1 # -*- coding: utf-8 -*-
  2 import scrapy
  3 import sys
  4 import os
  5 
  6 # noinspection PyUnresolvedReferences
  7 from sinainfo.items import SinainfoItem
  8 
  9 reload(sys)
 10 sys.setdefaultencoding(‘utf-8‘)
 11 
 12 
 13 class SinaSpider(scrapy.Spider):
 14     name = ‘sina‘
 15     allowed_domains = [‘sina.com.cn‘]
 16     start_urls = [‘http://news.sina.com.cn/guide/‘]
 17 
 18     def parse(self, response):
 19         items = []
 20         # 所有大类的标题和url
 21         parentTitle = response.xpath("//div[@id=‘tab01‘]/div/h3/a/text()").extract()
 22         parentUrls = response.xpath(‘//div[@id="tab01"]/div/h3/a/@href‘).extract()
 23 
 24         # 所有小类的ur 和 标题
 25         subUrls = response.xpath(‘//div[@id="tab01"]/div/ul/li/a/@href‘).extract()
 26         subTitle = response.xpath(‘//div[@id="tab01"]/div/ul/li/a/text()‘).extract()
 27 
 28         # 爬取所有大类
 29         for i in range(0, len(parentTitle)):
 30             # 指定大类目录的路径和目录名
 31             parentFilename = "./Data/" + parentTitle[i]
 32             # 如果目录不存在，则创建目录
 33             if (not os.path.exists(parentFilename)):
 34                 os.makedirs(parentFilename)
 35 
 36             # 爬取所有小类
 37             for j in range(0, len(subUrls)):
 38                 item = SinainfoItem()
 39                 # 保存大类的title和urls
 40                 item[‘parentTitle‘] = parentTitle[i]
 41                 item[‘parentUrls‘] = parentUrls[i]
 42                 # 检查小类的url是否以同类别大类url开头，如果是返回Ture
 43                 if_belong = subUrls[j].startswith(item[‘parentUrls‘])
 44                 # 如果属于本大类，将存储目录放在本大类下
 45                 if (if_belong):
 46                     subFilename = parentFilename + ‘/‘ + subTitle[j]
 47                     # 如果目录不存在，则创建目录
 48                     if (not os.path.exists(subFilename)):
 49                         os.makedirs(subFilename)
 50                     # 存储 小类url、title、和filename字段数据
 51                     item[‘subUrls‘] = subUrls[j]
 52                     item[‘subTitle‘] = subTitle[j]
 53                     item[‘subFilename‘] = subFilename
 54                     items.append(item)
 55 
 56         # 发送每个小类url的Request请求，得到Response连同包含meta数据
 57                     # 一同交给回调函数second_parse()处理
 58         for item in items:
 59             yield scrapy.Request(url = item[‘subUrls‘], 60                                  meta={‘meta_1‘:item}, callback=self.second_parse)
 61 
 62     # 对于返回的小类url，在进行递归请求
 63     def second_parse(self, response):
 64         # 提取每次Response的meta数据
 65         meta_1 = response.meta[‘meta_1‘]
 66         # 取出小类里所有字链接
 67         sonUrls = response.xpath(‘//a/@href‘).extract()
 68 
 69         items = []
 70         for i in range(0, len(sonUrls)):
 71             # 检查每个链接是否以大类url开头、以.shtml结尾，如果是返回True
 72             if_belong = sonUrls[i].endswith(‘.shtml‘) and sonUrls[i].startswith( 73                 meta_1[‘parentUrls‘])
 74             # 如果属于本大类，获取字段值放在同一个item下便于传输
 75             if (if_belong):
 76                 item = SinainfoItem()
 77                 item[‘parentTitle‘] = meta_1[‘parentTitle‘]
 78                 item[‘parentUrls‘] = meta_1[‘parentUrls‘]
 79                 item[‘subTitle‘] = meta_1[‘subTitle‘]
 80                 item[‘subUrls‘] = meta_1[‘subUrls‘]
 81                 item[‘subFilename‘] = meta_1[‘subFilename‘]
 82                 item[‘sonUrls‘] = sonUrls[i]
 83                 items.append(item)
 84 
 85         for item in items:
 86             yield scrapy.Request(url = item[‘sonUrls‘], 87                                  meta = {‘meta_2‘:item}, callback=self.detail_parse)
 88 
 89     # 数据解析方法，获取文章标题和内容
 90     def detail_parse(self, response):
 91         item = response.meta[‘meta_2‘]
 92         content = ""
 93         head = response.xpath(‘//h1[@id="main_title"]/text()‘)
 94         content_list = response.xpath(‘//div[@id="artibody"]/p/text()‘).extract()
 95         # 将p标签里的文本内容合并到一起
 96         for content_one in content_list:
 97             content += content_one
 98         item[‘head‘] = head
 99         item[‘content‘] = content