本文整理汇总了Python中pupa.scrape.Person.extras['name_middle']方法的典型用法代码示例。如果您正苦于以下问题：Python Person.extras['name_middle']方法的具体用法？Python Person.extras['name_middle']怎么用？Python Person.extras['name_middle']使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pupa.scrape.Person的用法示例。
在下文中一共展示了Person.extras['name_middle']方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: scrape_chamber
# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import extras['name_middle'] [as 别名]
def scrape_chamber(self, chamber=None):
if chamber == 'upper':
url = ('http://webserver.rilin.state.ri.us/Documents/Senators.xls')
rep_type = 'Senator'
contact_url = 'http://webserver.rilin.state.ri.us/Email/SenEmailListDistrict.asp'
elif chamber == 'lower':
url = ('http://webserver.rilin.state.ri.us/Documents/Representatives.xls')
rep_type = 'Representative'
contact_url = 'http://webserver.rilin.state.ri.us/Email/RepEmailListDistrict.asp'
contact_page = self.lxmlize(contact_url)
contact_info_by_district = {}
for row in contact_page.xpath('//tr[@valign="TOP"]'):
tds = row.xpath('td')
(detail_link, ) = tds[link_col_ix].xpath('.//a/@href')
# Ignore name (2nd col). We have a regex built up below for the spreadsheet name
# I don't want to touch
district, _, email, phone = [td.text_content().strip() for td in tds[:link_col_ix]]
contact_info_by_district[district] = {
'email': email,
'phone': phone,
'detail_link': detail_link,
}
self.urlretrieve(url, 'ri_leg.xls')
wb = xlrd.open_workbook('ri_leg.xls')
sh = wb.sheet_by_index(0)
for rownum in range(1, sh.nrows):
d = {
field: sh.cell(rownum, col_num).value
for field, col_num in excel_mapping.items()
}
# Convert float to an int, and then to string, the format required by pupa
district = str(int(d['district']))
if d['full_name'].upper() == "VACANT":
self.warning(
"District {}'s seat is vacant".format(district))
continue
contact_info = contact_info_by_district[district]
# RI is very fond of First M. Last name formats and
# they're being misparsed upstream, so fix here
(first, middle, last) = ('', '', '')
full_name = re.sub(r"^{}(?=\s?[A-Z].*$)".format(rep_type), '', d['full_name']).strip()
if re.match(r'^\S+\s[A-Z]\.\s\S+$', full_name):
(first, middle, last) = full_name.split()
# Note - if we ever need to speed this up, it looks like photo_url can be mapped
# from the detail_link a la /senators/Paolino/ -> /senators/pictures/Paolino.jpg
detail_page = self.lxmlize(contact_info['detail_link'])
(photo_url, ) = detail_page.xpath('//div[@class="ms-WPBody"]//img/@src')
person = Person(
primary_org=chamber, district=district, name=full_name,
party=translate[d['party']], image=photo_url
)
person.extras['town_represented'] = d['town_represented']
person.extras['name_first'] = first
person.extras['name_middle'] = middle
person.extras['name_last'] = last
person.add_link(detail_link)
person.add_contact_detail(type='address', value=d['address'], note='District Office')
person.add_contact_detail(
type='voice', value=contact_info['phone'], note='District Office')
person.add_contact_detail(
type='email', value=contact_info['email'], note='District Office')
person.add_source(contact_url)
person.add_source(contact_info['detail_link'])
yield person