初识Scrapy

 1 Scrapy
 2     # 创建project
 3     scrapy startproject wyb
 4     wyb
 5         wyb/
 6             spiders           # 爬虫文件
 7                 chouti.py
 8             items.py          # 持久化
 9             middlewares.py    # 中间件
10             pipelines.py      # 持久化
11             settings.py       # 项目配置文件
12         scrapy.cfg            # 配置文件（部署）
13       
14       
15     cd wyb
16     # 创建爬虫
17     scrapy genspider chouti chouti.com
18     
19     # 启动爬虫
20     scrapy crawl chouti
21     scrapy crawl chouti --nolog  # 不打印日志

 1 # -*- coding: utf-8 -*-
 2 import sys
 3 import os
 4 import io
 5 import scrapy
 6 
 7 # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding=‘gb18030‘) 编码问题
 8 
 9 
10 class ChoutiSpider(scrapy.Spider):
11     name = ‘chouti‘
12     # 爬取定向的网页 只允许这个域名的
13     allowed_domains = [‘chouti.com‘]
14     start_urls = [‘http://chouti.com/‘]
15 
16     def parse(self, response):
17         from scrapy.http.response.html import HtmlResponse
18         # print(response, type(response))
19         # print(response.text)
20         f = open(‘new.log‘, ‘a+‘)
21         item_list = response.xpath(‘//div[@id="content-list"]/div[@class="item"]‘)
22         for item in item_list:
23             text = item.xpath(‘.//a/text()‘).extract_first()
24             href = item.xpath(‘.//a/@href‘).extract_first()
25             print(href, text.strip())
26             f.write(href+‘\n‘)
27         f.close()
28 
29         page_list = response.xpath(‘//div[@id="dig_lcpage"]//a/@href‘).extract()
30         for page in page_list:
31             from scrapy.http import Request
32             page = "https://dig.chouti.com"+page
33             # 继续发请求，回调函数parse
34             yield Request(url=page, callback=self.parse)