def parse(self, response):
"""获取医院相关信息"""
self.logger.info('>>>>>>正在抓取医院相关信息……')
hospital_info = json.loads(response.text)
for each_hospital in hospital_info[3:4]:
is_medicare = '是' if str(each_hospital.get('Ismedicalcard', '')) == '1' else '否'
loader = CommonLoader(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', each_hospital.get('hospitalname', ''))
loader.add_value('hospital_level', each_hospital.get('levelName', ''))
loader.add_value('hospital_addr', each_hospital.get('address', ''))
loader.add_value('hospital_pro', '四川')
loader.add_value('hospital_city', each_hospital.get('areaName', ''))
loader.add_value('is_medicare', is_medicare)
loader.add_value('dataSource_from', self.source_from)
loader.add_value('update_time', now_day())
hospital_item = loader.load_item()
yield hospital_item
hospital_id = each_hospital.get('hospitalid')
if hospital_id:
dept_request = FormRequest(self.dept_link,
headers=self.headers,
callback=self.parse_dept_info,
formdata={'hospitalId': str(hospital_id)},
dont_filter=True)
self.headers['Referer'] = 'http://www.scgh114.com/web/register/gh'
yield dept_request
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value(
'consulting_hour', '急诊和临床住院科室_24小时值班;'
'行政及其它_上午8:00~12:00,下午14:00~17:00')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '中医医院')
loader.add_value('hospital_addr', '四川省彭州市天彭镇南大街396号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '彭州市')
loader.add_value('hospital_county', '')
loader.add_value('hospital_phone', '028-83701908')
loader.add_xpath(
'hospital_intro', '//div[@id="about-right-b"]',
MapCompose(remove_tags, custom_remove_tags, clean_info))
# loader.add_value('is_medicare', '是')
# loader.add_value('medicare_type', '成都市医保、工伤保险定点医院')
loader.add_value('registered_channel', '官网')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '门诊上午_8:00-12:00;门诊下午_14:00-17:30')
loader.add_value('hospital_level', '二级甲等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '综合医院')
loader.add_value('hospital_addr', '成都市东三环龙泉驿区十陵街道江华路8号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '龙泉驿区')
loader.add_value(
'hospital_phone', '急救电话_028-84615120;电话咨询_028-84604546转科室;'
'24小时医护热线_028-84615789')
loader.add_xpath('hospital_intro', '//article[@class="content"]/div',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('is_medicare', '是')
loader.add_value('medicare_type', '成都市医保、工伤保险定点医院')
loader.add_value('registered_channel', '官网或官方微信公众号(工作日),法定节假日电话预约')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '上午8：00—12:00;下午2:00—5:30')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '妇幼保健院')
loader.add_value('hospital_addr', '四川省成都市双流区东升街道涧槽中街396号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '')
loader.add_value(
'hospital_phone', '母婴咨询热线_028-85884888(工作日);'
'总值班电话_028-85808438;'
'预约挂号电话_028-85801029(7:30-19:30)')
loader.add_xpath('hospital_intro', '//div[@class="describe htmledit"]',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('is_medicare', '是')
# loader.add_value('medicare_type', '')
loader.add_value('registered_channel', '电话预约;自助挂号机;诊室预约;'
'医院微信公众号;健康双流;现场')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
def parse(self, response):
self.logger.info('正在抓取{}:医院信息'.format(self.hospital_name))
loader = MedicalMapLoader(item=HospitalInfoItem(), response=response)
# loader.add_value('hospital_id', self.hospital_id)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '普通门诊上午_8:00-12:00;普通门诊下午13：00-16：30')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '综合医院')
# loader.add_value('hospital_addr', '四川省金堂县赵镇金广路886号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '金堂县')
loader.add_value('hospital_phone', '医院服务电话_028-84902884;服务质量监督投诉电话_028-84932532;'
'急诊急救电话_18181938532;产科急救电话_18181938532;'
'医保结算电话_028-84932721;'
'预约挂号电话_028-84931443;预约挂号电话_028-84902884;预约挂号电话_028-61568616')
loader.add_xpath('hospital_intro', '//div[@class="baseRight-intro"]/p[position()<7]/span/text()')
loader.add_value('is_medicare', '')
loader.add_value('medicare_type', '')
loader.add_value('vaccine_name', '')
loader.add_value('is_cpc', '')
loader.add_value('is_bdc', '')
loader.add_value('cooperative_business', '')
loader.add_value('hospital_district', '')
loader.add_value('registered_channel', '微信公众号_' + self.hospital_name)
loader.add_value('dataSource_from', '官网:http://www.jintangyy.com/index.aspx')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
request = Request(self.dep_link, callback=self.parse_hospital_dep)
request.meta['Referer'] = response.url
yield request
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '妇幼保健院')
loader.add_value('hospital_addr', '成都市温江区万春路140')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '')
loader.add_value('hospital_phone', '24小时急救电话_028-82723131;咨询电话_围产期保健_028-82715727;'
'咨询电话_妇科门诊_028-82711383;咨询电话_儿童保健_028-82711527;'
'咨询电话_婚检科_028-82720337;'
'投诉电话_028-82724901(上班时间);投诉电话_13688488598(下班时间)')
loader.add_xpath('hospital_intro',
'//div[@id="info_txt"]',
MapCompose(remove_tags, custom_remove_tags))
# loader.add_value('is_medicare', '是')
# loader.add_value('medicare_type', '')
loader.add_value('registered_channel', '电话预约;挂号窗口;医院微信公众号')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
def parse(self, response):
"""获取医院信息"""
all_hospital_links = response.xpath('//div[@class="c-hidden disen-list-hos c-f12"]/ul/li')
self.logger.info('该地区共{}家医院'.format(str(len(all_hospital_links))))
for each_hospital_link in all_hospital_links:
loader = YiHuLoader(item=HospitalInfoItem(), selector=each_hospital_link)
loader.add_xpath('hospital_name', 'a/text()')
loader.add_xpath('hospital_level', 'span/text()', MapCompose(remove_number2))
hospital_link = each_hospital_link.xpath('a/@href').extract_first('')
if hospital_link:
# 医院信息
hospital_detail_link = re.sub(r'/sc/', '/detail/', hospital_link)
contact_hos_link = re.sub(r'/sc/', '/contact/', hospital_link)
hospital_detail_request = Request(hospital_detail_link,
headers=self.headers,
callback=self.parse_hospital_detail,
meta={'loader': loader,
'contact_hos_link': contact_hos_link})
self.headers['Referer'] = response.url
yield hospital_detail_request
# 医院科室信息
dep_request = Request(hospital_link,
headers=self.headers,
callback=self.parse_hospital_dep)
self.headers['Referer'] = response.url
yield dep_request
def parse_hospital_info(self, response):
self.logger.info('>>>>>>正在抓取:医院信息>>>>>>')
try:
# 获取区或县
hospital_address = response.xpath(
'//div[@class="yy_js clearfix"]/div/dl/dd[1]/text()'
).extract_first('')
if hospital_address:
hospital_county = get_county2('中国|江苏省|江苏|南京市|南京',
hospital_address)
else:
hospital_county = None
# 获取医院信息
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name',
'//div[@class="yy_til"]/h2/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_level',
response.meta.get('hospital_level'),
MapCompose(custom_remove_tags, clean_info))
loader.add_xpath(
'hospital_addr',
'//div[@class="yy_js clearfix"]/div/dl/dd[1]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', '江苏省')
loader.add_value('hospital_city', '南京市')
loader.add_value('hospital_county', hospital_county)
loader.add_xpath(
'hospital_phone',
'//div[@class="yy_js clearfix"]/div/dl/dd[2]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_intro', '//dd[@id="wrap"]',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('hospital_url', response.url)
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
# 获取科室信息
# self.logger.info('>>>>>>正在抓取{}:科室详细信息>>>>>>')
all_dept_links = response.xpath(
'//dl[@class="kfyy clearfix"]/dd/span/a/@href').extract()
for each_dept_link in all_dept_links:
dept_link = urljoin(
self.host,
re.sub(r';jsessionid=(.*?)\?', '?', each_dept_link))
self.headers['Referer'] = response.url
yield Request(dept_link,
headers=self.headers,
callback=self.parse_hospital_dep_detail)
except Exception as e:
self.logger.error('在抓取医院详细信息和科室的过程中出错了,原因是：{}'.format(repr(e)))
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '门诊时间_8:30-17:30;急诊时间_7*24小时')
loader.add_value('hospital_level', '二级甲等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '中医医院')
loader.add_value(
'hospital_addr', '川化病区:青白江区化工北路41号（原川化医院）;'
'城厢病区:青白江区城厢镇大南街51号（中医血防医院）;'
'中医名医馆地址：中医医院川化病区一号楼1楼')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '青白江区')
loader.add_value('hospital_phone', '24小时急诊电话_028-83632835')
loader.add_xpath('hospital_intro',
'//div[@class="right-about clearfix"]',
MapCompose(remove_tags))
loader.add_value('registered_channel', '医院挂号室')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
# 医院信息
yield hospital_info_item
# 获取科室信息
dept_links = response.xpath(
'//ul[@id="navul"]/li[5]/ul/li|//ul[@id="navul"]/li[6]/ul/li')
for each_dept_link in dept_links:
dept_link = each_dept_link.xpath('a/@href').extract_first('')
dept_name = each_dept_link.xpath('a/text()').extract_first('')
if dept_link and dept_name:
dept_request = Request(urljoin(self.host, dept_link),
headers=self.headers,
callback=self.parse_hospital_dep_detail,
meta={'dept_name': dept_name})
dept_request.meta['Referer'] = response.url
yield dept_request
# 获取医生信息
doctor_links = response.xpath('//ul[@id="navul"]/li[8]/ul/li')
for each_dept_link in doctor_links:
dept_link = each_dept_link.xpath('a/@href').extract_first('')
dept_name = each_dept_link.xpath('a/text()').extract_first('')
if dept_link and dept_name:
dept_request = Request(urljoin(self.host, dept_link),
headers=self.headers,
callback=self.parse_doctor_info,
meta={'dept_name': dept_name})
dept_request.meta['Referer'] = response.url
yield dept_request
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '门诊上午_8:00-12:00;门诊下午_14:00-17:30')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '中医医院')
loader.add_value('hospital_addr', '四川省成都市郫都区南大街342号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '郫都区')
loader.add_value(
'hospital_phone',
'咨询电话_028-87920858;急诊电话_028-87925131;预约挂号_028-87925042;'
'投诉电话_028-87920858;人事招聘_028-87925158;医保出入院处_028-87925172;'
'体验科_028-87922056')
loader.add_xpath('hospital_intro',
'//div[@class="rightPanel"]/p[position()>2]',
MapCompose(remove_tags))
loader.add_value('is_medicare', '是')
loader.add_value('registered_channel', '官方微信公众号或华医通APP')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
# 医院信息
yield hospital_info_item
# 获取科室信息
dept_request = Request(self.dept_link,
headers=self.headers,
callback=self.parse_hospital_dep,
dont_filter=True)
dept_request.meta['Referer'] = self.entry_url
yield dept_request
# 获取医生信息
for each_dept_link in self.doctor_links:
dept_request = Request(each_dept_link,
headers=self.headers,
callback=self.parse_doctor_info,
dont_filter=True)
dept_request.meta['Referer'] = each_dept_link
yield dept_request
def parse(self, response):
"""获取医院信息"""
self.logger.info('正在抓取{}:医院信息'.format(self.hospital_name))
loader = PxfybjyLoader(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '门诊上午_8:00-12:00;门诊下午14:00-17:30')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '妇幼保健院')
loader.add_value('hospital_addr', '郫都区郫筒街道新南街283号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '郫都区')
loader.add_value(
'hospital_phone',
'产科急救_028-87922244;儿科急救_028-87931629;产检门诊_028-87924116;'
'婚检_028-87885339;儿保科_028-87931911')
loader.add_xpath(
'hospital_intro',
'//div[@class="FrontComContent_detail01-1468317290474_htmlbreak"]/'
'p[position()<9]')
# loader.add_value('is_medicare', '')
# loader.add_value('medicare_type', '')
# loader.add_value('vaccine_name', '')
# loader.add_value('is_cpc', '')
# loader.add_value('is_bdc', '')
# loader.add_value('cooperative_business', '')
# loader.add_value('hospital_district', '')
# loader.add_value('registered_channel', '')
loader.add_value('dataSource_from',
'官网:http://www.pxfybjy.cn/index.html')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
# 医院信息
yield hospital_info_item
# 科室信息
request = Request(self.index_link,
headers=self.headers,
callback=self.parse_hospital_dep)
request.meta['Referer'] = response.url
yield request
def parse_hospital_info(self, response):
self.logger.info('>>>>>>正在抓取:医院详细信息>>>>>>')
try:
# 获取医院信息
hospital_info = json.loads(response.text)
# 获取医院等级
hospital_level_info = hospital_info.get('HIS_LVL')
if hospital_level_info == '3':
hospital_level = '三级'
elif hospital_level_info == '2':
hospital_level = '二级'
elif hospital_level_info == '1':
hospital_level = '一级'
else:
hospital_level = None
# 获取医院所在区或县
hospital_address = hospital_info.get('HIS_AD')
if hospital_address:
hospital_county = get_county2('中国|广东省|广东|广州市|广州',
hospital_address)
else:
hospital_county = None
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', hospital_info.get('HIS_NM'))
loader.add_value('hospital_level', hospital_level)
loader.add_value('hospital_category', '')
loader.add_value('hospital_addr', hospital_address)
loader.add_value('hospital_pro', '广东省')
loader.add_value('hospital_city', '广州市')
loader.add_value('hospital_county', hospital_county)
loader.add_value('hospital_phone', hospital_info.get('TEL_NO'))
loader.add_value('hospital_intro', hospital_info.get('HIS_RM'))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('hospital_url', response.url)
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
except Exception as e:
self.logger.error('在抓取医院详细信息过程中出错了,原因是：{}'.format(repr(e)))
def parse(self, response):
"""获取医院信息"""
self.logger.info('正在抓取{}:医院信息'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '8:00-17:00')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '中医医院')
loader.add_value('hospital_addr', '成都市双流区东升街道花园路二段（新院）,淳化街205号（老院）')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '成都市')
loader.add_value('hospital_county', '')
loader.add_value('hospital_phone', '预约电话_028-69803716;体检咨询_028-85808932')
loader.add_xpath('hospital_intro',
'//div[@class="text"]',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('registered_channel', '实名制电话预约、现场预约、自助机预约、诊间预约')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
# 医院信息
yield hospital_info_item
def parse_hospital_info(self, response):
self.logger.info('>>>>>>正在抓取医院详细信息>>>>>>')
try:
hospital_address = response.xpath(
'//b[contains(text(),"医院地址")]/'
'ancestor::td[1]/text()').extract_first('')
hospital_county = get_county2('中国|广东省|广东|珠海市|珠海', hospital_address)
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath(
'hospital_name',
'//b[contains(text(),"医院全称")]/ancestor::td[1]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath(
'hospital_level',
'//b[contains(text(),"医院级别")]/ancestor::td[1]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_addr', hospital_address,
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', '广东省')
loader.add_value('hospital_city', '珠海市')
loader.add_value('hospital_county', hospital_county,
MapCompose(custom_remove_tags))
loader.add_xpath(
'hospital_phone',
'//b[contains(text(),"联系电话")]/ancestor::td[1]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath(
'hospital_intro', '//b[contains(text(),"简介")]/ancestor::td[1]',
MapCompose(remove_tags, custom_remove_tags, match_special))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('crawled_url', response.url)
loader.add_value('update_time', now_day())
hospital_item = loader.load_item()
yield hospital_item
except Exception as e:
self.logger.error('在抓取医院详细信息过程中出错了,原因是：{}'.format(repr(e)))
def parse(self, response):
"""获取医院信息"""
self.logger.info('>>>>>>正在抓取{}:医院信息>>>>>>'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '门诊时间(无假日医院)8:30-17:30')
loader.add_value('hospital_level', '三级乙等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '专科医院')
loader.add_value('hospital_addr', '绵阳市经开区红塔路16号（绵阳市红星街97号）')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '绵阳市')
loader.add_value('hospital_county', '')
loader.add_value('hospital_phone', '0816-2265553;0816-2261517')
loader.add_xpath('hospital_intro',
'//div[@class="content-left pull-left"]',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('is_medicare', '是')
# loader.add_value('medicare_type', '')
loader.add_value('registered_channel', '现场预约(一楼挂号交费处);电话预约;官网')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
# 科室信息
dept_links = response.xpath(
'//div[@class="ddsmoothmenu"]/ul/li[position()=4]/ul/li')
for each_dept_link in dept_links[0:1]:
dept_link = each_dept_link.xpath('a/@href').extract_first('')
dept_name = each_dept_link.xpath('a/text()').extract_first('')
if dept_link and dept_name:
dept_request = Request(dept_link,
headers=self.headers,
callback=self.parse_hospital_dep,
meta={'dept_name': dept_name})
dept_request.meta['Referer'] = response.url
yield dept_request
def parse(self, response):
self.logger.info('>>>>>>正在抓取所有医院信息>>>>>>')
all_hospitals = json.loads(response.text)
for each_hospital in all_hospitals.get('list'):
hospital_name = each_hospital.get('hospitalname')
hospital_address = each_hospital.get('address')
hospital_county = get_county2('中国|广东省|广东|中山市|中山', hospital_address)
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', hospital_name,
MapCompose(custom_remove_tags))
loader.add_value('hospital_addr', hospital_address,
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', '广东省')
loader.add_value('hospital_city', '中山市')
loader.add_value('hospital_county', hospital_county,
MapCompose(custom_remove_tags))
loader.add_value('hospital_phone',
each_hospital.get('telephoneno'),
MapCompose(custom_remove_tags))
loader.add_value('hospital_intro',
each_hospital.get('information'),
MapCompose(custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('hospital_url', response.url)
loader.add_value('update_time', now_day())
hospital_item = loader.load_item()
yield hospital_item
# 获取科室信息、医生信息
hospital_id = each_hospital.get('hospitalid')
if hospital_id:
self.headers['Referer'] = self.entry_url
yield Request(self.hospital_detail_url.format(hospital_id),
headers=self.headers,
callback=self.parse_hospital_dep,
meta={'hospital_name': hospital_name})
def parse(self, response):
"""获取医院信息"""
self.logger.info('正在抓取{}:医院信息'.format(self.hospital_name))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_value('hospital_name', self.hospital_name)
loader.add_value('consulting_hour', '上午_8:00-12:00;下午14:00-17:30')
loader.add_value('hospital_level', '二级甲等')
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '综合医院')
loader.add_value('hospital_addr', '四川都江堰市发展路89号')
loader.add_value('hospital_pro', '四川省')
loader.add_value('hospital_city', '都江堰市')
loader.add_value('hospital_county', '')
loader.add_value(
'hospital_phone',
'急救电话_028-68963120;免费咨询电话_028-69219766;投诉电话_028-69263900 ')
loader.add_xpath('hospital_intro', '//div[@class="fleft wd740"]')
loader.add_value('registered_channel', '电话')
loader.add_value('dataSource_from', '医院官网')
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
# 医院信息
yield hospital_info_item
# 科室信息
# 第一版 获取导航菜单子菜单中的科室信息,不全只有10个
# dept_links = response.xpath('//div[@id="head1_ksdh"]/div/div/a')
# if dept_links:
# for each_dept_link in dept_links:
# dept_link = each_dept_link.xpath('@href').extract_first('')
# dept_name = each_dept_link.xpath('text()').extract_first('')
# if dept_link:
# dept_request = Request(urljoin(self.host, dept_link),
# headers=self.headers,
# callback=self.parse_hospital_dep_detail,
# meta={'dept_name': dept_name})
# dept_request.meta['Referer'] = response.url
# yield dept_request
# 获取科室信息,第二版
# 获取默认页面的科室信息
dept_default_request = Request(self.dept_link,
headers=self.headers,
callback=self.parse_hospital_dep_detail,
meta={'dept_name': '门诊部'},
dont_filter=True)
dept_default_request.meta['Referer'] = response.url
yield dept_default_request
# 获取默认页面中的其他科室信息
dept_request = Request(self.dept_link,
headers=self.headers,
callback=self.parse_hospital_dep,
dont_filter=True)
dept_request.meta['Referer'] = response.url
yield dept_request
# 医生信息,官网翻页不太好用
for each_doctor_link in self.doctor_link_list:
doctor_request = Request(each_doctor_link,
headers=self.headers,
callback=self.parse_doctor_info)
doctor_request.meta['Referer'] = response.url
yield doctor_request
def parse_hospital_info(self, response):
hospital_name = response.meta.get('hospital_name')
self.logger.info('>>>>>>正在抓取[{}]医院信息和科室信息>>>>>>'.format(hospital_name))
hospital_city = response.xpath(
'//div[@class="jieshao_zi"]/p[4]/text()').extract()
if hospital_city:
hospital_address = custom_remove_tags(''.join(hospital_city))
hospital_city2 = get_city(hospital_address)
useless_info = '中国|湖南省|湖南|{}'.format(hospital_city2)
hospital_county = get_county2(useless_info, hospital_address)
else:
hospital_county = None
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name',
'//div[@class="jieshao_zi"]/p/font/text()',
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_level',
'//div[@class="jieshao_zi"]/p[2]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_type', '公立')
loader.add_value('hospital_category', '')
loader.add_xpath('hospital_addr',
'//div[@class="jieshao_zi"]/p[4]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', '湖南省')
loader.add_xpath('hospital_city',
'//div[@class="jieshao_zi"]/p[4]/text()',
MapCompose(custom_remove_tags, get_city))
loader.add_value('hospital_county', hospital_county)
loader.add_xpath('hospital_phone',
'//div[@class="jieshao_zi"]/p[3]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath(
'hospital_intro', '//div[@id="starlist"]',
MapCompose(remove_tags, custom_remove_tags, clean_info))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
# 获取科室信息
self.logger.info('>>>>>>正在抓取[{}]科室信息>>>>>>'.format(hospital_name))
dept_links = response.xpath('//div[@class="xuanze_kslb"]')
if dept_links:
for each_dept_link in dept_links:
dept_type = each_dept_link.xpath(
'div[1]/ul/li/text()').extract_first('')
all_dept_links = each_dept_link.xpath('div[2]/ul/li/a')
for dept_link in all_dept_links:
# dept_name = dept_link.xpath('text()').extract_first('')
data_info = dept_link.xpath('@onclick').extract_first('')
if data_info:
data_info = ''.join(re.findall(r'\S+', data_info))
is_sp_time = re.search(r'isSpTime:\'(.*?)\'',
data_info)
pay_mode = re.search(r'paymode:\'(.*?)\'', data_info)
dept_id = re.search(r'platformDeptId:\'(.*?)\'',
data_info)
hos_id = re.search(r'platformHosId:\'(.*?)\'',
data_info, S)
dept_name = re.search(r'tempDeptName:\'(.*?)\'',
data_info, S)
org_name = re.search(r'orgname:\'(.*?)\'', data_info,
S)
if dept_id and hos_id and dept_name and org_name:
is_sp_time = is_sp_time.group(1)
pay_mode = pay_mode.group(1)
dept_id = dept_id.group(1)
hos_id = hos_id.group(1)
dept_name = dept_name.group(1)
org_name = org_name.group(1)
data = {
'isSpTime': str(is_sp_time),
'paymode': quote(pay_mode),
'doctorCollectResult': '',
'platformDeptId': str(dept_id),
'orgname': quote(org_name),
'tempDeptName': quote(dept_name),
'platformHosId': str(hos_id),
'platformDoctorId': ''
}
self.headers.update({
'Content-Type':
'application/x-www-form-urlencoded',
'Origin': 'http://www.hnyygh.com',
'Referer':
'http://www.hnyygh.com/searchDeptmentAction.action',
'Pragma': 'no-cache'
})
splash_args = {
'url': self.dept_detail_url,
'headers': self.headers,
'lua_source': self.dept_script,
'data': data
}
yield SplashRequest(
self.dept_detail_url,
endpoint='execute',
args=splash_args,
dont_filter=True,
headers=self.headers,
callback=self.parse_hospital_dep_detail,
meta={
'dept_type': dept_type,
'dept_name': dept_name,
'hospital_name': org_name
})
# 获取医生信息
data = {
'platformDeptId': dept_id,
'platformHosId': hos_id,
'platformDoctorId': '',
'nextNumInfo': '0'
}
self.headers.update({
'Content-Type':
'application/x-www-form-urlencoded',
'Origin':
'http://www.hnyygh.com',
'Referer':
'http://www.hnyygh.com/searchOrderNumInfoAction.action'
})
splash_args = {
'url': self.doctor_url,
'headers': self.headers,
'lua_source': self.dept_script,
'data': data
}
yield SplashRequest(
self.doctor_url,
endpoint='execute',
args=splash_args,
dont_filter=True,
headers=self.headers,
callback=self.parse_doctor_info,
meta={
'dept_type': dept_type,
'dept_name': dept_name,
'dept_id': dept_id,
'hospital_name': org_name
})
def parse_hospital_info(self, response):
self.logger.info('>>>>>>正在抓取:医院详细信息>>>>>>')
try:
# 获取医院信息
# 获取医院等级与地区
hospital_info = response.xpath(
'//p[@class="yygh_box_top_p2"]').extract()
hospital_info2 = custom_remove_tags(
remove_tags(''.join(hospital_info)))
hospital_level = hospital_info2.split(':')[1].replace('区域', '')
hospital_county = hospital_info2.split(':')[2].replace('分类', '')
if hospital_level:
res = re.search(r'(.*等|.*级|.*合格|.*甲)(.*?)$', hospital_level)
if res:
h_l = res.group(1)
h_c = res.group(2)
if h_c:
h_c_2 = re.sub(r'合格|医院', '', h_c)
if h_c_2:
h_c = '{0}{1}'.format(h_c_2, '医院')
else:
h_l = h_c = None
else:
h_l = h_c = None
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name',
'//p[@class="yygh_box_top_p"]/strong/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_level', h_l,
MapCompose(custom_remove_tags))
loader.add_value('hospital_category', h_c)
loader.add_xpath(
'hospital_addr',
'//span[@class="yygh_box_con_dl_span1"]/ancestor::dl[1]/dd[1]/p/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', '')
loader.add_value('hospital_city', '北京市')
loader.add_value('hospital_county', hospital_county,
MapCompose(custom_remove_tags))
loader.add_xpath(
'hospital_phone',
'//span[@class="yygh_box_con_dl_span3"]/ancestor::dl[1]/dd[1]/p/text()',
MapCompose(custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('hospital_url', response.url)
loader.add_value('update_time', now_day())
# 获取医院介绍
hospital_intro_link = response.xpath(
'//a[contains(text(),"医院介绍")]/@href').extract_first('')
if hospital_intro_link:
hospital_intro_link = urljoin(self.host, hospital_intro_link)
self.headers['Referer'] = response.url
yield Request(hospital_intro_link,
headers=self.headers,
callback=self.parse_hospital_detail_info,
meta={'loader': loader})
# 获取科室信息
all_dept_links = response.xpath('//div[@class="kfyuks_yyksbox"]')
for each_dept_link in all_dept_links:
dept_type = each_dept_link.xpath(
'div[1]/text()').extract_first('')
dept_info = each_dept_link.xpath(
'div[2]/div/ul/li/a/text()').extract()
for each_dept_info in dept_info:
dept_loader = CommonLoader2(item=HospitalDepItem(),
response=response)
dept_loader.add_value('dept_name', each_dept_info,
MapCompose(custom_remove_tags))
dept_loader.add_value('dept_type', dept_type,
MapCompose(custom_remove_tags))
dept_loader.add_xpath(
'hospital_name',
'//p[@class="yygh_box_top_p"]/strong/text()',
MapCompose(custom_remove_tags))
dept_loader.add_value('dept_info', '')
dept_loader.add_value('dataSource_from',
self.data_source_from)
dept_loader.add_value('update_time', now_day())
dept_item = dept_loader.load_item()
yield dept_item
except Exception as e:
self.logger.error('在抓取医院详细信息过程中出错了,原因是：{}'.format(repr(e)))
def parse_hospital_info(self, response):
self.logger.info('>>>>>>正在抓取:医院详细信息和科室信息>>>>>>')
try:
# 获取医院信息
hospital_type = response.meta.get('hospital_type')
hospital_category = '{0}{1}'.format(
hospital_type, '医院') if hospital_type else None
hospital_info = custom_remove_tags(
remove_tags(''.join(
response.xpath('//td[@class='
'"title_yh14"]').extract())))
hospital_address = get_hospital_info(hospital_info, '地址：', '电话：')
hospital_address = hospital_address.replace(
'查看地图', '') if hospital_address else None
hospital_phone = get_hospital_info(hospital_info, '电话：', '官网')
hospital_intro = get_hospital_info(hospital_info, '简介：', '$')
hospital_intro = hospital_intro.replace(
'...更多>>', '') if hospital_intro else None
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name', '//span[@class="title"]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_level', '//span[@class="dj"]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_category', hospital_category)
loader.add_value('hospital_addr', hospital_address,
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', '山西省')
loader.add_xpath(
'hospital_city',
'//td[contains(text(),"山西")]/ancestor::tr[1]/td[1]/a[1]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath(
'hospital_county',
'//td[contains(text(),"山西")]/ancestor::tr[1]/td[1]/a[2]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_phone', hospital_phone,
MapCompose(custom_remove_tags))
loader.add_value('hospital_intro', hospital_intro,
MapCompose(custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('update_time', now_day())
hospital_info_item = loader.load_item()
yield hospital_info_item
# 获取科室信息
self.logger.info('>>>>>>正在抓取科室详细信息>>>>>>')
all_dept_links = response.xpath('//tr[@class="h_bottom"]')
for each_dept_link in all_dept_links:
dept_type = each_dept_link.xpath('td[1]/text()').extract_first(
'')
dept_name = each_dept_link.xpath(
'td[2]/table/tr/td/a/text()').extract()
for each_dept_name in dept_name:
dept_loader = CommonLoader2(item=HospitalDepItem(),
response=response)
dept_loader.add_value(
'dept_name', each_dept_name,
MapCompose(custom_remove_tags, match_special2))
dept_loader.add_value(
'dept_type', dept_type,
MapCompose(custom_remove_tags, match_special2))
dept_loader.add_xpath('hospital_name',
'//span[@class="title"]/text()',
MapCompose(custom_remove_tags))
dept_loader.add_value('dept_info', '')
dept_loader.add_value('dataSource_from',
self.data_source_from)
dept_loader.add_value('update_time', now_day())
dept_item = dept_loader.load_item()
yield dept_item
except Exception as e:
self.logger.error('在抓取医院详细信息和科室的过程中出错了,原因是：{}'.format(repr(e)))
def parse_hospital_info(self, response):
hospital_name = response.meta.get('hospital_name')
self.logger.info('>>>>>>正在抓取[{}]医院详细信息>>>>>>'.format(hospital_name))
try:
hospital_id = response.meta.get('hospital_id')
data_type = response.meta.get('data_type')
hospital_pro = response.meta.get('province_name')
if data_type == '1':
hospital_address = response.xpath('///div[@class="search-result-hospital-text"]/'
'p[4]/text()').extract_first('')
hospital_phone = response.xpath('//div[@class="search-result-hospital-text"]/'
'p[3]/text()').extract_first('')
check_phone = re.search('(\d{6,})', hospital_phone)
if not check_phone and not hospital_address:
hospital_address = hospital_phone
hospital_phone = ''
# hospital_city = get_city('', hospital_address)
# hospital_county = get_county2('', match_special2(hospital_address))
df = transform([hospital_address])
# hospital_pro = df.head()['省'][0]
hospital_city = df.head()['市'][0]
hospital_county = df.head()['区'][0]
if hospital_pro in MUNICIPALITY2:
hospital_city = '{0}{1}'.format(hospital_pro, '市')
hospital_pro = ''
else:
hospital_pro = '{0}{1}'.format(hospital_pro, '省')
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name',
'//span[@class="search-result-hospital-name"]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_level',
'//div[@class="search-result-hospital-text"]/p[2]/text()',
MapCompose(custom_remove_tags, clean_info2))
loader.add_value('hospital_addr', hospital_address, MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', hospital_pro)
loader.add_value('hospital_city', hospital_city)
loader.add_value('hospital_county', hospital_county, MapCompose(custom_remove_tags))
loader.add_value('hospital_phone', hospital_phone, MapCompose(custom_remove_tags))
loader.add_xpath('hospital_intro',
'//li[@id="info"]/p',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('crawled_url', response.url)
loader.add_value('update_time', now_day())
loader.add_xpath('hospital_route',
'//div[@class="search-result-hospital-text"]/p[5]/text()',
MapCompose(custom_remove_tags, match_special2))
loader.add_xpath('hospital_img_url', 'div[@class="search-result-hospital-img"]/img/@src')
loader.add_value('hospital_tags', '1')
loader.add_value('gmt_created', now_time())
loader.add_value('gmt_modified', now_time())
loader.add_value('hospital_id', hospital_id)
hospital_item = loader.load_item()
yield hospital_item
# 获取科室信息
# 从一级科室获取二级科室信息
all_dept = response.xpath('//ul[@id="parent-list"]/li[@id]')
for each_dept in all_dept:
each_dept_id = each_dept.xpath('@id').extract_first('')
each_dept_type = each_dept.xpath('div/span/text()').extract_first('')
self.headers['Referer'] = response.url
dept_link = self.dept_url.format(hospital_id, each_dept_id)
yield Request(dept_link,
headers=self.headers,
callback=self.parse_hospital_dep,
meta={
'hospital_name': hospital_name,
'hospital_id': hospital_id,
'dept_type': each_dept_type
})
# 获取医生信息
self.headers['Referer'] = response.url
doctor_info_link = self.doctor_url.format(hospital_id, '1')
yield Request(doctor_info_link,
headers=self.headers,
callback=self.parse_doctor_info,
meta={
'hospital_name': hospital_name,
'hospital_id': hospital_id
})
elif data_type == '2':
hospital_address = response.xpath('//p[@class="hospital-private-address-line fc-6"]'
'[contains(text(),"地址")]/text()').extract_first('')
# hospital_city = get_city('', hospital_address)
# hospital_county = get_county2('', match_special2(hospital_address))
df = transform([hospital_address])
# hospital_pro = df.head()['省'][0]
hospital_city = df.head()['市'][0]
hospital_county = df.head()['区'][0]
if hospital_pro in MUNICIPALITY2:
hospital_city = '{0}{1}'.format(hospital_pro, '市')
hospital_pro = ''
else:
hospital_pro = '{0}{1}'.format(hospital_pro, '省')
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name',
'//p[@class="hospital-private-content-tit"]/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_addr', hospital_address, MapCompose(custom_remove_tags, match_special2))
loader.add_value('hospital_pro', hospital_pro)
loader.add_value('hospital_city', hospital_city)
loader.add_value('hospital_county', hospital_county, MapCompose(custom_remove_tags))
loader.add_xpath('hospital_phone',
'//div[@class="search-result-hospital-text"]/p[3]/text()',
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_intro',
'//li[@id="info"]/p',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('crawled_url', response.url)
loader.add_value('update_time', now_day())
loader.add_xpath('hospital_route',
'//li[@id="address"]/p[3]/text()',
MapCompose(custom_remove_tags, match_special2))
# loader.add_xpath('hospital_img_url', 'div[@class="search-result-hospital-img"]/img/@src')
loader.add_value('hospital_tags', '2')
loader.add_value('gmt_created', now_time())
loader.add_value('gmt_modified', now_time())
loader.add_value('hospital_id', hospital_id)
hospital_item = loader.load_item()
yield hospital_item
# 获取科室信息
# 从一级科室获取二级科室信息
all_dept = response.xpath('//ul[@id="parent-list"]/li[position()>1]')
for each_dept in all_dept:
dept_id = each_dept.xpath('div/@id').extract_first('')
dept_name = each_dept.xpath('div/span/text()').extract_first('')
dept_loader = CommonLoader2(item=HospitalDepItem(), response=response)
dept_loader.add_value('dept_name', dept_name, MapCompose(custom_remove_tags))
dept_loader.add_value('hospital_name', hospital_name, MapCompose(custom_remove_tags))
dept_loader.add_value('dataSource_from', self.data_source_from)
dept_loader.add_value('crawled_url', response.url)
dept_loader.add_value('update_time', now_day())
dept_loader.add_value('dept_id', dept_id.replace('subDepLi-', ''))
dept_loader.add_value('dept_url', response.url)
dept_loader.add_value('gmt_created', now_time())
dept_loader.add_value('gmt_modified', now_time())
dept_item = dept_loader.load_item()
yield dept_item
# 获取医生信息
self.headers['Referer'] = response.url
doctor_info_link = self.doctor_url.format(hospital_id, '1')
yield Request(doctor_info_link,
headers=self.headers,
callback=self.parse_doctor_info,
meta={
'hospital_name': hospital_name,
'hospital_id': hospital_id,
'dept_name': dept_name
})
except Exception as e:
self.logger.error('在抓取医院详细信息过程中出错了,原因是：{}'.format(repr(e)))
def parse_hospital_info(self, response):
hospital_name = response.meta.get('hospital_name')
self.logger.info('>>>>>>正在抓取:[{}]医院详细信息>>>>>>'.format(hospital_name))
try:
# 获取医院等级与类别
l_a_c = response.xpath(
'//div[@class="l"]/h2/span/i/text()').extract()
l_a_c = custom_remove_tags(remove_tags('|'.join(l_a_c)))
h_l = h_c = m_t = None
if l_a_c:
# 等级
level = re.search(r'(.*等|.*级|.*甲)', l_a_c)
if level:
h_l = level.group(1).split('|')[-1]
# 类别
category = re.search(r'(.*?医院)', l_a_c.replace('医保定点医院', ''))
if category:
h_c = category.group(1).split('|')[-1]
# 医保类型
medical_type = re.search(r'(.*定点)', l_a_c)
if medical_type:
m_t = medical_type.group(1).split('|')[-1]
else:
h_l = h_c = None
# 获取省市信息
hospital_pro = response.meta.get('hospital_pro')
hospital_city = hospital_county = None
h_a = response.xpath(
'//dt[contains(text(),"地址")]/ancestor::dl[1]/dd').extract()
hospital_address = custom_remove_tags(
remove_tags(''.join(h_a).replace('查看地图', '')))
if hospital_pro and hospital_address:
if hospital_pro in MUNICIPALITY2:
hospital_city = hospital_pro
hospital_pro = ''
hos_c = hospital_city.replace('市', '')
useless_info = '{}{}|{}'.format(hos_c, '市', hos_c)
single_address = match_special2(
hospital_address.split(';')[0])
hospital_county = get_county2(useless_info, single_address)
else:
hos_p = hospital_pro
hospital_pro = '{0}{1}'.format(hospital_pro, '省')
single_address = match_special2(
hospital_address.split(';')[0])
hospital_city = get_city(hospital_pro, single_address)
if hospital_city:
hos_c = hospital_city.replace('市', '')
useless_info = '{}|{}|{}|{}'.format(
hospital_pro, hos_p, hospital_city, hos_c)
hospital_county = get_county2(useless_info,
single_address)
# 公立/私立
h_t = custom_remove_tags(
response.xpath(
'//li/b[contains(text(),"国营")]/text()').extract_first(''))
hospital_type = '公立' if h_t == '国营' else ''
# 医院信息item
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath('hospital_name', '//div[@class="l"]/h2/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_level', h_l,
MapCompose(custom_remove_tags))
loader.add_value('hospital_type', hospital_type)
loader.add_value('hospital_category', h_c,
MapCompose(custom_remove_tags))
loader.add_value('hospital_addr', hospital_address,
MapCompose(custom_remove_tags))
loader.add_value('hospital_pro', hospital_pro,
MapCompose(custom_remove_tags))
loader.add_value('hospital_city', hospital_city,
MapCompose(custom_remove_tags))
loader.add_value('hospital_county', hospital_county,
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_phone',
'//dt[contains(text(),"电话")]/ancestor::dl[1]/dd',
MapCompose(remove_tags, custom_remove_tags))
loader.add_xpath(
'hospital_intro',
'//dt/strong[contains(text(),"简介")]/ancestor::dl[1]/dd',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('medicare_type', m_t,
MapCompose(custom_remove_tags))
# loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('hospital_url', response.url)
loader.add_value('update_time', now_day())
hospital_item = loader.load_item()
yield hospital_item
# 获取医院别名
hospital_alias = response.xpath(
'//div[@class="l"]/p/text()').extract_first('')
if hospital_alias:
h_s = custom_remove_tags(hospital_alias)
if h_s:
all_hospital_alias = h_s.split('，')
for each_alias in all_hospital_alias:
if each_alias != hospital_name:
alias_loader = CommonLoader2(
item=HospitalAliasItem(), response=response)
alias_loader.add_xpath(
'hospital_name', '//div[@class="l"]/h2/text()',
MapCompose(custom_remove_tags))
alias_loader.add_value(
'hospital_alias_name', each_alias,
MapCompose(custom_remove_tags, match_special))
alias_loader.add_value('dataSource_from',
self.data_source_from)
alias_loader.add_value('update_time', now_day())
alias_item = alias_loader.load_item()
yield alias_item
except Exception as e:
self.logger.error('在抓取医院详细信息过程中出错了,原因是：{}'.format(repr(e)))
def parse_doctor_website(self, response):
self.logger.info('>>>>>>正在抓取医生个人主页相关信息……')
# 获取医生相关信息
loader = YiHuLoader(item=DoctorInfoItem(), response=response)
loader.add_xpath('doctor_name', '//span[@class="c-f22 c-333"]/text()')
loader.add_xpath('dept_name',
'//div[@class="doctor-info"]/dl/dd[2]/a[2]/text()')
loader.add_xpath('hospital_name',
'//div[@class="doctor-info"]/dl/dd[2]/a[1]/text()')
loader.add_xpath('doctor_level',
'//div[@class="doctor-info"]/dl/dd[1]/text()')
loader.add_xpath(
'doctor_intro',
'//table[@class="pop-myinfo-tb"]/tr[@class="last"]/td/p/text()')
loader.add_xpath('doctor_goodAt',
'//table[@class="pop-myinfo-tb"]/tr[5]/td/text()')
loader.add_value('update_time', now_day())
doctor_item = loader.load_item()
yield doctor_item
# 获取医院相关信息
hos_link = response.xpath(
'//div[@class="doctor-info"]/dl/dd[2]/a[1]/@href').extract_first(
'')
dept_link = response.xpath(
'//div[@class="doctor-info"]/dl/dd[2]/a[2]/@href').extract_first(
'')
# 抓取医院详细信息
if hos_link:
hos_id = re.search(r'/sc/(.*?).shtml', hos_link)
if hos_id and hos_id.group(1) not in self.crawled_ids:
self.crawled_ids.add(hos_id.group(1))
hos_intro_link = re.sub(r'/sc/', '/detail/', hos_link)
hos_con_link = re.sub(r'/sc/', '/contact/', hos_link)
hos_loader = YiHuLoader(item=HospitalInfoItem(),
response=response)
hos_loader.add_xpath(
'hospital_name',
'//div[@class="doctor-info"]/dl/dd[2]/a[1]/text()')
hospital_detail_request = Request(
hos_intro_link,
headers=self.headers,
callback=self.parse_hospital_detail,
meta={
'loader': hos_loader,
'contact_hos_link': hos_con_link
})
hospital_detail_request.meta['Referer'] = response.url
yield hospital_detail_request
# 存储科室信息
if dept_link:
dept_link_id = re.search(r'/arrange/(.*?).shtml', dept_link)
if dept_link_id and dept_link_id.group(1) not in self.crawled_dept:
self.crawled_dept.add(dept_link_id.group(1))
dept_loader = YiHuLoader(item=HospitalDepItem(),
response=response)
dept_loader.add_xpath(
'dept_name',
'//div[@class="doctor-info"]/dl/dd[2]/a[2]/text()')
dept_loader.add_xpath(
'hospital_name',
'//div[@class="doctor-info"]/dl/dd[2]/a[1]/text()')
dept_loader.add_value('update_time', now_day())
dept_item = dept_loader.load_item()
yield dept_item
def parse_hospital_info(self, response):
hospital_name = response.meta.get('hospital_name')
self.logger.info('>>>>>>正在抓取医院详细信息>>>>>>')
try:
hospital_id = response.meta.get('hospital_id')
hospital_img_url = response.xpath(
'//div[@class="divLeft_Img"]/img/@src').extract_first('')
hospital_img_url = urljoin(
self.host, hospital_img_url) if hospital_img_url else ''
hospital_address = response.xpath(
'//li[contains(text(),"地址")]/text()').extract_first('')
hospital_county = get_county2('中国|福建省|福建|厦门市|厦门',
match_special2(hospital_address))
loader = CommonLoader2(item=HospitalInfoItem(), response=response)
loader.add_xpath(
'hospital_name',
'//div[@class="divLeft_Info"]/ul/li[1]/span/text()',
MapCompose(custom_remove_tags))
loader.add_value('hospital_addr', hospital_address,
MapCompose(custom_remove_tags, match_special2))
loader.add_value('hospital_pro', '福建省')
loader.add_value('hospital_city', '厦门市')
loader.add_value('hospital_county', hospital_county,
MapCompose(custom_remove_tags))
loader.add_xpath('hospital_phone',
'//li[contains(text(),"电话")]/text()',
MapCompose(custom_remove_tags, match_special2))
loader.add_xpath('hospital_intro', '//div[@class="introduceSpan"]',
MapCompose(remove_tags, custom_remove_tags))
loader.add_value('registered_channel', self.data_source_from)
loader.add_value('dataSource_from', self.data_source_from)
loader.add_value('crawled_url', response.url)
loader.add_value('update_time', now_day())
loader.add_xpath('hospital_official_website',
'//li[contains(text(),"官网")]/text()',
MapCompose(custom_remove_tags, match_special2))
loader.add_xpath('hospital_route',
'//li[contains(text(),"公交线路")]/text()',
MapCompose(custom_remove_tags, match_special2))
loader.add_value('hospital_img_url', hospital_img_url)
loader.add_value('gmt_created', now_time())
loader.add_value('gmt_modified', now_time())
loader.add_value('hospital_id', hospital_id)
hospital_item = loader.load_item()
yield hospital_item
# 科室信息
all_dept_info = response.xpath(
'//div[@class="medicineOne"]|//div[@class="medicineTwo"]')
for each_dept_info in all_dept_info:
dept_type = each_dept_info.xpath(
'div[1]/span/text()').extract_first('')
dept_names = each_dept_info.xpath('div[2]/div[1]')
for each_dept_name in dept_names:
dept_name = each_dept_name.xpath('a/text()').extract_first(
'')
dept_link = each_dept_name.xpath('a/@href').extract_first(
'')
doctor_num_of_dept = each_dept_name.xpath(
'span/text()').extract_first('')
# 获取科室人数
if doctor_num_of_dept:
dept_person_num = re.search(r'(\d+)',
doctor_num_of_dept)
dept_person_num = int(dept_person_num.group(
1)) if dept_person_num else None
else:
dept_person_num = None
# 获取科室详细信息
dept_loader = CommonLoader2(item=HospitalDepItem(),
response=response)
dept_loader.add_value('dept_name', dept_name,
MapCompose(custom_remove_tags))
dept_loader.add_value('hospital_name', hospital_name,
MapCompose(custom_remove_tags))
dept_loader.add_value('dept_type', dept_type,
MapCompose(custom_remove_tags))
dept_loader.add_value('dataSource_from',
self.data_source_from)
dept_info = ''.join(
response.xpath(
'//p[contains(text(),"科室简介")]/ancestor::tr[1]').
extract())
dept_loader.add_value(
'dept_info', dept_info,
MapCompose(remove_tags, custom_remove_tags,
match_special2))
dept_loader.add_value('crawled_url', response.url)
dept_loader.add_value('update_time', now_day())
dept_loader.add_value('dept_id', dept_link,
MapCompose(match_special2))
dept_loader.add_value('hospital_id', hospital_id)
dept_loader.add_value('dept_person_num', dept_person_num)
dept_loader.add_value('dept_url',
urljoin(self.host, dept_link))
dept_loader.add_value('gmt_created', now_time())
dept_loader.add_value('gmt_modified', now_time())
dept_item = dept_loader.load_item()
yield dept_item
# 获取医生信息
if dept_link and dept_person_num:
self.headers['Referer'] = response.url
yield Request(urljoin(self.host, dept_link),
headers=self.headers,
callback=self.parse_doctor_info,
dont_filter=True,
meta={
'hospital_name': hospital_name,
'dept_name': dept_name,
})
except Exception as e:
self.logger.error('在抓取医院详细信息过程中出错了,原因是：{}'.format(repr(e)))
