def parse_item(self, response):
item = PythonJobItem()
q = response.xpath
#body = response.body.decode("utf-8")
item['address'] = response.meta['city']
item['salary'] = response.meta['salary']
item['create_time'] = response.meta['createTime']
item['body'] = q('//div[@class="content"]/p/text()').extract()
item['company_name'] = response.meta['companyName']
item['position_id'] = response.meta['positionId']
item['position_name'] = response.meta['positionName']
def parse_detail(self, response):
item = PythonJobItem()
print("response.url==", response.url)
title = response.xpath('//div[@class="cn"]/h1/text()').extract()
title = "".join(title)
location = response.xpath('//div[@class="cn"]/span/text()').extract()
location = "".join(location)
salary = response.xpath('//div[@class="cn"]/strong/text()').extract()
salary = "".join(salary)
company_name = response.xpath(
'//div[@class="cn"]/p/a/text()').extract()
company_name = "".join(company_name)
company_info = response.xpath(
'//div[@class="cn"]/p[@class="msg ltype"]/text()').extract()
company_info = "".join(company_info)
experience = response.xpath(
'//div[@class="t1"]/span[1]/text()').extract()
experience = "".join(experience)
job_info = response.xpath(
'//div[@class="bmsg job_msg inbox"]/p/text()|//div[@class="bmsg job_msg inbox"]/text()|//div[@class="bmsg job_msg inbox"]//p//span/text()'
).extract()
job_info = "".join(job_info)
address = response.xpath(
'//div[@class="bmsg inbox"]/p/text()').extract()
address = "".join(address)
item["url"] = response.url
item["title"] = title
item["location"] = location
item["salary"] = salary
item["company_name"] = company_name
item["company_info"] = company_info
item["experience"] = experience
item["job_info"] = job_info
item["address"] = address
# print(item)
yield item
def parse_item(self, response):
item = PythonJobItem()
q = response.xpath
item['address'] = q('//div[@class="jt"]/em/text()').extract_first('北京')
item['salary'] = q('//p[@class="jp"]/text()').extract_first('面议')
item['create_time'] = q(
'//div[@class="jt"]/span//text()').extract_first()
item['postion_id'] = response.url.split("/")[-1].split('.')[0]
item['position_name'] = q(
'//div[@class="jt"]/p/text()').extract_first()
item['work_year'] = q('//span[@class="s_n"]/text()').extract_first(
'不限')
item['company_name'] = q('//p[@class="c_444"]/text()').extract_first()
item['educational'] = q('//span[@class="s_x"]//text()').extract_first(
'不限')
item['body'] = q('//div[@class="ain"]/article//text()').extract()
yield item
def parse_item(self, response):
item = PythonJobItem()
q = response.xpath
item['address'] = q(
'/html/body/div[1]/div[2]/div[1]/div/div/div[2]/p/text()'
).extract_first()
item['work_year'] = q(
'/html/body/div[1]/div[2]/div[1]/div/div/div[2]/p/text()').extract(
)[1]
item['educational'] = q(
'/html/body/div[1]/div[2]/div[1]/div/div/div[2]/p/text()').extract(
)[2]
item['salary'] = q('//span[@class="salary"]/text()').extract_first()
item['company_name'] = q(
'/html/body/div[1]/div[2]/div[2]/div/div[2]/div[3]/text()'
).extract_first()
item['postion_id'] = response.url.split("/")[-1].split('.')[0]
item['position_name'] = q(
'//*[@id="main"]/div[2]/div/div[2]/div[1]/h1/text()'
).extract_first()
item['body'] = q(
'//div[1]/div[2]/div[3]/div/div[2]/div[2]/div[1]/div/text()'
).extract()
yield item