scrapy

#1、执行全局命令：请确保不在某个项目的目录下，排除受该项目配置的影响
scrapy startproject MyProject

cd MyProject
scrapy genspider baidu www.baidu.com

scrapy settings --get XXX #如果切换到项目目录下，看到的则是该项目的配置

scrapy runspider baidu.py

scrapy shell https://www.baidu.com
    response
    response.status
    response.body
    view(response)
    
scrapy view https://www.taobao.com #如果页面显示内容不全，不全的内容则是ajax请求实现的，以此快速定位问题

scrapy fetch --nolog --headers https://www.taobao.com

scrapy version #scrapy的版本

scrapy version -v #依赖库的版本


#2、执行项目命令：切到项目目录下
scrapy crawl baidu
scrapy check
scrapy list
scrapy parse http://quotes.toscrape.com/ --callback parse
scrapy bench
    

#在项目目录下新建：entrypoint.py
from scrapy.cmdline import execute
execute(['scrapy', 'crawl', 'xiaohua'])

import sys,os
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')

#1、name = 'amazon' 
定义爬虫名，scrapy会根据该值定位爬虫程序
所以它必须要有且必须唯一（In Python 2 this must be ASCII only.）

#2、allowed_domains = ['www.amazon.cn'] 
定义允许爬取的域名，如果OffsiteMiddleware启动（默认就启动），
那么不属于该列表的域名及其子域名都不允许爬取
如果爬取的网址为：https://www.example.com/1.html，那就添加'example.com'到列表.

#3、start_urls = ['http://www.amazon.cn/']
如果没有指定url，就从该列表中读取url来生成第一个请求

#4、custom_settings
值为一个字典，定义一些配置信息，在运行爬虫程序时，这些配置会覆盖项目级别的配置
所以custom_settings必须被定义成一个类属性，由于settings会在类实例化前被加载

#5、settings
通过self.settings['配置项的名字']可以访问settings.py中的配置，如果自己定义了custom_settings还是以自己的为准

#6、logger
日志名默认为spider的名字
self.logger.debug('=============>%s' %self.settings['BOT_NAME'])

#5、crawler：了解
该属性必须被定义到类方法from_crawler中

#6、from_crawler(crawler, *args, **kwargs)：了解
You probably won’t need to override this directly  because the default implementation acts as a proxy to the __init__() method, calling it with the given arguments args and named arguments kwargs.

#7、start_requests()
该方法用来发起第一个Requests请求，且必须返回一个可迭代的对象。它在爬虫程序打开时就被Scrapy调用，Scrapy只调用它一次。
默认从start_urls里取出每个url来生成Request(url, dont_filter=True)

#针对参数dont_filter,请看自定义去重规则

如果你想要改变起始爬取的Requests，你就需要覆盖这个方法，例如你想要起始发送一个POST请求，如下
class MySpider(scrapy.Spider):
    name = 'myspider'

    def start_requests(self):
        return [scrapy.FormRequest("http://www.example.com/login",
                                   formdata={'user': 'john', 'pass': 'secret'},
                                   callback=self.logged_in)]

    def logged_in(self, response):
        # here you would extract links to follow and return Requests for
        # each of them, with another callback
        pass
        
#8、parse(response)
这是默认的回调函数，所有的回调函数必须返回an iterable of Request and/or dicts or Item objects.

#9、log(message[, level, component])：了解
Wrapper that sends a log message through the Spider’s logger, kept for backwards compatibility. For more information see Logging from Spiders.

#10、closed(reason)
爬虫程序结束时自动触发

去重规则应该多个爬虫共享的，但凡一个爬虫爬取了，其他都不要爬了，实现方式如下

#方法一：
1、新增类属性
visited=set() #类属性

2、回调函数parse方法内：
def parse(self, response):
    if response.url in self.visited:
        return None
    .......

    self.visited.add(response.url) 

#方法一改进：针对url可能过长，所以我们存放url的hash值
def parse(self, response):
        url=md5(response.request.url)
    if url in self.visited:
        return None
    .......

    self.visited.add(url) 

#方法二：Scrapy自带去重功能
配置文件：
DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter' #默认的去重规则帮我们去重，去重规则在内存中
DUPEFILTER_DEBUG = False
JOBDIR = "保存范文记录的日志路径，如：/root/"  # 最终路径为 /root/requests.seen，去重规则放文件中

scrapy自带去重规则默认为RFPDupeFilter，只需要我们指定
Request(...,dont_filter=False) ，如果dont_filter=True则告诉Scrapy这个URL不参与去重。

#方法三：
我们也可以仿照RFPDupeFilter自定义去重规则，

from scrapy.dupefilter import RFPDupeFilter，看源码，仿照BaseDupeFilter

#步骤一：在项目目录下自定义去重文件dup.py
class UrlFilter(object):
    def __init__(self):
        self.visited = set() #或者放到数据库

    @classmethod
    def from_settings(cls, settings):
        return cls()

    def request_seen(self, request):
        if request.url in self.visited:
            return True
        self.visited.add(request.url)

    def open(self):  # can return deferred
        pass

    def close(self, reason):  # can return a deferred
        pass

    def log(self, request, spider):  # log that a request has been filtered
        pass

#步骤二：配置文件settings.py：
DUPEFILTER_CLASS = '项目名.dup.UrlFilter'


# 源码分析：
from scrapy.core.scheduler import Scheduler
见Scheduler下的enqueue_request方法：self.df.request_seen(request)

#例一：
import scrapy

class MySpider(scrapy.Spider):
    name = 'example.com'
    allowed_domains = ['example.com']
    start_urls = [
        'http://www.example.com/1.html',
        'http://www.example.com/2.html',
        'http://www.example.com/3.html',
    ]

    def parse(self, response):
        self.logger.info('A response from %s just arrived!', response.url)
        
    
#例二：一个回调函数返回多个Requests和Items
import scrapy

class MySpider(scrapy.Spider):
    name = 'example.com'
    allowed_domains = ['example.com']
    start_urls = [
        'http://www.example.com/1.html',
        'http://www.example.com/2.html',
        'http://www.example.com/3.html',
    ]

    def parse(self, response):
        for h3 in response.xpath('//h3').extract():
            yield {"title": h3}

        for url in response.xpath('//a/@href').extract():
            yield scrapy.Request(url, callback=self.parse)
            
            
#例三：在start_requests()内直接指定起始爬取的urls，start_urls就没有用了，

import scrapy
from myproject.items import MyItem

class MySpider(scrapy.Spider):
    name = 'example.com'
    allowed_domains = ['example.com']

    def start_requests(self):
        yield scrapy.Request('http://www.example.com/1.html', self.parse)
        yield scrapy.Request('http://www.example.com/2.html', self.parse)
        yield scrapy.Request('http://www.example.com/3.html', self.parse)

    def parse(self, response):
        for h3 in response.xpath('//h3').extract():
            yield MyItem(title=h3)

        for url in response.xpath('//a/@href').extract():
            yield scrapy.Request(url, callback=self.parse)

我们可能需要在命令行为爬虫程序传递参数，比如传递初始的url，像这样
#命令行执行
scrapy crawl myspider -a category=electronics

#在__init__方法中可以接收外部传进来的参数
import scrapy

class MySpider(scrapy.Spider):
    name = 'myspider'

    def __init__(self, category=None, *args, **kwargs):
        super(MySpider, self).__init__(*args, **kwargs)
        self.start_urls = ['http://www.example.com/categories/%s' % category]
        #...

        
#注意接收的参数全都是字符串，如果想要结构化的数据，你需要用类似json.loads的方法

response.selector.css()
response.selector.xpath()
可简写为
response.css()
response.xpath()

#1 //与/
response.xpath('//body/a/')#
response.css('div a::text')

>>> response.xpath('//body/a') #开头的//代表从整篇文档中寻找,body之后的/代表body的儿子
[]
>>> response.xpath('//body//a') #开头的//代表从整篇文档中寻找,body之后的//代表body的子子孙孙
[<Selector xpath='//body//a' data='<a href="image1.html">Name: My image 1 <'>, <Selector xpath='//body//a' data='<a href="image2.html">Name: My image 2 <'>, <Selector xpath='//body//a' data='<a href="
image3.html">Name: My image 3 <'>, <Selector xpath='//body//a' data='<a href="image4.html">Name: My image 4 <'>, <Selector xpath='//body//a' data='<a href="image5.html">Name: My image 5 <'>]

#2 text
>>> response.xpath('//body//a/text()')
>>> response.css('body a::text')

#3、extract与extract_first:从selector对象中解出内容
>>> response.xpath('//div/a/text()').extract()
['Name: My image 1 ', 'Name: My image 2 ', 'Name: My image 3 ', 'Name: My image 4 ', 'Name: My image 5 ']
>>> response.css('div a::text').extract()
['Name: My image 1 ', 'Name: My image 2 ', 'Name: My image 3 ', 'Name: My image 4 ', 'Name: My image 5 ']

>>> response.xpath('//div/a/text()').extract_first()
'Name: My image 1 '
>>> response.css('div a::text').extract_first()
'Name: My image 1 '

#4、属性：xpath的属性加前缀@
>>> response.xpath('//div/a/@href').extract_first()
'image1.html'
>>> response.css('div a::attr(href)').extract_first()
'image1.html'

#4、嵌套查找
>>> response.xpath('//div').css('a').xpath('@href').extract_first()
'image1.html'

#5、设置默认值
>>> response.xpath('//div[@id="xxx"]').extract_first(default="not found")
'not found'

#4、按照属性查找
response.xpath('//div[@id="images"]/a[@href="image3.html"]/text()').extract()
response.css('#images a[@href="image3.html"]/text()').extract()

#5、按照属性模糊查找
response.xpath('//a[contains(@href,"image")]/@href').extract()
response.css('a[href*="image"]::attr(href)').extract()

response.xpath('//a[contains(@href,"image")]/img/@src').extract()
response.css('a[href*="imag"] img::attr(src)').extract()

response.xpath('//*[@href="image1.html"]')
response.css('*[href="image1.html"]')

#6、正则表达式
response.xpath('//a/text()').re(r'Name: (.*)')
response.xpath('//a/text()').re_first(r'Name: (.*)')

#7、xpath相对路径
>>> res=response.xpath('//a[contains(@href,"3")]')[0]
>>> res.xpath('img')
[<Selector xpath='img' data='<img src="image3_thumb.jpg">'>]
>>> res.xpath('./img')
[<Selector xpath='./img' data='<img src="image3_thumb.jpg">'>]
>>> res.xpath('.//img')
[<Selector xpath='.//img' data='<img src="image3_thumb.jpg">'>]
>>> res.xpath('//img') #这就是从头开始扫描
[<Selector xpath='//img' data='<img src="image1_thumb.jpg">'>, <Selector xpath='//img' data='<img src="image2_thumb.jpg">'>, <Selector xpath='//img' data='<img src="image3_thumb.jpg">'>, <Selector xpa
th='//img' data='<img src="image4_thumb.jpg">'>, <Selector xpath='//img' data='<img src="image5_thumb.jpg">'>]

#8、带变量的xpath
>>> response.xpath('//div[@id=$xxx]/a/text()',xxx='images').extract_first()
'Name: My image 1 '
>>> response.xpath('//div[count(a)=$yyy]/@id',yyy=5).extract_first() #求有5个a标签的div的id
'images'