Scrapy框架
win安装
- twisted 依赖 ，安装不了，找whl文件
- pip3 install wheel
- pip3 install ****.whl
- pip3 install pywin32
Django:
django-admin startproject mysite
cd mysite
python manage.py startapp app01
Scrapy
# 创建项目
scrapy startproject sp1
sp1
- sp1
- spiders目录
- middlewares.py 中间件
- items.py 设置数据存储模板，用于数据格式化 如django的model
- pipelines.py 持久化
- settings.py 配置文件
- scrapy.cfg 项目的主配置信息，
# 创建爬虫
cd sp1
scrapy genspider example example.com
# 执行爬虫，进入project
scrapy crawl baidu
scrapy crawl baidu --nolog # 无日志
# 展示所有爬虫列表
scrapy list
Scrapy 使用了 Twisted异步网络库来处理网络通讯。整体架构大致如下
# 小试牛刀
import scrapy
from scrapy.selector import HtmlXPathSelector
from scrapy.http.request import Request
class DigSpider(scrapy.Spider):
def __init__():
声明浏览器对象
def closed(self,spider):
关闭浏览器对象
# 在中间件process_response方法中获取浏览器对象（spider.bro)
# 在中间件process_response方法中，获取页面源码数据bro.page_source
# 将源码数据赋值给HtmlResponse(url,body,request,encoding)的body参数
name = "dig" # 通过此名称启动爬虫命令
allowed_domains = ["chouti.com"]
start_urls = ['http://dig.chouti.com/', ]
has_request_set = {}
def parse(self, response):
hxs = HtmlXPathSelector(response) # HtmlXpathSelector用于结构化HTML代码并提供选择器功能
page_list = hxs.select('//div[@id="dig_lcpage"]//a[re:test(@href, "/all/hot/recent/\d+")]/@href').extract()
for page in page_list:
page_url = 'http://dig.chouti.com%s' % page
key = self.md5(page_url)
if key in self.has_request_set:
pass
else:
self.has_request_set[key] = page_url
obj = Request(url=page_url, method='GET', callback=self.parse)
yield obj
@staticmethod
def md5(val):
import hashlib
ha = hashlib.md5()
ha.update(bytes(val, encoding='utf-8'))
key = ha.hexdigest()
return key
HtmlXPathSelector提供了类似beautifulsoup解析html的功能
具体使用方法：
from scrapy.selector import Selector, HtmlXPathSelector
from scrapy.http import HtmlResponse
html = """<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<title></title>
</head>
<body>
<ul>
<li class="item-"><a id='i1' href="link.html">first item</a></li>
<li class="item-0"><a id='i2' href="link.html">first item</a></li>
<li class="item-1"><a href="link2.html">second item<span>vv</span></a></li>
</ul>
<div><a href="link1.html">second item</a></div>
</body>
</html>
"""
# //子子孙孙 /当前孩子
# 先对字符串进行封装，使其成为一个response对象
response = HtmlResponse(url='http://example.com', body=html, encoding='utf-8')
# Selector对象
# hxs = HtmlXPathSelector(response) 已被弃用
# hxs = Selector(response).xpath("//a") # 找到所有的a标签
# hxs = Selector(response).xpath("//a[@id]") # 找到所有有id属性的a标签
# hxs = Selector(response).xpath("//a[@id='i1']") # 找到所有有id属性且是i1的a标签
# hxs = Selector(response).xpath('//a[@href="link.html"][@id="i1"]') # 多个属性并列
# hxs = Selector(response=response).xpath('//a[contains(@href, "link")]') # href属性包含link
# hxs = Selector(response=response).xpath('//a[starts-with(@href, "link")]') # href属性以link开头
# hxs = Selector(response=response).xpath('//a[re:test(@id, "i\d+")]') # 正则匹配 以re:test开始
# 使用extract()变成标签
# hxs = Selector(response).xpath("//a/text()")[0].extract() # 取所有a标签的text
# hxs = Selector(response).xpath('//a/@href')[0].extract_first() # 取第一个a标签的href
# print(hxs)
item_list = response.xpath("//div[@id='content-list']/div[@class='item']")
for item in item_list:
text = item.xpath('.//a/text()').extract_first()
href = item.xpath('.//a/@href').extract_first()
print(href, text.strip())
转载：https://blog.csdn.net/fei347795790/article/details/100559371
查看评论