillor_links:
if not link.text.startswith('Councillor'):
continue
url = link.attrib['href']
page = lxmlize(url)
mail_link = page.xpath('//a[@title]')[0]
name = mail_link.attrib['title']
email = mail_link.attrib['href'][len('mailto:'):]
photo_url = page.xpath('string(//div[@class="pageContent"]//img[@align="right"]/@src)')
p = Legislator(name=name, post_id='Abbotsford', role='Councillor',
image=photo_url)
p.add_source(url)
p.add_contact('email', email, None)
yield p
page = lxmlize(MAYOR_URL)
name = page.xpath('string(//h1)').split(' ', 1)[1]
photo_url = page.xpath('string(//img[@hspace=10]/@src)')
# email is hidden behind a form
p = Legislator(name=name, post_id='Abbotsford', role='Mayor', image=photo_url)
p.add_source(MAYOR_URL)
yield p
def get_people(self):
# mayor first, can't find email
page = lxmlize(MAYOR_URL)
photo_url = page.xpath('string(//img/@src[contains(., "Maire")])')
name = page.xpath('string(//td[@class="contenu"]/text()[last()])')
p = Legislator(name=name, post_id=u"Trois-Rivières", role="Maire", image=photo_url)
p.add_source(MAYOR_URL)
yield p
resp = requests.get(COUNCIL_PAGE)
# page rendering through JS on the client
page_re = re.compile(r'createItemNiv3.+"District (.+?)".+(index.+)\\"')
for district, url_rel in page_re.findall(resp.text):
if district not in ("des Estacades", "des Plateaux", "des Terrasses", "du Sanctuaire"):
district = re.sub("\A(?:de(?: la)?|des|du) ", "", district)
url = urljoin(COUNCIL_PAGE, url_rel)
page = lxmlize(url)
name = page.xpath("string(//h2)")
email = page.xpath('string(//a/@href[contains(., "mailto:")])')[len("mailto:") :]
photo_url = page.xpath('string(//img/@src[contains(., "Conseiller")])')
p = Legislator(name=name, post_id=district, role="Conseiller", image=photo_url)
p.add_source(url)
p.add_contact("email", email, None)
yield p
def get_people(self):
# mayor first, can't find email
page = lxmlize(MAYOR_URL)
photo_url = page.xpath('string(//img/@src[contains(., "Maire")])')
name = page.xpath('string(//td[@class="contenu"]/text()[last()])')
p = Legislator(name=name,
post_id=u"Trois-Rivières",
role="Maire",
image=photo_url)
p.add_source(MAYOR_URL)
yield p
resp = requests.get(COUNCIL_PAGE)
# page rendering through JS on the client
page_re = re.compile(r'createItemNiv3.+"District (.+?)".+(index.+)\\"')
for district, url_rel in page_re.findall(resp.text):
if district not in ('des Estacades', 'des Plateaux',
'des Terrasses', 'du Sanctuaire'):
district = re.sub('\A(?:de(?: la)?|des|du) ', '', district)
url = urljoin(COUNCIL_PAGE, url_rel)
page = lxmlize(url)
name = page.xpath('string(//h2)')
email = page.xpath(
'string(//a/@href[contains(., "mailto:")])')[len('mailto:'):]
photo_url = page.xpath(
'string(//img/@src[contains(., "Conseiller")])')
p = Legislator(name=name,
post_id=district,
role='Conseiller',
image=photo_url)
p.add_source(url)
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillor_trs = [tr for tr in page.xpath('//table//tr[1]') if len(tr) == 2][:-1]
for councillor_tr in councillor_trs:
desc = [text.strip() for text in councillor_tr.xpath('.//text()[normalize-space()]') if text.strip()]
if len(desc) == 3:
role = 'Maire'
district = u'Saint-Jérôme'
else:
role = 'Conseiller'
district = desc[0].replace(u'numéro ', '')
name = desc[-3]
phone = desc[-2]
email = desc[-1]
image = councillor_tr.xpath('string(.//img/@src)')[0]
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.image = image
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//p[@class="WSIndent"]/a')
for councillor in councillors:
district = re.findall(r'(Ward [0-9]{1,2})', councillor.text_content())
if district:
district = district[0]
name = councillor.text_content().replace(district, '').strip()
role = 'Councillor'
else:
district = 'Kawartha Lakes'
name = councillor.text_content().replace('Mayor', '').strip()
role = 'Mayor'
url = councillor.attrib['href']
page = lxmlize(url)
email = page.xpath('//a[contains(@href, "mailto:")]/@href')[0].rsplit(':', 1)[1].strip()
image = page.xpath('//img[@class="image-right"]/@src')[0]
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
p.image = image
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE, user_agent='Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)')
yield self.scrape_mayor(page)
councillors = page.xpath('//strong[contains(text(), "Councillor")]/parent::p|//b[contains(text(), "Councillor")]/parent::p')
for councillor in councillors:
name = councillor.xpath('./strong/text()|./b/text()')[0].replace('Councillor', '').strip()
district = re.findall('(?<=Ward \d, ).*', councillor.text_content())[0].strip()
p = Legislator(name=name, post_id=district, role='Councillor')
p.add_source(COUNCIL_PAGE)
p.image = councillor.xpath('.//img/@src')[0]
phone = re.findall(r'Phone(.*)', councillor.text_content())
node = councillor
while not phone:
node = node.xpath('./following-sibling::p')[1]
phone = re.findall(r'Phone(.*)', node.text_content())
phone = phone[0].strip()
email = councillor.xpath('.//a[contains(@href, "mailto:")]')
if not email:
email = councillor.xpath('./following-sibling::p//a[contains(@href, "mailto")]')
email = email[0].text_content()
if len(re.sub(r'\D', '', phone)) == 7:
phone = '902-%s' % phone
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE, 'iso-8859-1')
councillors = page.xpath('//div[@id="PageContent"]/table/tbody/tr/td')
for councillor in councillors:
if not councillor.text_content().strip():
continue
if councillor == councillors[0]:
district = 'Kirkland'
role = 'Maire'
else:
district = councillor.xpath('.//h2')[0].text_content()
district = re.search('- (.+)', district).group(1).strip()
district = district.replace(' Ouest', ' ouest').replace(' Est', ' est')
role = 'Conseiller'
name = councillor.xpath('.//strong/text()')[0]
phone = councillor.xpath('.//div[contains(text(), "#")]/text()')[0].replace('T ', '').replace(' ', '-').replace(',-#-', ' x')
email = councillor.xpath('.//a[contains(@href, "mailto:")]')[0].text_content()
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
p.image = councillor.xpath('.//img/@src')[0]
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillors = page.xpath('//p[@class="WSIndent"]/a')
for councillor in councillors:
district = re.findall(r'(Ward [0-9]{1,2})',
councillor.text_content())
if district:
district = district[0]
name = councillor.text_content().replace(district, '').strip()
role = 'Councillor'
else:
district = 'Kawartha Lakes'
name = councillor.text_content().replace('Mayor', '').strip()
role = 'Mayor'
url = councillor.attrib['href']
page = lxmlize(url)
email = page.xpath(
'//a[contains(@href, "mailto:")]/@href')[0].rsplit(
':', 1)[1].strip()
image = page.xpath('//img[@class="image-right"]/@src')[0]
p = Legislator(name=name, post_id=district, role=role)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
p.image = image
yield p
def mayor_data(url, name):
page = lxmlize(url)
photo_url = urljoin(url,
page.xpath('string((//div[@id="contentcontainer"]//img)[1]/@src)'))
contact_page = lxmlize(MAYOR_CONTACT_URL)
email = contact_page.xpath('string(//a[contains(., "@")][1])')
m = Legislator(name=name, post_id='Regina', role='Mayor')
m.add_source(COUNCIL_PAGE)
m.add_source(url)
m.add_source(MAYOR_CONTACT_URL)
m.add_contact('email', email, None)
m.image = photo_url
return m
def councillor_data(url, name, ward):
page = lxmlize(url)
# email is, sadly, a form
photo_url = urljoin(url, page.xpath('string(//img[@class="bio_pic"]/@src)'))
phone = page.xpath('string(//td[contains(., "Phone")]/following-sibling::td)')
email = (page.xpath('string(//tr[contains(., "Email")]//a/@href)').
split('=')[1] + '@winnipeg.ca')
p = Legislator(name=name, post_id=ward, role='Councillor')
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
p.add_contact('voice', phone, 'legislature')
p.image = photo_url
return p
def mayor_data(url):
page = lxmlize(url)
name = page.xpath('string(//h1)').split('-')[1]
content_node = page.xpath('//div[@class="usercontent"]')[0]
photo_url = urljoin(url, content_node.xpath('string(.//img[1]/@src)'))
email = content_node.xpath('string(.//a/text()[contains(., "@")])')
phone = content_node.xpath('string(.//strong[contains(., "Phone")]/'
'following-sibling::text()[1])').strip()
p = Legislator(name=name, post_id='Strathcona County', role='Mayor')
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
p.image = photo_url
return p
def mayor_data(url, name):
page = lxmlize(url)
photo_url = urljoin(
url,
page.xpath('string((//div[@id="contentcontainer"]//img)[1]/@src)'))
contact_page = lxmlize(MAYOR_CONTACT_URL)
email = contact_page.xpath('string(//a[contains(., "@")][1])')
m = Legislator(name=name, post_id='Regina', role='Mayor')
m.add_source(COUNCIL_PAGE)
m.add_source(url)
m.add_source(MAYOR_CONTACT_URL)
m.add_contact('email', email, None)
m.image = photo_url
return m
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
for link in page.xpath('//div[@class="section"]//a'):
url = link.attrib['href']
if url.endswith('address.html'):
continue
page = lxmlize(url)
role, name = page.xpath('string(//div[@id="content"]/h1)').split(' ', 1)
name = ' '.join(name.split()[:-1])
photo_url = page.xpath('string(//img[@class="float-right"]/@src)')
email = page.xpath('string(//a[starts-with(@href, "mailto:")])')
p = Legislator(name=name, post_id='Saanich', role=role, image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_contact('email', email, None)
yield p
def councillor_data(url, name, role):
page = lxmlize(url)
email = page.xpath('string(//a[contains(@href, "mailto")])')
phone_str = page.xpath('string(//div[@id="content"]//strong[1]/'
'following-sibling::text()[contains(., "Phone")])')
phone = phone_str.split(':')[1]
photo_url = urljoin(
url, page.xpath('string(//div[@id="content"]//img[1]/@src)'))
# TODO: should post_id be "Nieghborhood Liaison"?
m = Legislator(name=name, post_id='Victoria', role=role)
m.add_source(COUNCIL_PAGE)
m.add_source(url)
m.add_contact('email', email, None)
m.add_contact('voice', phone, 'legislature')
m.image = photo_url
return m
def get_people(self):
page = lxmlize(COUNCIL_PAGE, 'iso-8859-1')
mayor_url = page.xpath('//li[@id="pageid193"]//a/@href')[0]
yield scrape_mayor(mayor_url)
councillors = page.xpath('//td[@class="cityfonts"]')
for councillor in councillors:
try:
name = councillor.xpath('.//a')[0].text_content()
except IndexError:
continue
districts = [
x.strip() for x in councillor.xpath('.//span/text()')
if re.sub(u'\xa0', ' ', x).strip()
]
district = districts[1]
if district == 'At Large':
district = 'Moncton'
elif district == 'Deputy Mayor':
district = districts[2]
url = councillor.xpath('.//a')[-1].attrib['href']
page = lxmlize(url)
p = Legislator(name=name, post_id=district, role='Councillor')
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.image = councillor.xpath('.//img/@src')[0]
email = page.xpath('string(.//a[contains(@href, "mailto:")]/@href)'
)[len('mailto:'):]
p.add_contact('email', email, None)
contact_info = page.xpath(
'.//table[@class="whiteroundedbox"]//td/p[contains(text()," ")]'
)[0].text_content()
phone_nos = re.findall(r'(([0-9]{3}-)?([0-9]{3}-[0-9]{4}))',
contact_info)
for phone_no in phone_nos:
if len(re.sub(r'\D', '', phone_no[0])) == 7:
phone = '506-%s' % phone_no[0]
else:
phone = phone_no[0]
p.add_contact('voice', phone, 'legislature')
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
for row in page.xpath('//div[@id="content"]/table/tbody/tr'):
full_name, party_abbr, post = row.xpath('./td//text()')[:3]
name = ' '.join(reversed(full_name.split(',')))
detail_url = row[0][0].attrib['href']
image, phone, email = get_details(detail_url)
p = Legislator(name=name, post_id=post, role='MLA',
party=get_party(party_abbr), image=image)
p.add_source(COUNCIL_PAGE)
p.add_source(detail_url)
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
for councillor_row in page.xpath('//tr'):
post = councillor_row.xpath('string(./td[2]/p/text())')
if post == 'Maire de Laval':
district = 'Laval'
role = 'Maire'
else:
district = re.sub('^C.?irconscription (?:no )?\d+\D- ', '',
post).replace("L'",
'').replace(' ', '').replace(
'bois', 'Bois')
role = 'Conseiller'
full_name = councillor_row.xpath(
'string(./td[2]/p/text()[2])').strip()
name = ' '.join(full_name.split()[1:])
phone = councillor_row.xpath(
'string(.//span[@class="icon-phone"]/following::text())')
email = councillor_row.xpath(
'string(.//a[contains(@href, "mailto:")]/@href)')[len('mailto:'
):]
photo_url = councillor_row[0][0].attrib['src']
p = Legislator(name=name,
post_id=district,
role=role,
image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def get_people(self):
member_page = lxmlize(COUNCIL_PAGE)
table = member_page.xpath('//table')[0]
rows = table.cssselect('tr')[1:]
for row in rows:
(namecell, constitcell, partycell) = row.cssselect('td')
full_name = namecell.text_content().strip()
if full_name.lower() == 'vacant':
continue
(last, first) = full_name.split(',')
name = first.replace('Hon.', '').strip() + ' ' + last.title().strip()
district = ' '.join(constitcell.text_content().split())
party = get_party(partycell.text)
data = {
'elected_office': 'MLA',
'source_url': COUNCIL_PAGE
}
url = namecell.cssselect('a')[0].get('href')
photo, email = get_details(url)
p = Legislator(name=name, post_id=district, role='MLA',
party=party, image=photo)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
mayor_info = page.xpath('//h2[contains(text(), "MAYOR")]//following-sibling::p')[0]
yield self.scrape_mayor(mayor_info)
wards = page.xpath('//h3')
for ward in wards:
district = re.sub('\AWARD \d+ - ', '', ward.text_content())
councillors = ward.xpath('following-sibling::p')
for councillor in councillors:
name = councillor.xpath('./strong')[0].text_content()
p = Legislator(name=name, post_id=district, role='Councillor')
p.add_source(COUNCIL_PAGE)
info = councillor.xpath('./text()')
address = info.pop(0)
p.add_contact('address', address, 'legislature')
# get phone numbers
for line in info:
stuff = re.split(ur'(\xbb)|(\xa0)', line)
tmp = [y for y in stuff if y and not re.match(ur'\xa0', y)]
self.get_tel_numbers(tmp, p)
email = councillor.xpath('string(./a)')
p.add_contact('email', email, None)
yield p
if councillor == councillors[1]:
break
def get_people(self):
member_page = lxmlize(COUNCIL_PAGE)
table = member_page.xpath('//table')[0]
rows = table.cssselect('tr')[1:]
for row in rows:
(namecell, constitcell, partycell) = row.cssselect('td')
full_name = namecell.text_content().strip()
if full_name.lower() == 'vacant':
continue
(last, first) = full_name.split(',')
name = first.replace('Hon.',
'').strip() + ' ' + last.title().strip()
district = ' '.join(constitcell.text_content().split())
party = get_party(partycell.text)
data = {'elected_office': 'MLA', 'source_url': COUNCIL_PAGE}
url = namecell.cssselect('a')[0].get('href')
photo, email = get_details(url)
p = Legislator(name=name,
post_id=district,
role='MLA',
party=party,
image=photo)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
yield p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
councillor_elems = page.xpath('//a[contains(@class, "slide item-")]')
email_links = page.xpath('//a[contains(@href, "mailto:")]')
for elem in councillor_elems:
name_elem = elem.xpath('.//strong')[0]
name = re.search('(Mr\. )?(.+)', name_elem.text).group(2)
position = name_elem.xpath('string(following-sibling::text())')
role = 'Conseiller'
if 'Mayor' in position:
district = 'Brossard'
role = 'Maire'
else:
district = re.sub(r'(?<=[0-9]).+', '', position).strip()
photo = re.search(r'url\((.+)\)', elem.attrib['style']).group(1)
p = Legislator(name=name, post_id=district, role=role, image=photo)
p.add_source(COUNCIL_PAGE)
try:
email_elem = [link for link in email_links
if name in link.text_content().replace(u'\u2019', "'")][0]
email = re.match('mailto:([email protected])', email_elem.attrib['href']).group(1)
p.add_contact('email', email, None)
phone = email_elem.xpath(
'./following-sibling::text()[contains(., "450")]')[0]
p.add_contact('voice', phone, 'legislature')
except IndexError: # oh Francyne/Francine Raymond, who are you, really?
pass
yield p
def mayor_data(page):
# Strip the word "mayor" from the beginning of the photo lavel
photo_node = page.xpath('//img[@class="mayorsPic"]')[0]
name = photo_node.xpath('string(./@alt)').replace('Mayor ', '')
photo_url = photo_node.xpath('string(./@src)')
address_node = page.xpath('//div[@class="address"]')[0]
email = address_node.xpath('string(.//a)')
address = ''.join(address_node.xpath('./p/text()')[:3])
phone = address_node.xpath('string(./p/text()[4])')
p = Legislator(name=name, post_id='Brampton', role='Mayor')
p.add_source(MAYOR_PAGE)
p.add_contact('voice', phone, 'legislature')
p.add_contact('address', address, 'legislature')
p.add_contact('email', email, None)
p.image = photo_url
return p
def councillor_data(url, name, role):
page = lxmlize(url)
email = page.xpath('string(//a[contains(@href, "mailto")])')
phone_str = page.xpath('string(//div[@id="content"]//strong[1]/'
'following-sibling::text()[contains(., "Phone")])')
phone = phone_str.split(':')[1]
photo_url = urljoin(url,
page.xpath('string(//div[@id="content"]//img[1]/@src)'))
# TODO: should post_id be "Nieghborhood Liaison"?
m = Legislator(name=name, post_id='Victoria', role=role)
m.add_source(COUNCIL_PAGE)
m.add_source(url)
m.add_contact('email', email, None)
m.add_contact('voice', phone, 'legislature')
m.image = photo_url
return m
def scrape_mayor(url):
page = lxmlize(url)
name = page.xpath('//div[@class="interiorContentWrapper"]/p/strong/text()')[0]
address = ' '.join(page.xpath('//div[@class="interiorContentWrapper"]/p/text()')[1:3])
address = re.sub(r'\s{2,}', ' ', address)
contact_elem = page.xpath('//div[@class="interiorContentWrapper"]/p[3]')[0]
phone = contact_elem.text.split(':')[1].strip()
email = contact_elem.xpath('string(./a)')
p = Legislator(name=name, post_id='Markham', role='Mayor')
p.add_source(url)
p.add_contact('address', address, 'legislature')
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
yield p
def scrape_person(url):
page = lxmlize(url)
role, name = page.xpath('string(//title)').split(' ', 1)
photo_url = page.xpath('string(//div[@id="content"]//img[@style]/@src)')
email = page.xpath('string(//a[contains(@href, "mailto:")])')
phone = page.xpath('string(//li[contains(text(), "Phone:")])')
p = Legislator(name=name, post_id='Burnaby', role=role, image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_source(url)
p.add_contact('email', email, None)
if phone:
p.add_contact('voice', phone, 'legislature')
return p
def get_people(self):
page = lxmlize(COUNCIL_PAGE)
for person_header_elem in page.xpath('//h2'):
role, name_post = person_header_elem.text.split(' - ')
try:
name, caps_post = re.match(r'(.+) \((.+)\)', name_post).groups()
post = caps_post.title()
except AttributeError:
name = name_post
post = "Clarington"
email = person_header_elem.xpath(
'string(./following-sibling::a[1]/@href)')[len('mailto:'):]
photo_url = person_header_elem.xpath(
'string(./following-sibling::img[1]/@src)')
p = Legislator(name=name, post_id=post, role=role, image=photo_url)
p.add_source(COUNCIL_PAGE)
p.add_contact('email', email, None)
yield p
def councillor_data(url):
page = lxmlize(url)
name, ward = re.match('Councillor (.+) - (.+)',
page.xpath('string(//h1)')).groups()
content_node = page.xpath('//div[@class="usercontent"]')[0]
photo_url_rel = content_node.xpath('string(.//img[1]/@src)')
photo_url = urljoin(COUNCIL_PAGE, photo_url_rel)
email = content_node.xpath('string(.//a/text()[contains(., "@")])')
phone = content_node.xpath('string(.//strong[contains(., "Phone")]/'
'following-sibling::text()[1])').strip()
p = Legislator(name=name, post_id=ward, role='Councillor')
p.add_source(COUNCIL_PAGE)
p.add_source(url)
if phone:
p.add_contact('voice', phone, 'legislature')
p.add_contact('email', email, None)
p.image = photo_url
return p
