1 # coding:utf-8
 2 import scrapy
 3 import re
 4 import os
 5 import sqlite3
 6 from myspider.items import SpiderItem
 7 
 8 
 9 class ZolSpider(scrapy.Spider):
10     name = "zol"
11     # allowed_domains = ["http://detail.zol.com.cn/"]  # 用于限定爬取的服务器域名
12     start_urls = [
13         # 主要爬去中关村在线的手机信息页面，考虑到是演示目的就仅仅爬了首页，其实爬分页跟二级爬虫原理相同，出于节省时间目的就没爬
14         # 这里可以写个入口URL
15         "http://detail.zol.com.cn/cell_phone_index/subcate57_list_1.html"
16     ]
17     item = SpiderItem()  # 没法动态创建，索性没用上用的meta在spider函数间传值
18     # 只是test一下就用sqlite吧，比较轻量
19     #database = sqlite3.connect(":memory:")
20     database_file = os.path.dirname(os.path.abspath(__file__)) + "\\phonedata.db"
21     if os.path.exists(database_file):
22         os.remove(database_file)
23     database = sqlite3.connect(database_file)
24     # 先建个字段，方便理解字段含义就用中文了
25     database.execute(
26         ‘‘‘
27         CREATE TABLE CELL_PHONES
28         (
29         手机型号 TEXT
30         );
31         ‘‘‘
32     )
33     # 用于检查数据增改是否全面，与total_changes对比
34     counter = 0
35 
36     # 手机报价首页爬取函数
37     def parse(self, response):
38         # 获取手机详情页链接并以其创建二级爬虫
39         hrefs = response.xpath("//h3/a")
40         for href in hrefs:
41             url = response.urljoin(href.xpath("@href")[0].extract())
42             yield scrapy.Request(url, self.parse_detail_page)
43 
44     # 手机详情页爬取函数
45     def parse_detail_page(self, response):
46         # 通过xpath获取手机型号
47         model = response.xpath("//h1").xpath("text()")[0].extract()
48         # 创建该型号手机的数据库记录
49         sql = ‘INSERT INTO CELL_PHONES (手机型号) VALUES ("‘ + model + ‘")‘
50         self.counter += 1
51         self.database.execute(sql)
52         self.database.commit()
53         # 获取参数详情页的链接
54         url = response.urljoin(response.xpath("//div[@id=‘tagNav‘]//a[text()=‘参数‘]").xpath("@href")[0].extract())
55         # 由于Scrapy是异步驱动的（逐级启动爬虫函数），所以当需绑定父子级爬虫函数间的某些变量时，可以采用meta字典传递，全局的item字段无法动弹创建，在较灵活的爬取场景中不是很适用
56         yield scrapy.Request(url, callback=self.parse_param_page, meta={‘model‘: model})
57 
58     # 手机参数详情页爬取函数
59     def parse_param_page(self, response):
60         # 获取手机参数字段并一一遍历
61         params = response.xpath("//span[contains(@class,‘param-name‘)]")
62         for param in params:
63             legal_param_name_field = param_name = param.xpath("text()")[0].extract()
64             # 将手机参数字段转变为合法的数据库字段（非数字开头，且防止SQL逻辑污染剔除了‘/‘符号）
65             if re.match(r‘^\d‘, param_name):
66                 legal_param_name_field = re.sub(r‘^\d‘, "f" + param_name[0], param_name)
67             if ‘/‘ in param_name:
68                 legal_param_name_field = legal_param_name_field.replace(‘/‘, ‘‘)
69             # 通过查询master表检查动态添加的字段是否已经存在，若不存在则增加该字段
70             sql = "SELECT * FROM sqlite_master WHERE name=‘CELL_PHONES‘ AND SQL LIKE ‘%" + legal_param_name_field + "%‘"
71             if self.database.execute(sql).fetchone() is None:
72                 sql = "ALTER TABLE CELL_PHONES ADD " + legal_param_name_field + " TEXT"
73                 self.database.execute(sql)
74                 self.database.commit()
75             # 根据参数字段名的xpath定位参数值元素
76             xpath = "//span[contains(@class,‘param-name‘) and text()=‘" + param_name +77                     "‘]/following-sibling::span[contains(@id,‘newPmVal‘)]//text()"
78             vals = response.xpath(xpath)
79             # 由于有些字段的参数值是多个值，所以需将其附加到一起，合成一个字段，以方便存储。
80             # 如需数据细分选用like子句或支持全文索引的数据库也不错，当然nosql更好
81             pm_val = ""
82             for val in vals:
83                 pm_val += val.extract()
84             re.sub(r‘\r|\n‘,"",pm_val)
85             sql = "UPDATE CELL_PHONES SET %s = ‘%s‘ WHERE 手机型号 = ‘%s‘" 86                   % (legal_param_name_field, pm_val, response.meta[‘model‘])
87             self.database.execute(sql)
88             self.counter += 1
89             # 检查下爬取的数据对不对
90         results = self.database.execute("SELECT * FROM CELL_PHONES").fetchall()
91         # 千万别忘了commit否则持久化数据库可能结果不全
92         self.database.commit()
93         print(self.database.total_changes, self.counter) # 对比下数据库的增改情况是否有丢失
94         for row in results:
95             print(row, end=‘\n‘)  # 其实这里有个小小的编码问题需要解决
96         # 最后愉快的用scrapy crawl zol 启动爬虫吧！