python框架Scrapy中crawlSpider的使用——爬取内容写进MySQL

一、先在MySQL中创建test数据库，和相应的site数据表

二、创建Scrapy工程

#scrapy startproject 工程名
scrapy startproject demo4

三、进入工程目录，根据爬虫模板生成爬虫文件

#scrapy genspider -l # 查看可用模板
#scrapy genspider -t 模板名 爬虫文件名 允许的域名
scrapy genspider -t crawl test sohu.com

四、设置IP池或用户代理（middlewares.py文件）

 1 # -*- coding: utf-8 -*-
 2 # 导入随机模块
 3 import random
 4 # 导入有关IP池有关的模块
 5 from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware
 6 # 导入有关用户代理有关的模块
 7 from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware
 8
 9 # IP池
10 class HTTPPROXY(HttpProxyMiddleware):
11     # 初始化 注意一定是 ip=‘‘
12     def __init__(self, ip=‘‘):
13         self.ip = ip
14
15     def process_request(self, request, spider):
16         item = random.choice(IPPOOL)
17         try:
18             print("当前的IP是："+item["ipaddr"])
19             request.meta["proxy"] = "http://"+item["ipaddr"]
20         except Exception as e:
21             print(e)
22             pass
23
24
25 # 设置IP池
26 IPPOOL = [
27     {"ipaddr": "182.117.102.10:8118"},
28     {"ipaddr": "121.31.102.215:8123"},
29     {"ipaddr": "1222.94.128.49:8118"}
30 ]
31
32
33 # 用户代理
34 class USERAGENT(UserAgentMiddleware):
35     #初始化 注意一定是 user_agent=‘‘
36     def __init__(self, user_agent=‘‘):
37         self.user_agent = user_agent
38
39     def process_request(self, request, spider):
40         item = random.choice(UPPOOL)
41         try:
42             print("当前的User-Agent是："+item)
43             request.headers.setdefault(‘User-Agent‘, item)
44         except Exception as e:
45             print(e)
46             pass
47
48
49 # 设置用户代理池
50 UPPOOL = [
51     "Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Firefox/52.0", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.79 Safari/537.36 Edge/14.14393"
52 ]

五、settngs.py配置

 1 COOKIES_ENABLED = False
 2
 3 DOWNLOADER_MIDDLEWARES = {
 4     # ‘scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware‘:123,
 5     # ‘demo4.middlewares.HTTPPROXY‘ : 125,
 6     ‘scrapy.downloadermiddlewares.useragent.UserAgentMiddleware‘: 2,
 7     ‘demo4.middlewares.USERAGENT‘: 1
 8 }
 9
10 ITEM_PIPELINES = {
11     ‘demo4.pipelines.Demo4Pipeline‘: 300,
12 }

六、定义爬取关注的数据（items.py文件）

 1 # -*- coding: utf-8 -*-
 2 import scrapy
 3 # Define here the models for your scraped items
 4 #
 5 # See documentation in:
 6 # http://doc.scrapy.org/en/latest/topics/items.html
 7
 8 class Demo4Item(scrapy.Item):
 9     name = scrapy.Field()
10     link = scrapy.Field()

七、爬虫文件编写（test.py）

 1 # -*- coding: utf-8 -*-
 2 import scrapy
 3 from scrapy.linkextractors import LinkExtractor
 4 from scrapy.spiders import CrawlSpider, Rule
 5 from demo4.items import Demo4Item
 6
 7 class TestSpider(CrawlSpider):
 8     name = ‘test‘
 9     allowed_domains = [‘sohu.com‘]
10     start_urls = [‘http://www.sohu.com/‘]
11
12     rules = (
13         Rule(LinkExtractor(allow=(‘http://news.sohu.com‘), allow_domains=(‘sohu.com‘)), callback=‘parse_item‘,
14              follow=False),
15         # Rule(LinkExtractor(allow=(‘.*?/n.*?shtml‘),allow_domains=(‘sohu.com‘)), callback=‘parse_item‘, follow=False),
16     )
17
18     def parse_item(self, response):
19         i = Demo4Item()
20         i[‘name‘] = response.xpath(‘//div[@class="news"]/h1/a/text()‘).extract()
21         i[‘link‘] = response.xpath(‘//div[@class="news"]/h1/a/@href‘).extract()
22         #i[‘description‘] = response.xpath(‘//div[@id="description"]‘).extract()
23         return i

八、管道文件编写（pipelines.py）

 1 # -*- coding: utf-8 -*-
 2 import pymysql
 3 import json
 4 # Define your item pipelines here
 5 #
 6 # Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
 7 # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
 8
 9
10 class Demo4Pipeline(object):
11     def __init__(self):
12         # 数据库连接
13         self.conn = pymysql.connect(host=‘localhost‘, user=‘root‘, password=‘123456‘, database=‘chapter17‘, charset=‘utf8‘)
14         self.cur = self.conn.cursor()
15
16     def process_item(self, item, spider):
17         # 排除空值
18         for j in range(0, len(item["name"])):
19             nam = item["name"][j]
20             lin = item["link"][j]
21             print(type(nam))
22             print(type(lin))
23             # 注意参数化编写
24             sql = "insert into site(name,link) values(%s,%s)"
25             self.cur.execute(sql,(nam,lin))
26             self.conn.commit()
27         return item
28     def close_spider(self, spider):
29         self.cur.close()
30         self.conn.close()

九、总结

1.注意在测试完数据库正常运行时，再开始写入数据，当然，在sql参数化处理的过程中，注意格式，千万不要弄错了