def process_item(self, item):
name = CSS("a").match(item)[2].text_content()
name = re.sub(r"Contact Assembly Member", "", name).strip()
party = CSS("td").match(item)[2].text_content().strip()
if party == "Democrat":
party = "Democratic"
district = CSS("td").match(item)[1].text_content().strip().lstrip("0")
# District 18 has a vacant spot
if name == "edit":
self.skip("skipping Vacant seat in District {}".format(district))
photo_url = CSS("img").match(item, min_items=0)
if photo_url:
photo_url = photo_url[0].get("src")
p = ScrapePerson(
name=name,
state="ca",
chamber="lower",
district=district,
party=party,
image=photo_url,
)
capitol_office_header = CSS("h3").match(item)[0].text_content()
capitol_office_text = (
XPath(
"//*[@id='block-views-view-members-block-1']/div/div/div/table/tbody/tr[1]/td[4]/text()"
)
.match(item)[1]
.strip()
)
capitol_office_text, capitol_office_phone = capitol_office_text.split("; ")
capitol_office_address = capitol_office_header + capitol_office_text
p.capitol_office.address = capitol_office_address
p.capitol_office.voice = capitol_office_phone
district_offices = XPath(".//td/p[1]/text()").match(item)
for office in district_offices:
district_address, district_phone = office.split("; ")
p.add_office(
classification="district",
address=district_address.strip(),
voice=district_phone.strip(),
)
url = CSS("a").match(item)[0].get("href")
p.add_link(url)
p.add_source(self.source.url)
return p
def process_item(self, item):
lastname = item["LastName"]
firstname = item["FirstName"]
middlename = item["MiddleName"]
name = firstname + " " + middlename + " " + lastname
legislativebody = item["LegislativeBody"]
if legislativebody == "H":
chamber = "lower"
elif legislativebody == "S":
chamber = "upper"
district_county = item["County"]
district_num = item["District"]
district = f"{district_county} {district_num.lstrip('0')}"
party = item["party"]
if party == "D" or party == "d":
party = "Democratic"
elif party == "R" or party == "r":
party = "Republican"
p = ScrapePerson(
name=name, state="nh", chamber=chamber, district=district, party=party
)
p.add_source(self.source.url)
p.family_name = lastname
p.given_name = firstname
county = item["County"]
if county != "":
p.extras["county"] = county
electedStatus = item["electedStatus"].strip()
if electedStatus != "":
p.extras["elected status"] = electedStatus
addr = item["Address"].strip()
if addr != "":
addr += " "
if item["address2"].strip() != "":
addr += item["address2"]
addr += " "
addr += item["city"]
addr += ", NH "
addr += item["Zipcode"]
if item["Phone"].strip() != "":
p.add_office(
classification="primary", address=addr, voice=item["Phone"]
)
else:
p.add_office(classification="primary", address=addr)
# is this primary office? or district office?
if item["WorkEmail"].strip() != "":
p.email = item["WorkEmail"].strip()
if item["GenderCode"].strip() != "":
p.extras["gender code"] = item["GenderCode"].strip()
if chamber == "upper":
detail_link = f"http://www.gencourt.state.nh.us/Senate/members/webpages/district{district_num}.aspx"
p.add_source(detail_link)
p.add_link(detail_link, note="homepage")
return SenDetail(p, source=detail_link)
# seat_number = seat_map[item["seatno"]]
# detail_link = f"http://www.gencourt.state.nh.us/house/members/member.aspx?member={seat_number}"
# return HouseDetail(p, source=detail_link)
return p
def process_item(self, item):
name = XPath(".//h3/text()").match(item)[0]
if name.endswith(" (R)"):
party = "Republican"
elif name.endswith(" (D)"):
party = "Democratic"
else:
self.skip("skipping " + name)
name = name.split(" (")[0]
district = (
XPath('.//div[contains(@class, "senator-district")]/div/text()'
).match(item)[0].strip().lstrip("0"))
photo_url = XPath(".//img/@src").match_one(item)
p = ScrapePerson(
name=name,
state="ca",
chamber="upper",
district=district,
party=party,
image=photo_url,
)
capitol_office = XPath(
".//div[contains(@class, 'views-field-field-senator-capitol-office')]//p"
).match_one(item)
capitol_address, capitol_phone = (
capitol_office.text_content().replace(u"\xa0", " ").split("; "))
p.capitol_office.address = capitol_address.strip()
p.capitol_office.voice = capitol_phone.strip()
district_office = XPath(
".//div[contains(@class, 'views-field-field-senator-district-office')]"
).match_one(item)
for line in district_office.text_content().strip().splitlines():
try:
if re.search(r"District Offices?", line):
continue
addr, phone = line.strip().replace(u"\xa0", " ").split("; ")
p.add_office(
classification="district",
address=addr.strip(),
voice=phone.strip(),
)
except ValueError:
# Steven Bradford address/phone separated by period instead of semi-colon
if re.search(r"\w+\.\s\(\d{3}\)", line):
addr, phone = line.strip().replace(u"\xa0",
" ").split(". (")
phone = "(" + phone
p.add_office(
classification="district",
address=addr.strip(),
voice=phone.strip(),
)
url = XPath(".//a/@href").match(item)[0]
p.add_link(url)
p.add_source(self.source.url)
return p