selenium模块

selenium模块

什么是selenium？selenium是Python的一个第三方库，对外提供的接口可以操作浏览器，然后让浏览器完成自动化的操作。　
selenium最初是一个自动化测试工具,而爬虫中使用它主要是为了解决requests无法直接执行JavaScript代码的问题 selenium本质是通过驱动浏览器，完全模拟浏览器的操作，比如跳转、输入、点击、下拉等，来拿到网页渲染之后的结果，可支持多种浏览器

下载安装

1 下载驱动

http://npm.taobao.org/mirrors/chromedriver/2.35/　　

if mac系统：

然后将解压后的chromedriver移动到/usr/local/bin目录下

if window系统：

下载chromdriver.exe放到python安装路径的scripts目录中即可，注意最新版本是2.38，并非2.9

2 安装pip包

pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple selenium

注意：selenium3默认支持的webdriver是Firfox，而Firefox需要安装geckodriver 下载链接

更多操作

"""
## 1、Selenium支持非常多的浏览器，如Chrome、Firefox、Edge等，还有Android、BlackBerry等手机端的浏览器。另外，也支持无界面浏览器PhantomJS。

from selenium import webdriver

browser = webdriver.Chrome()
browser = webdriver.Firefox()
browser = webdriver.Edge()
browser = webdriver.PhantomJS()
browser = webdriver.Safari()

## 2、元素定位

webdriver 提供了一系列的元素定位方法，常用的有以下几种：
id
name
class name
tag name
link text
partial link text
xpath
css selector


分别对应python webdriver 中的方法为：
find_element_by_id()
find_element_by_name()
find_element_by_class_name()
find_element_by_tag_name()
find_element_by_link_text()
find_element_by_partial_link_text()
find_element_by_xpath()
find_element_by_css_selector()


1、find_element_by_xxx找的是第一个符合条件的标签，find_elements_by_xxx找的是所有符合条件的标签。
2、根据ID、CSS选择器和XPath获取，它们返回的结果完全一致。
3、另外，Selenium还提供了通用方法find_element()，它需要传入两个参数：查找方式By和值。实际上，它就是find_element_by_id()这种方法的通用函数版本，
比如find_element_by_id(id)就等价于find_element(By.ID, id)，二者得到的结果完全一致。



## 3、节点交互
Selenium可以驱动浏览器来执行一些操作，也就是说可以让浏览器模拟执行一些动作。比较常见的用法有：输入文字时用send_keys()方法，清空文字时用clear()方法，
点击按钮时用click()方法。示例如下：

"""
from selenium import webdriver
import time

browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input = browser.find_element_by_id('q')
input.send_keys('MAC')
time.sleep(1)
input.clear()
input.send_keys('IPhone')
button = browser.find_element_by_class_name('btn-search')
button.click()



"""
4 动作链

在上面的实例中，一些交互动作都是针对某个节点执行的。比如，对于输入框，我们就调用它的输入文字和清空文字方法；对于按钮，就调用它的点击方法。
其实，还有另外一些操作，它们没有特定的执行对象，比如鼠标拖曳、键盘按键等，这些动作用另一种方式来执行，那就是动作链。
比如，现在实现一个节点的拖曳操作，将某个节点从一处拖曳到另外一处，可以这样实现：

"""
from selenium import webdriver
from selenium.webdriver import ActionChains
import time
browser = webdriver.Chrome()
url = 'http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable'
browser.get(url)
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
target = browser.find_element_by_css_selector('#droppable')
actions = ActionChains(browser)
# actions.drag_and_drop(source, target)
actions.click_and_hold(source).perform()
time.sleep(1)
actions.move_to_element(target).perform()
time.sleep(1)
actions.move_by_offset(xoffset=50,yoffset=0).perform()

actions.release()

"""
5 执行JavaScript

对于某些操作，Selenium API并没有提供。比如，下拉进度条，它可以直接模拟运行JavaScript，此时使用execute_script()方法即可实现，代码如下：



"""
from selenium import webdriver

browser = webdriver.Chrome()
browser.get('https://www.jd.com/')
browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')
browser.execute_script('alert("123")')
"""
6 获取节点信息

通过page_source属性可以获取网页的源代码，接着就可以使用解析库（如正则表达式、Beautiful Soup、pyquery等）来提取信息了。
不过，既然Selenium已经提供了选择节点的方法，返回的是WebElement类型，那么它也有相关的方法和属性来直接提取节点信息，如属性、文本等。
这样的话，我们就可以不用通过解析源代码来提取信息了，非常方便。

"""
from selenium import webdriver
from selenium.webdriver.common.by import By #按照什么方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素

browser=webdriver.Chrome()

browser.get('https://www.amazon.cn/')

wait=WebDriverWait(browser,10)
wait.until(EC.presence_of_element_located((By.ID,'cc-lm-tcgShowImgContainer')))

tag=browser.find_element(By.CSS_SELECTOR,'#cc-lm-tcgShowImgContainer img')

#获取标签属性，
print(tag.get_attribute('src'))
#获取标签ID，位置，名称，大小（了解）
print(tag.id)
print(tag.location)
print(tag.tag_name)
print(tag.size)


browser.close()
"""
7 延时等待

在Selenium中，get()方法会在网页框架加载结束后结束执行，此时如果获取page_source，可能并不是浏览器完全加载完成的页面，
如果某些页面有额外的Ajax请求，我们在网页源代码中也不一定能成功获取到。所以，这里需要延时等待一定时间，确保节点已经加载出来。
这里等待的方式有两种：一种是隐式等待，一种是显式等待。

隐式等待：

当使用隐式等待执行测试的时候，如果Selenium没有在DOM中找到节点，将继续等待，超出设定时间后，则抛出找不到节点的异常。换句话说，
当查找节点而节点并没有立即出现的时候，隐式等待将等待一段时间再查找DOM，默认的时间是0。示例如下：

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什么方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #键盘按键操作
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素

browser=webdriver.Chrome()

#隐式等待:在查找所有元素时，如果尚未被加载，则等10秒
browser.implicitly_wait(10)

browser.get('https://www.baidu.com')
input_tag=browser.find_element_by_id('kw')
input_tag.send_keys('美女')
input_tag.send_keys(Keys.ENTER)

contents=browser.find_element_by_id('content_left') #没有等待环节而直接查找，找不到则会报错
print(contents)

browser.close()
显示等待：

隐式等待的效果其实并没有那么好，因为我们只规定了一个固定时间，而页面的加载时间会受到网络条件的影响。这里还有一种更合适的显式等待方法，
它指定要查找的节点，然后指定一个最长等待时间。如果在规定时间内加载出来了这个节点，就返回查找的节点；如果到了规定时间依然没有加载出该节点，
则抛出超时异常。

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什么方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #键盘按键操作
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待页面加载某些元素

browser=webdriver.Chrome()
browser.get('https://www.baidu.com')


input_tag=browser.find_element_by_id('kw')
input_tag.send_keys('美女')
input_tag.send_keys(Keys.ENTER)


#显式等待：显式地等待某个元素被加载
wait=WebDriverWait(browser,10)
wait.until(EC.presence_of_element_located((By.ID,'content_left')))

contents=browser.find_element(By.CSS_SELECTOR,'#content_left')
print(contents)


browser.close()
关于等待条件，其实还有很多，比如判断标题内容，判断某个节点内是否出现了某文字等。more



8 Cookies

使用Selenium，还可以方便地对Cookies进行操作，例如获取、添加、删除Cookies等。示例如下：

from selenium import webdriver
 
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
print(browser.get_cookies())
browser.add_cookie({'name': 'name', 'domain': 'www.zhihu.com', 'value': 'germey'})
print(browser.get_cookies())
browser.delete_all_cookies()
print(browser.get_cookies())


9 异常处理

from selenium import webdriver
from selenium.common.exceptions import TimeoutException,NoSuchElementException,NoSuchFrameException

try:
    browser=webdriver.Chrome()
    browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
    browser.switch_to.frame('iframssseResult')

except TimeoutException as e:
    print(e)
except NoSuchFrameException as e:
    print(e)
finally:
    browser.close()
"""

"""
PhantomJS是一款无界面的浏览器，其自动化操作流程和上述操作谷歌浏览器是一致的。由于是无界面的，为了能够展示自动化操作流程，
PhantomJS为用户提供了一个截屏的功能，使用save_screenshot函数实现。
"""
from selenium import webdriver
import time

# phantomjs路径
path = r'PhantomJS驱动路径'
browser = webdriver.PhantomJS(path)

# 打开百度
url = 'http://www.baidu.com/'
browser.get(url)

time.sleep(3)

browser.save_screenshot(r'phantomjsaidu.png')

# 查找input输入框
my_input = browser.find_element_by_id('kw')
# 往框里面写文字
my_input.send_keys('美女')
time.sleep(3)
#截屏
browser.save_screenshot(r'phantomjsmeinv.png')

# 查找搜索按钮
button = browser.find_elements_by_class_name('s_btn')[0]
button.click()

time.sleep(3)

browser.save_screenshot(r'phantomjsshow.png')

time.sleep(3)

browser.quit()


"""
重点：selenium+phantomjs 就是爬虫终极解决方案:有些网站上的内容信息是通过动态加载js形成的，所以使用普通爬虫程序无法回去动态加载的js内容。
例如豆瓣电影中的电影信息是通过下拉操作动态加载更多的电影信息。
综合操作：需求是尽可能多的爬取豆瓣网中的电影信息
"""

from selenium import webdriver
from time import sleep
import time

if __name__ == '__main__':
    url = 'https://movie.douban.com/typerank?type_name=%E6%81%90%E6%80%96&type=20&interval_id=100:90&action='
    # 发起请求前，可以让url表示的页面动态加载出更多的数据
    path = r'C:UsersAdministratorDesktop爬虫授课day05ziliaophantomjs-2.1.1-windowsinphantomjs.exe'
    # 创建无界面的浏览器对象
    bro = webdriver.PhantomJS(path)
    # 发起url请求
    bro.get(url)
    time.sleep(3)
    # 截图
    bro.save_screenshot('1.png')

    # 执行js代码（让滚动条向下偏移n个像素（作用：动态加载了更多的电影信息））
    js = 'window.scrollTo(0,document.body.scrollHeight)'
    bro.execute_script(js)  # 该函数可以执行一组字符串形式的js代码
    time.sleep(2)

    bro.execute_script(js)  # 该函数可以执行一组字符串形式的js代码
    time.sleep(2)
    bro.save_screenshot('2.png') 
    time.sleep(2) 
    # 使用爬虫程序爬去当前url中的内容 
    html_source = bro.page_source # 该属性可以获取当前浏览器的当前页的源码（html） 
    with open('./source.html', 'w', encoding='utf-8') as fp: 
        fp.write(html_source) 
    bro.quit()

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait # 等待元素加载的
from selenium.webdriver.common.action_chains import ActionChains  #拖拽
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, NoSuchElementException
from selenium.webdriver.common.by import By
from PIL import Image
import requests
import re
import random
from io import BytesIO
import time


def merge_image(image_file,location_list):
    """
     拼接图片
    """
    im = Image.open(image_file)
    im.save('code.jpg')
    new_im = Image.new('RGB',(260,116))
    # 把无序的图片 切成52张小图片
    im_list_upper = []
    im_list_down = []
    # print(location_list)
    for location in location_list:
        # print(location['y'])
        if location['y'] == -58: # 上半边
            im_list_upper.append(im.crop((abs(location['x']),58,abs(location['x'])+10,116)))
        if location['y'] == 0:  # 下半边
            im_list_down.append(im.crop((abs(location['x']),0,abs(location['x'])+10,58)))

    x_offset = 0
    for im in im_list_upper:
        new_im.paste(im,(x_offset,0))  # 把小图片放到 新的空白图片上
        x_offset += im.size[0]

    x_offset = 0
    for im in im_list_down:
        new_im.paste(im,(x_offset,58))
        x_offset += im.size[0]
    #new_im.show()
    return new_im

def get_image(driver,div_path):
    '''
    下载无序的图片  然后进行拼接 获得完整的图片
    :param driver:
    :param div_path:
    :return:
    '''
    background_images = driver.find_elements_by_xpath(div_path)
    location_list = []
    for background_image in background_images:
        location = {}
        result = re.findall('background-image: url("(.*?)"); background-position: (.*?)px (.*?)px;',background_image.get_attribute('style'))
        # print(result)
        location['x'] = int(result[0][1])
        location['y'] = int(result[0][2])

        image_url = result[0][0]
        location_list.append(location)
    image_url = image_url.replace('webp','jpg')
    # '替换url http://static.geetest.com/pictures/gt/579066de6/579066de6.webp'
    image_result = requests.get(image_url).content
    image_file = BytesIO(image_result) # 是一张无序的图片
    image = merge_image(image_file,location_list)

    return image


def get_track(distance):

    # 初速度
    v=0
    # 单位时间为0.2s来统计轨迹，轨迹即0.2内的位移
    t=0.2
    # 位移/轨迹列表，列表内的一个元素代表0.2s的位移
    tracks=[]
    tracks_back=[]
    # 当前的位移
    current=0
    # 到达mid值开始减速
    mid=distance * 7/8
    print("distance",distance)
    global random_int
    random_int=8
    distance += random_int # 先滑过一点，最后再反着滑动回来

    while current < distance:
        if current < mid:
            # 加速度越小，单位时间的位移越小,模拟的轨迹就越多越详细
            a = random.randint(2,5)  # 加速运动
        else:
            a = -random.randint(2,5) # 减速运动
        # 初速度
        v0 = v
        # 0.2秒时间内的位移
        s = v0*t+0.5*a*(t**2)
        # 当前的位置
        current += s
        # 添加到轨迹列表
        if round(s)>0:
            tracks.append(round(s))
        else:
            tracks_back.append(round(s))


        # 速度已经达到v,该速度作为下次的初速度
        v= v0+a*t

        print("tracks:",tracks)
        print("tracks_back:",tracks_back)
        print("current:",current)

    # 反着滑动到大概准确位置

    tracks_back.append(distance-current)
    tracks_back.extend([-2,-5,-8,])

    return tracks,tracks_back


def get_distance(image1,image2):
    '''
       拿到滑动验证码需要移动的距离
      :param image1:没有缺口的图片对象
      :param image2:带缺口的图片对象
      :return:需要移动的距离
      '''
    # print('size', image1.size)

    threshold = 50
    for i in range(0,image1.size[0]):  # 260
        for j in range(0,image1.size[1]):  # 160
            pixel1 = image1.getpixel((i,j))
            pixel2 = image2.getpixel((i,j))
            res_R = abs(pixel1[0]-pixel2[0]) # 计算RGB差
            res_G = abs(pixel1[1] - pixel2[1])  # 计算RGB差
            res_B = abs(pixel1[2] - pixel2[2])  # 计算RGB差
            if res_R > threshold and res_G > threshold and res_B > threshold:
                return i  # 需要移动的距离


def main_check_code(driver,element):
    """
    拖动识别验证码
    :param driver:
    :param element:
    :return:
    """

    login_btn = driver.find_element_by_class_name('js-login')
    login_btn.click()

    element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'gt_guide_tip')))
    slide_btn = driver.find_element_by_class_name('gt_guide_tip')
    slide_btn.click()



    image1 = get_image(driver, '//div[@class="gt_cut_bg gt_show"]/div')
    image2 = get_image(driver, '//div[@class="gt_cut_fullbg gt_show"]/div')
    # 图片上 缺口的位置的x坐标

    # 2 对比两张图片的所有RBG像素点，得到不一样像素点的x值，即要移动的距离
    l = get_distance(image1, image2)
    print('l=',l)

    # 3 获得移动轨迹
    track_list = get_track(l)
    print('第一步,点击滑动按钮')
    element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'gt_slider_knob')))
    ActionChains(driver).click_and_hold(on_element=element).perform()  # 点击鼠标左键，按住不放
    import time
    time.sleep(0.4)
    print('第二步,拖动元素')
    for track in track_list[0]:
         ActionChains(driver).move_by_offset(xoffset=track, yoffset=0).perform()  # 鼠标移动到距离当前位置（x,y）
    #time.sleep(0.4)
    for track in track_list[1]:
          ActionChains(driver).move_by_offset(xoffset=track, yoffset=0).perform()  # 鼠标移动到距离当前位置（x,y）
          time.sleep(0.1)
    import time
    time.sleep(0.6)
    # ActionChains(driver).move_by_offset(xoffset=2, yoffset=0).perform()  # 鼠标移动到距离当前位置（x,y）
    # ActionChains(driver).move_by_offset(xoffset=8, yoffset=0).perform()  # 鼠标移动到距离当前位置（x,y）
    # ActionChains(driver).move_by_offset(xoffset=2, yoffset=0).perform()  # 鼠标移动到距离当前位置（x,y）
    print('第三步,释放鼠标')
    ActionChains(driver).release(on_element=element).perform()
    time.sleep(1)

def main_check_slider(driver):
    """
    检查滑动按钮是否加载
    :param driver:
    :return:
    """
    while True:
        try :
            driver.get('https://www.huxiu.com/')
            element = WebDriverWait(driver, 30, 0.5).until(EC.element_to_be_clickable((By.CLASS_NAME, 'js-login')))
            if element:
                return element
        except TimeoutException as e:
            print('超时错误，继续')
            time.sleep(5)

if __name__ == '__main__':

    try:
        count = 3  # 最多识别3次
        driver = webdriver.Chrome()
        while count > 0:
            # 等待滑动按钮加载完成
            element = main_check_slider(driver)
            main_check_code(driver,element)
            try:
                success_element = (By.CSS_SELECTOR, '.gt_success')
                # 得到成功标志
                success_images = WebDriverWait(driver,3).until(EC.presence_of_element_located(success_element))
                if success_images:
                    print('成功识别！！！！！！')
                    count = 0
                    import sys
                    sys.exit()
            except Exception as e:
                print('识别错误，继续')
                count -= 1
                time.sleep(1)
        else:
            print('too many attempt check code ')
            exit('退出程序')
    finally:
        driver.close()

Scrapy

"""
1. scrapy startproject 项目名称
   - 在当前目录中创建中创建一个项目文件（类似于Django）

2. scrapy genspider [-t template] <name> <domain>
   - 创建爬虫应用
   如：
      scrapy gensipider -t basic oldboy oldboy.com
      scrapy gensipider -t xmlfeed autohome autohome.com.cn
   PS:
      查看所有命令：scrapy gensipider -l
      查看模板命令：scrapy gensipider -d 模板名称

3. scrapy list
   - 展示爬虫应用列表

4. scrapy crawl 爬虫应用名称
   - 运行单独爬虫应用
"""

## 注意：settings.py中设置DEPTH_LIMIT = 1来指定“递归”的层数。
import scrapy
from scrapy.selector import HtmlXPathSelector
from scrapy.http.request import Request
from scrapy.http.cookies import CookieJar
from scrapy import FormRequest


class ChouTiSpider(scrapy.Spider):
    # 爬虫应用的名称，通过此名称启动爬虫命令
    name = "chouti"
    # 允许的域名
    allowed_domains = ["chouti.com"]

    cookie_dict = {}
    has_request_set = {}

    def start_requests(self):
        url = 'http://dig.chouti.com/'
        # return [Request(url=url, callback=self.login)]
        yield Request(url=url, callback=self.login)

    def login(self, response):
        cookie_jar = CookieJar()
        cookie_jar.extract_cookies(response, response.request)
        for k, v in cookie_jar._cookies.items():
            for i, j in v.items():
                for m, n in j.items():
                    self.cookie_dict[m] = n.value

        req = Request(
            url='http://dig.chouti.com/login',
            method='POST',
            headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
            body='phone=8615131255089&password=pppppppp&oneMonth=1',
            cookies=self.cookie_dict,
            callback=self.check_login
        )
        yield req

    def check_login(self, response):
        req = Request(
            url='http://dig.chouti.com/',
            method='GET',
            callback=self.show,
            cookies=self.cookie_dict,
            dont_filter=True
        )
        yield req

    def show(self, response):
        # print(response)
        hxs = HtmlXPathSelector(response)
        news_list = hxs.select('//div[@id="content-list"]/div[@class="item"]')
        for new in news_list:
            # temp = new.xpath('div/div[@class="part2"]/@share-linkid').extract()
            link_id = new.xpath('*/div[@class="part2"]/@share-linkid').extract_first()
            yield Request(
                url='http://dig.chouti.com/link/vote?linksId=%s' %(link_id,),
                method='POST',
                cookies=self.cookie_dict,
                callback=self.do_favor
            )

        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
            import hashlib
            hash = hashlib.md5()
            hash.update(bytes(page_url,encoding='utf-8'))
            key = hash.hexdigest()
            if key in self.has_request_set:
                pass
            else:
                self.has_request_set[key] = page_url
                yield Request(
                    url=page_url,
                    method='GET',
                    callback=self.show
                )

    def do_favor(self, response):
        print(response.text)




#pipelines
import json
import os
import requests


class JsonPipeline(object):
    def __init__(self):
        self.file = open('xiaohua.txt', 'w')

    def process_item(self, item, spider):
        v = json.dumps(dict(item), ensure_ascii=False)
        self.file.write(v)
        self.file.write('
')
        self.file.flush()
        return item


class FilePipeline(object):
    def __init__(self):
        if not os.path.exists('imgs'):
            os.makedirs('imgs')

    def process_item(self, item, spider):
        response = requests.get(item['url'], stream=True)
        file_name = '%s_%s.jpg' % (item['name'], item['school'])
        with open(os.path.join('imgs', file_name), mode='wb') as f:
            f.write(response.content)
        return item



##自定义pipelines
from scrapy.exceptions import DropItem

class CustomPipeline(object):
    def __init__(self,v):
        self.value = v

    def process_item(self, item, spider):
        # 操作并进行持久化

        # return表示会被后续的pipeline继续处理
        return item

        # 表示将item丢弃，不会被后续pipeline处理
        # raise DropItem()


    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化时候，用于创建pipeline对象
        :param crawler:
        :return:
        """
        val = crawler.settings.getint('MMMM')
        return cls(val)

    def open_spider(self,spider):
        """
        爬虫开始执行时，调用
        :param spider:
        :return:
        """
        print('000000')

    def close_spider(self,spider):
        """
        爬虫关闭时，被调用
        :param spider:
        :return:
        """
        print('111111')


#settings
ITEM_PIPELINES = {
   'spider1.pipelines.JsonPipeline': 100,
   'spider1.pipelines.FilePipeline': 300,
}
# 每行后面的整型值，确定了他们运行的顺序，item按数字从低到高的顺序，通过pipeline，通常将这些数字定义在0-1000范围内。


####爬虫中间件
class SpiderMiddleware(object):

    def process_spider_input(self,response, spider):
        """
        下载完成，执行，然后交给parse处理
        :param response:
        :param spider:
        :return:
        """
        pass

    def process_spider_output(self,response, result, spider):
        """
        spider处理完成，返回时调用
        :param response:
        :param result:
        :param spider:
        :return: 必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
        """
        return result

    def process_spider_exception(self,response, exception, spider):
        """
        异常调用
        :param response:
        :param exception:
        :param spider:
        :return: None,继续交给后续中间件处理异常；含 Response 或 Item 的可迭代对象(iterable)，交给调度器或pipeline
        """
        return None


    def process_start_requests(self,start_requests, spider):
        """
        爬虫启动时调用
        :param start_requests:
        :param spider:
        :return: 包含 Request 对象的可迭代对象
        """
        return start_requests



###下载中间件
class DownMiddleware1(object):
    def process_request(self, request, spider):
        """
        请求需要被下载时，经过所有下载器中间件的process_request调用
        :param request:
        :param spider:
        :return:
            None,继续后续中间件去下载；
            Response对象，停止process_request的执行，开始执行process_response
            Request对象，停止中间件的执行，将Request重新调度器
            raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
        """
        pass



    def process_response(self, request, response, spider):
        """
        spider处理完成，返回时调用
        :param response:
        :param result:
        :param spider:
        :return:
            Response 对象：转交给其他中间件process_response
            Request 对象：停止中间件，request会被重新调度下载
            raise IgnoreRequest 异常：调用Request.errback
        """
        print('response1')
        return response

    def process_exception(self, request, exception, spider):
        """
        当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
        :param response:
        :param exception:
        :param spider:
        :return:
            None：继续交给后续中间件处理异常；
            Response对象：停止后续process_exception方法
            Request对象：停止中间件，request将会被重新调用下载
        """
        return None

1. 自定制命令

• 在spiders同级创建任意目录，如：commands
• 在其中创建 crawlall.py 文件 （此处文件名就是自定义的命令）
  
• 在settings.py 中添加配置 COMMANDS_MODULE = '项目名称.目录名称'
• 在项目目录执行命令：scrapy crawlall 

from scrapy.commands import ScrapyCommand
    from scrapy.utils.project import get_project_settings


    class Command(ScrapyCommand):

        requires_project = True

        def syntax(self):
            return '[options]'

        def short_desc(self):
            return 'Runs all of the spiders'

        def run(self, args, opts):
            spider_list = self.crawler_process.spiders.list()
            for name in spider_list:
                self.crawler_process.crawl(name, **opts.__dict__)
            self.crawler_process.start()

2. 自定义扩展

自定义扩展时，利用信号在指定位置注册制定操作

from scrapy import signals


class MyExtension(object):
    def __init__(self, value):
        self.value = value

    @classmethod
    def from_crawler(cls, crawler):
        val = crawler.settings.getint('MMMM')
        ext = cls(val)

        crawler.signals.connect(ext.spider_opened, signal=signals.spider_opened)
        crawler.signals.connect(ext.spider_closed, signal=signals.spider_closed)

        return ext

    def spider_opened(self, spider):
        print('open')

    def spider_closed(self, spider):
        print('close')

3. 避免重复访问

scrapy默认使用 scrapy.dupefilter.RFPDupeFilter 进行去重，相关配置有：

DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter'
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

class RepeatUrl:
    def __init__(self):
        self.visited_url = set()

    @classmethod
    def from_settings(cls, settings):
        """
        初始化时，调用
        :param settings: 
        :return: 
        """
        return cls()

    def request_seen(self, request):
        """
        检测当前请求是否已经被访问过
        :param request: 
        :return: True表示已经访问过；False表示未访问过
        """
        if request.url in self.visited_url:
            return True
        self.visited_url.add(request.url)
        return False

    def open(self):
        """
        开始爬去请求时，调用
        :return: 
        """
        print('open replication')

    def close(self, reason):
        """
        结束爬虫爬取时，调用
        :param reason: 
        :return: 
        """
        print('close replication')

    def log(self, request, spider):
        """
        记录日志
        :param request: 
        :param spider: 
        :return: 
        """
        print('repeat', request.url)

4.其他

# -*- coding: utf-8 -*-

# Scrapy settings for step8_king project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

# 1. 爬虫名称
BOT_NAME = 'step8_king'

# 2. 爬虫应用路径
SPIDER_MODULES = ['step8_king.spiders']
NEWSPIDER_MODULE = 'step8_king.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# 3. 客户端 user-agent请求头
# USER_AGENT = 'step8_king (+http://www.yourdomain.com)'

# Obey robots.txt rules
# 4. 禁止爬虫配置
# ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# 5. 并发请求数
# CONCURRENT_REQUESTS = 4

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# 6. 延迟下载秒数
# DOWNLOAD_DELAY = 2


# The download delay setting will honor only one of:
# 7. 单域名访问并发数，并且延迟下次秒数也应用在每个域名
# CONCURRENT_REQUESTS_PER_DOMAIN = 2
# 单IP访问并发数，如果有值则忽略：CONCURRENT_REQUESTS_PER_DOMAIN，并且延迟下次秒数也应用在每个IP
# CONCURRENT_REQUESTS_PER_IP = 3

# Disable cookies (enabled by default)
# 8. 是否支持cookie，cookiejar进行操作cookie
# COOKIES_ENABLED = True
# COOKIES_DEBUG = True

# Disable Telnet Console (enabled by default)
# 9. Telnet用于查看当前爬虫的信息，操作爬虫等...
#    使用telnet ip port ，然后通过命令操作
# TELNETCONSOLE_ENABLED = True
# TELNETCONSOLE_HOST = '127.0.0.1'
# TELNETCONSOLE_PORT = [6023,]


# 10. 默认请求头
# Override the default request headers:
# DEFAULT_REQUEST_HEADERS = {
#     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#     'Accept-Language': 'en',
# }


# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
# 11. 定义pipeline处理请求
# ITEM_PIPELINES = {
#    'step8_king.pipelines.JsonPipeline': 700,
#    'step8_king.pipelines.FilePipeline': 500,
# }



# 12. 自定义扩展，基于信号进行调用
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#     # 'step8_king.extensions.MyExtension': 500,
# }


# 13. 爬虫允许的最大深度，可以通过meta查看当前深度；0表示无深度
# DEPTH_LIMIT = 3

# 14. 爬取时，0表示深度优先Lifo(默认)；1表示广度优先FiFo

# 后进先出，深度优先
# DEPTH_PRIORITY = 0
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleLifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.LifoMemoryQueue'
# 先进先出，广度优先

# DEPTH_PRIORITY = 1
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleFifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.FifoMemoryQueue'

# 15. 调度器队列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'
# from scrapy.core.scheduler import Scheduler


# 16. 访问URL去重
# DUPEFILTER_CLASS = 'step8_king.duplication.RepeatUrl'


# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html

"""
17. 自动限速算法
    from scrapy.contrib.throttle import AutoThrottle
    自动限速设置
    1. 获取最小延迟 DOWNLOAD_DELAY
    2. 获取最大延迟 AUTOTHROTTLE_MAX_DELAY
    3. 设置初始下载延迟 AUTOTHROTTLE_START_DELAY
    4. 当请求下载完成后，获取其"连接"时间 latency，即：请求连接到接受到响应头之间的时间
    5. 用于计算的... AUTOTHROTTLE_TARGET_CONCURRENCY
    target_delay = latency / self.target_concurrency
    new_delay = (slot.delay + target_delay) / 2.0 # 表示上一次的延迟时间
    new_delay = max(target_delay, new_delay)
    new_delay = min(max(self.mindelay, new_delay), self.maxdelay)
    slot.delay = new_delay
"""

# 开始自动限速
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# 初始下载延迟
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# 最大下载延迟
# AUTOTHROTTLE_MAX_DELAY = 10
# The average number of requests Scrapy should be sending in parallel to each remote server
# 平均每秒并发数
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:
# 是否显示
# AUTOTHROTTLE_DEBUG = True

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings


"""
18. 启用缓存
    目的用于将已经发送的请求或相应缓存下来，以便以后使用
    
    from scrapy.downloadermiddlewares.httpcache import HttpCacheMiddleware
    from scrapy.extensions.httpcache import DummyPolicy
    from scrapy.extensions.httpcache import FilesystemCacheStorage
"""
# 是否启用缓存策略
# HTTPCACHE_ENABLED = True

# 缓存策略：所有请求均缓存，下次在请求直接访问原来的缓存即可
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.DummyPolicy"
# 缓存策略：根据Http响应头：Cache-Control、Last-Modified 等进行缓存的策略
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"

# 缓存超时时间
# HTTPCACHE_EXPIRATION_SECS = 0

# 缓存保存路径
# HTTPCACHE_DIR = 'httpcache'

# 缓存忽略的Http状态码
# HTTPCACHE_IGNORE_HTTP_CODES = []

# 缓存存储的插件
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'


"""
19. 代理，需要在环境变量中设置
    from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
    
    方式一：使用默认
        os.environ
        {
            http_proxy:http://root:woshiniba@192.168.11.11:9999/
            https_proxy:http://192.168.11.11:9999/
        }
    方式二：使用自定义下载中间件
    
    def to_bytes(text, encoding=None, errors='strict'):
        if isinstance(text, bytes):
            return text
        if not isinstance(text, six.string_types):
            raise TypeError('to_bytes must receive a unicode, str or bytes '
                            'object, got %s' % type(text).__name__)
        if encoding is None:
            encoding = 'utf-8'
        return text.encode(encoding, errors)
        
    class ProxyMiddleware(object):
        def process_request(self, request, spider):
            PROXIES = [
                {'ip_port': '111.11.228.75:80', 'user_pass': ''},
                {'ip_port': '120.198.243.22:80', 'user_pass': ''},
                {'ip_port': '111.8.60.9:8123', 'user_pass': ''},
                {'ip_port': '101.71.27.120:80', 'user_pass': ''},
                {'ip_port': '122.96.59.104:80', 'user_pass': ''},
                {'ip_port': '122.224.249.122:8088', 'user_pass': ''},
            ]
            proxy = random.choice(PROXIES)
            if proxy['user_pass'] is not None:
                request.meta['proxy'] = to_bytes（"http://%s" % proxy['ip_port']）
                encoded_user_pass = base64.encodestring(to_bytes(proxy['user_pass']))
                request.headers['Proxy-Authorization'] = to_bytes('Basic ' + encoded_user_pass)
                print "**************ProxyMiddleware have pass************" + proxy['ip_port']
            else:
                print "**************ProxyMiddleware no pass************" + proxy['ip_port']
                request.meta['proxy'] = to_bytes("http://%s" % proxy['ip_port'])
    
    DOWNLOADER_MIDDLEWARES = {
       'step8_king.middlewares.ProxyMiddleware': 500,
    }
    
"""

"""
20. Https访问
    Https访问时有两种情况：
    1. 要爬取网站使用的可信任证书(默认支持)
        DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
        DOWNLOADER_CLIENTCONTEXTFACTORY = "scrapy.core.downloader.contextfactory.ScrapyClientContextFactory"
        
    2. 要爬取网站使用的自定义证书
        DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
        DOWNLOADER_CLIENTCONTEXTFACTORY = "step8_king.https.MySSLFactory"
        
        # https.py
        from scrapy.core.downloader.contextfactory import ScrapyClientContextFactory
        from twisted.internet.ssl import (optionsForClientTLS, CertificateOptions, PrivateCertificate)
        
        class MySSLFactory(ScrapyClientContextFactory):
            def getCertificateOptions(self):
                from OpenSSL import crypto
                v1 = crypto.load_privatekey(crypto.FILETYPE_PEM, open('/Users/wupeiqi/client.key.unsecure', mode='r').read())
                v2 = crypto.load_certificate(crypto.FILETYPE_PEM, open('/Users/wupeiqi/client.pem', mode='r').read())
                return CertificateOptions(
                    privateKey=v1,  # pKey对象
                    certificate=v2,  # X509对象
                    verify=False,
                    method=getattr(self, 'method', getattr(self, '_ssl_method', None))
                )
    其他：
        相关类
            scrapy.core.downloader.handlers.http.HttpDownloadHandler
            scrapy.core.downloader.webclient.ScrapyHTTPClientFactory
            scrapy.core.downloader.contextfactory.ScrapyClientContextFactory
        相关配置
            DOWNLOADER_HTTPCLIENTFACTORY
            DOWNLOADER_CLIENTCONTEXTFACTORY

"""



"""
21. 爬虫中间件
    class SpiderMiddleware(object):

        def process_spider_input(self,response, spider):
            '''
            下载完成，执行，然后交给parse处理
            :param response: 
            :param spider: 
            :return: 
            '''
            pass
    
        def process_spider_output(self,response, result, spider):
            '''
            spider处理完成，返回时调用
            :param response:
            :param result:
            :param spider:
            :return: 必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
            '''
            return result
    
        def process_spider_exception(self,response, exception, spider):
            '''
            异常调用
            :param response:
            :param exception:
            :param spider:
            :return: None,继续交给后续中间件处理异常；含 Response 或 Item 的可迭代对象(iterable)，交给调度器或pipeline
            '''
            return None
    
    
        def process_start_requests(self,start_requests, spider):
            '''
            爬虫启动时调用
            :param start_requests:
            :param spider:
            :return: 包含 Request 对象的可迭代对象
            '''
            return start_requests
    
    内置爬虫中间件：
        'scrapy.contrib.spidermiddleware.httperror.HttpErrorMiddleware': 50,
        'scrapy.contrib.spidermiddleware.offsite.OffsiteMiddleware': 500,
        'scrapy.contrib.spidermiddleware.referer.RefererMiddleware': 700,
        'scrapy.contrib.spidermiddleware.urllength.UrlLengthMiddleware': 800,
        'scrapy.contrib.spidermiddleware.depth.DepthMiddleware': 900,

"""
# from scrapy.contrib.spidermiddleware.referer import RefererMiddleware
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
   # 'step8_king.middlewares.SpiderMiddleware': 543,
}


"""
22. 下载中间件
    class DownMiddleware1(object):
        def process_request(self, request, spider):
            '''
            请求需要被下载时，经过所有下载器中间件的process_request调用
            :param request:
            :param spider:
            :return:
                None,继续后续中间件去下载；
                Response对象，停止process_request的执行，开始执行process_response
                Request对象，停止中间件的执行，将Request重新调度器
                raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
            '''
            pass
    
    
    
        def process_response(self, request, response, spider):
            '''
            spider处理完成，返回时调用
            :param response:
            :param result:
            :param spider:
            :return:
                Response 对象：转交给其他中间件process_response
                Request 对象：停止中间件，request会被重新调度下载
                raise IgnoreRequest 异常：调用Request.errback
            '''
            print('response1')
            return response
    
        def process_exception(self, request, exception, spider):
            '''
            当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
            :param response:
            :param exception:
            :param spider:
            :return:
                None：继续交给后续中间件处理异常；
                Response对象：停止后续process_exception方法
                Request对象：停止中间件，request将会被重新调用下载
            '''
            return None

    
    默认下载中间件
    {
        'scrapy.contrib.downloadermiddleware.robotstxt.RobotsTxtMiddleware': 100,
        'scrapy.contrib.downloadermiddleware.httpauth.HttpAuthMiddleware': 300,
        'scrapy.contrib.downloadermiddleware.downloadtimeout.DownloadTimeoutMiddleware': 350,
        'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': 400,
        'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': 500,
        'scrapy.contrib.downloadermiddleware.defaultheaders.DefaultHeadersMiddleware': 550,
        'scrapy.contrib.downloadermiddleware.redirect.MetaRefreshMiddleware': 580,
        'scrapy.contrib.downloadermiddleware.httpcompression.HttpCompressionMiddleware': 590,
        'scrapy.contrib.downloadermiddleware.redirect.RedirectMiddleware': 600,
        'scrapy.contrib.downloadermiddleware.cookies.CookiesMiddleware': 700,
        'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 750,
        'scrapy.contrib.downloadermiddleware.chunked.ChunkedTransferMiddleware': 830,
        'scrapy.contrib.downloadermiddleware.stats.DownloaderStats': 850,
        'scrapy.contrib.downloadermiddleware.httpcache.HttpCacheMiddleware': 900,
    }

"""
# from scrapy.contrib.downloadermiddleware.httpauth import HttpAuthMiddleware
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'step8_king.middlewares.DownMiddleware1': 100,
#    'step8_king.middlewares.DownMiddleware2': 500,
# }

 

5.TinyScrapy

#!/usr/bin/env python
# -*- coding:utf-8 -*-
import types
from twisted.internet import defer
from twisted.web.client import getPage
from twisted.internet import reactor



class Request(object):
    def __init__(self, url, callback):
        self.url = url
        self.callback = callback
        self.priority = 0


class HttpResponse(object):
    def __init__(self, content, request):
        self.content = content
        self.request = request


class ChouTiSpider(object):

    def start_requests(self):
        url_list = ['http://www.cnblogs.com/', 'http://www.bing.com']
        for url in url_list:
            yield Request(url=url, callback=self.parse)

    def parse(self, response):
        print(response.request.url)
        # yield Request(url="http://www.baidu.com", callback=self.parse)




from queue import Queue
Q = Queue()


class CallLaterOnce(object):
    def __init__(self, func, *a, **kw):
        self._func = func
        self._a = a
        self._kw = kw
        self._call = None

    def schedule(self, delay=0):
        if self._call is None:
            self._call = reactor.callLater(delay, self)

    def cancel(self):
        if self._call:
            self._call.cancel()

    def __call__(self):
        self._call = None
        return self._func(*self._a, **self._kw)


class Engine(object):
    def __init__(self):
        self.nextcall = None
        self.crawlling = []
        self.max = 5
        self._closewait = None

    def get_response(self,content, request):
        response = HttpResponse(content, request)
        gen = request.callback(response)
        if isinstance(gen, types.GeneratorType):
            for req in gen:
                req.priority = request.priority + 1
                Q.put(req)


    def rm_crawlling(self,response,d):
        self.crawlling.remove(d)

    def _next_request(self,spider):
        if Q.qsize() == 0 and len(self.crawlling) == 0:
            self._closewait.callback(None)

        if len(self.crawlling) >= 5:
            return
        while len(self.crawlling) < 5:
            try:
                req = Q.get(block=False)
            except Exception as e:
                req = None
            if not req:
                return
            d = getPage(req.url.encode('utf-8'))
            self.crawlling.append(d)
            d.addCallback(self.get_response, req)
            d.addCallback(self.rm_crawlling,d)
            d.addCallback(lambda _: self.nextcall.schedule())


    @defer.inlineCallbacks
    def crawl(self):
        spider = ChouTiSpider()
        start_requests = iter(spider.start_requests())
        flag = True
        while flag:
            try:
                req = next(start_requests)
                Q.put(req)
            except StopIteration as e:
                flag = False

        self.nextcall = CallLaterOnce(self._next_request,spider)
        self.nextcall.schedule()

        self._closewait = defer.Deferred()
        yield self._closewait

    @defer.inlineCallbacks
    def pp(self):
        yield self.crawl()

_active = set()
obj = Engine()
d = obj.crawl()
_active.add(d)

li = defer.DeferredList(_active)
li.addBoth(lambda _,*a,**kw: reactor.stop())

reactor.run()

点击下载

 更多文档参见：http://scrapy-chs.readthedocs.io/zh_CN/latest/index.html

scrapy-redis是一个基于redis的scrapy组件，通过它可以快速实现简单分布式爬虫程序，该组件本质上提供了三大功能：

• scheduler - 调度器
• dupefilter - URL去重规则（被调度器使用）
• pipeline   - 数据持久化

6.scrapy-redis组件

定义去重规则（被调度器调用并应用）
 
    a. 内部会使用以下配置进行连接Redis
 
        # REDIS_HOST = 'localhost'                            # 主机名
        # REDIS_PORT = 6379                                   # 端口
        # REDIS_URL = 'redis://user:pass@hostname:9001'       # 连接URL（优先于以上配置）
        # REDIS_PARAMS  = {}                                  # Redis连接参数             默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}）
        # REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块  默认：redis.StrictRedis
        # REDIS_ENCODING = "utf-8"                            # redis编码类型             默认：'utf-8'
     
    b. 去重规则通过redis的集合完成，集合的Key为：
     
        key = defaults.DUPEFILTER_KEY % {'timestamp': int(time.time())}
        默认配置：
            DUPEFILTER_KEY = 'dupefilter:%(timestamp)s'
              
    c. 去重规则中将url转换成唯一标示，然后在redis中检查是否已经在集合中存在
     
        from scrapy.utils import request
        from scrapy.http import Request
         
        req = Request(url='http://www.cnblogs.com/wupeiqi.html')
        result = request.request_fingerprint(req)
        print(result) # 8ea4fd67887449313ccc12e5b6b92510cc53675c
         
         
        PS:
            - URL参数位置不同时，计算结果一致；
            - 默认请求头不在计算范围，include_headers可以设置指定请求头
            示例：
                from scrapy.utils import request
                from scrapy.http import Request
                 
                req = Request(url='http://www.baidu.com?name=8&id=1',callback=lambda x:print(x),cookies={'k1':'vvvvv'})
                result = request.request_fingerprint(req,include_headers=['cookies',])
                 
                print(result)
                 
                req = Request(url='http://www.baidu.com?id=1&name=8',callback=lambda x:print(x),cookies={'k1':666})
                 
                result = request.request_fingerprint(req,include_headers=['cookies',])
                 
                print(result)
         
"""
# Ensure all spiders share same duplicates filter through redis.
# DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

"""
调度器，调度器使用PriorityQueue（有序集合）、FifoQueue（列表）、LifoQueue（列表）进行保存请求，并且使用RFPDupeFilter对URL去重
     
    a. 调度器
        SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'          # 默认使用优先级队列（默认），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表）
        SCHEDULER_QUEUE_KEY = '%(spider)s:requests'                         # 调度器中请求存放在redis中的key
        SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"                  # 对保存到redis中的数据进行序列化，默认使用pickle
        SCHEDULER_PERSIST = True                                            # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空
        SCHEDULER_FLUSH_ON_START = True                                     # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空
        SCHEDULER_IDLE_BEFORE_CLOSE = 10                                    # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。
        SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter'                  # 去重规则，在redis中保存时对应的key
        SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'# 去重规则对应处理的类
 
 
"""
# Enables scheduling storing requests queue in redis.
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
 
# Default requests serializer is pickle, but it can be changed to any module
# with loads and dumps functions. Note that pickle is not compatible between
# python versions.
# Caveat: In python 3.x, the serializer must return strings keys and support
# bytes as values. Because of this reason the json or msgpack module will not
# work by default. In python 2.x there is no such issue and you can use
# 'json' or 'msgpack' as serializers.
# SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"
 
# Don't cleanup redis queues, allows to pause/resume crawls.
# SCHEDULER_PERSIST = True
 
# Schedule requests using a priority queue. (default)
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'
 
# Alternative queues.
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.FifoQueue'
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.LifoQueue'
 
# Max idle time to prevent the spider from being closed when distributed crawling.
# This only works if queue class is SpiderQueue or SpiderStack,
# and may also block the same time when your spider start at the first time (because the queue is empty).
# SCHEDULER_IDLE_BEFORE_CLOSE = 10　　

2. 定义持久化，爬虫yield Item对象时执行RedisPipeline
     
    a. 将item持久化到redis时，指定key和序列化函数
     
        REDIS_ITEMS_KEY = '%(spider)s:items'
        REDIS_ITEMS_SERIALIZER = 'json.dumps'
     
    b. 使用列表保存item数据

"""
起始URL相关
 
    a. 获取起始URL时，去集合中获取还是去列表中获取？True，集合；False，列表
        REDIS_START_URLS_AS_SET = False    # 获取起始URL时，如果为True，则使用self.server.spop；如果为False，则使用self.server.lpop
    b. 编写爬虫时，起始URL从redis的Key中获取
        REDIS_START_URLS_KEY = '%(name)s:start_urls'
         
"""
# If True, it uses redis' ``spop`` operation. This could be useful if you
# want to avoid duplicates in your start urls list. In this cases, urls must
# be added via ``sadd`` command or you will get a type error from redis.
# REDIS_START_URLS_AS_SET = False
 
# Default start urls key for RedisSpider and RedisCrawlSpider.
# REDIS_START_URLS_KEY = '%(name)s:start_urls'

DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"


from scrapy_redis.scheduler import Scheduler
from scrapy_redis.queue import PriorityQueue
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'          # 默认使用优先级队列（默认），其他：PriorityQueue（有序集合），FifoQueue（列表）、LifoQueue（列表）
SCHEDULER_QUEUE_KEY = '%(spider)s:requests'                         # 调度器中请求存放在redis中的key
SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"                  # 对保存到redis中的数据进行序列化，默认使用pickle
SCHEDULER_PERSIST = True                                            # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空
SCHEDULER_FLUSH_ON_START = False                                    # 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空
SCHEDULER_IDLE_BEFORE_CLOSE = 10                                    # 去调度器中获取数据时，如果为空，最多等待时间（最后没数据，未获取到）。
SCHEDULER_DUPEFILTER_KEY = '%(spider)s:dupefilter'                  # 去重规则，在redis中保存时对应的key
SCHEDULER_DUPEFILTER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'# 去重规则对应处理的类



REDIS_HOST = '10.211.55.13'                           # 主机名
REDIS_PORT = 6379                                     # 端口
# REDIS_URL = 'redis://user:pass@hostname:9001'       # 连接URL（优先于以上配置）
# REDIS_PARAMS  = {}                                  # Redis连接参数             默认：REDIS_PARAMS = {'socket_timeout': 30,'socket_connect_timeout': 30,'retry_on_timeout': True,'encoding': REDIS_ENCODING,}）
# REDIS_PARAMS['redis_cls'] = 'myproject.RedisClient' # 指定连接Redis的Python模块  默认：redis.StrictRedis
REDIS_ENCODING = "utf-8"                              # redis编码类型             默认：'utf-8'

import scrapy


class ChoutiSpider(scrapy.Spider):
    name = "chouti"
    allowed_domains = ["chouti.com"]
    start_urls = (
        'http://www.chouti.com/',
    )

    def parse(self, response):
        for i in range(0,10):
            yield