8_2 scrapy入门实战之CrawlSpider（微信小程序社区教程爬取示例）

CrawlSpider可用于有规则的网站，对其整站的爬取

一、创建项目

scrapy startproject wxapp

cd wxapp

scrapy genspider -t crawl wxapp_spider wxapp-union.com

二、更改setting.py

ROBOTSTXT_OBEY = False

DOWNLOAD_DELAY = 3

DEFAULT_REQUEST_HEADERS = {...}

三、wxapp_spider.py编写（重点）

　　代码编写

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule 6 
class WxappSpiderSpider(CrawlSpider):
    name = 'wxapp_spider'
    allowed_domains = ['wxapp-union.com']
    #start_urls = ['http://wxapp-union.com/']
    start_urls = ['http://www.wxapp-union.com/portal.php?mod=list&catid=2&page=1']

    rules = (
14         # 注意特殊字符加
15         Rule(LinkExtractor(allow=r'.+list&catid=2&page=d'), follow=True),
16         Rule(LinkExtractor(allow=r'.+article.+.html'), callback='parse_detail', follow=False)
    )

    def parse_detail(self, response):
　　　　　　print(type(response))

　　附：注意问题：

　　　　1、parse_detail(self, response):是用在Rule中的回调函数，若是要对其进行调试，则start_url和allowed_domains域名要一致。不一致的话是程序无法进入parse_detail(self, response):，因为会自动过滤。

　　　　2、需要使用LinkExtractor和Rule，这两个决定爬虫的爬取方法；

　　　　　　2.1　　allow设置规则的方法：限制在程序需要爬取的url，同时注意re特殊字符的转义

　　　　　　2.2　　什么情况下使用follow：如果在爬取页面的时候，需要将满足当前条件的url再进行跟进，那么设置为Ture，否则设置False　　　

　　 　　　　2.3　　什么情况下使用callback：如果想要获取url对应页面中的数据，那么就需要指定爬取函数为callback 。如果获取页面只是为了获取更多的url，不要需要其数据，则无需指定callback

四、对页面进行爬取

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule

class WxappSpiderSpider(CrawlSpider):
    name = 'wxapp_spider'
    allowed_domains = ['wxapp-union.com']
    #start_urls = ['http://wxapp-union.com/']
    start_urls = ['http://www.wxapp-union.com/portal.php?mod=list&catid=2&page=1']

    rules = (
        # 注意特殊字符加
        Rule(LinkExtractor(allow=r'.+list&catid=2&page=d'), follow=True),
        Rule(LinkExtractor(allow=r'.+article.+.html'), callback='parse_detail', follow=False)
    )

    def parse_detail(self, response):
        title = response.xpath("//h1[@class='ph']/text()").get()
20         author_p = response.xpath("//p[@class='authors']")
21         author = author_p.xpath(".//a/text()").get()
22         pub_time = author_p.xpath(".//span/text()").get()
23         content = response.xpath("//td[@id='article_content']//text()").getall()
24         content = "".join(content).strip()

五、数据存储

　　1、items.py

import scrapy


class WxappItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    title = scrapy.Field()
 8     author = scrapy.Field()
 9     pub_time = scrapy.Field()
10     content = scrapy.Field()

　　2、pipelines.py

 1 from scrapy.exporters import JsonLinesItemExporter

class WxappPipeline:
    def __init__(self):
 5         self.fp = open('wxjc.json', 'wb')
 6         self.exporter = JsonLinesItemExporter(self.fp,
 7                                               ensure_ascii=False,
 8                                               encoding='utf-8')

    def process_item(self, item, spider):
        self.exporter.export_item(item)
12         return item

    def close_spider(self,spider):
15         self.fp.close()

　　3、wxapp_spider.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from wxapp.items import WxappItem

class WxappSpiderSpider(CrawlSpider):
    name = 'wxapp_spider'
    allowed_domains = ['wxapp-union.com']
    #start_urls = ['http://wxapp-union.com/']
    start_urls = ['http://www.wxapp-union.com/portal.php?mod=list&catid=2&page=1']

    rules = (
        # 注意特殊字符加
        Rule(LinkExtractor(allow=r'.+list&catid=2&page=d'), follow=True),
        Rule(LinkExtractor(allow=r'.+article.+.html'), callback='parse_detail', follow=False)
    )

    def parse_detail(self, response):
        title = response.xpath("//h1[@class='ph']/text()").get()
        author_p = response.xpath("//p[@class='authors']")
        author = author_p.xpath(".//a/text()").get()
        pub_time = author_p.xpath(".//span/text()").get()
        content = response.xpath("//td[@id='article_content']//text()").getall()
        content = "".join(content).strip()

        # 数据存储
28         item = WxappItem(title=title, author=author,pub_time=pub_time, content=content)
29         yield item

　　4、更改setting.py

ITEM_PIPELINES = {
   'wxapp.pipelines.WxappPipeline': 300,
}