Блог

Это мой код:

 from scrapy.spider import Spider
from scrapy.selector import Selector
from thuctapsinhvietnam.items import ThuctapsinhvietnamItem


class ThuctapsinhvietnamSpider(Spider):
    name = "thuctapsinhvietnam"
    allowed_domains ["thuctapsinhvietnam.com"]
    start_urls = [
        "http://www.thuctapsinhvietnam.com/thuctap-phuong-vinh-hao-3970.html"
        ]

    def parse(self, response):
        def parse(self, response):
        cases = Selector(response).xpath('//div[@id="areaThongTinCaNhan"]/table/tbody/tr[2]/td/table/tbody/tr/td/table/tbody/tr')

        for case in cases:
            item = ThuctapsinhvietnamItem()
            item['Name'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['Phone'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['Email'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['Dob'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['Sex'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['School'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['Introduction'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            item['Place'] = question.xpath(
                '//td[3][@class="thongtin"]/text()')extract()[0]
            yield item
  

У меня проблема при попытке scrapy в ubuntu, я использую xpath для получения данных.
Я пытаюсь получить информацию с этого веб-сайта, но здесь есть ошибка:

 File "thuctapsinhvietnam_spider.py", line 15
cases = Selector(response).xpath('//div[@id="areaThongTinCaNhan"]/table/tbody/tr[2]/td/table/tbody/tr/td/table/tbody/tr') 
     ^
IndentationError: expected an indented block
  

У вас есть два из них:

 def parse(self, response):
     def parse(self, response):