爬虫模块之selenium模块

2023-08-10 23:19:28

一模块的介绍

　selenium模块最开始是一个自动化测试的工具，驱动浏览器完全模拟浏览器自动测试。

from selenium import webdriver  # 驱动浏览器

browser=webdriver.Chrome()  # 谷歌浏览器

browser=webdriver.Firefox()   # 火狐浏览器

browser=webdriver.PhantomJS()  # 虚拟浏览器

browser=webdriver.Safari()

browser=webdriver.Edge()

二下载安装

#安装：selenium+chromedriver

pip3 install selenium

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2.29，并非2.9

国内镜像网站地址：http://npm.taobao.org/mirrors/chromedriver/2.29/

最新的版本去官网找:https://sites.google.com/a/chromium.org/chromedriver/downloads

#验证安装

C:\Users\Administrator>python3

Python 3.6.1 (v3.6.1:69c0db5, Mar 21 2017, 18:41:36) [MSC v.1900 64 bit (AMD64)] on win32

Type "help", "copyright", "credits" or "license" for more information.

>>> from selenium import webdriver

>>> driver=webdriver.Chrome() #弹出浏览器

>>> driver.get('https://www.baidu.com')

>>> driver.page_source

#注意：

selenium3默认支持的webdriver是Firfox，而Firefox需要安装geckodriver

下载链接：https://github.com/mozilla/geckodriver/releases

#安装：selenium+phantomjs

pip3 install selenium

下载phantomjs，解压后把phantomjs.exe所在的bin目录放到环境变量

下载链接：http://phantomjs.org/download.html

#验证安装

C:\Users\Administrator>phantomjs

phantomjs> console.log('egon gaga')

egon gaga

undefined

phantomjs> ^C

C:\Users\Administrator>python3

Python 3.6.1 (v3.6.1:69c0db5, Mar 21 2017, 18:41:36) [MSC v.1900 64 bit (AMD64)] on win32

Type "help", "copyright", "credits" or "license" for more information.

>>> from selenium import webdriver

>>> driver=webdriver.PhantomJS() #*面浏览器

>>> driver.get('https://www.baidu.com')

>>> driver.page_source

三基本使用

　ActionChains：拖动的一些事。

　expected_conditions：加载的时间设置

　find_element_by_id：id查找的方式。

　send_keys：发送查找的关键字

　click：点击事件

　current_url：获取正在驱动的url

　get_cookies：获取cookies信息

　page_source：页面源代码

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()

try:

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

    input_tag=browser.find_element_by_id('kw')

    input_tag.send_keys('美女') #python2中输入中文错误，字符串前加个u

    input_tag.send_keys(Keys.ENTER) #输入回车

    wait=WebDriverWait(browser,10)

    wait.until(EC.presence_of_element_located((By.ID,'content_left'))) #等到id为content_left的元素加载完毕,最多等10秒

    print(browser.page_source)

    print(browser.current_url)

    print(browser.get_cookies())

finally:

    browser.close()

四选择器

　基本选择器查找：　

　find_element_by_id：根据ID查找

　find_element_by_link_text：通过文本查找

　find_element_by_partial_link_text：根据某些文本模糊查找到第一个内容

　find_element_by_class_name：通过class查找

　find_element_by_name：通过name属性查找

　　补充：

　　presence_of_all_elements_located：相对应的所有元素加载完毕过后

　　presence_of_element_located：查找到第一个加载完毕后

　　element_to_be_clickable：等待可以点击过后。

　　By.CLASS_NAME：class查找的方式

　　get_attribute：访问标签的属性

　　text：访问文本

　　tag_name：访问name

# 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

# import time

#

# try:

#     '''

#     find_element_by_id

#     find_element_by_name

#     find_element_by_link_text

#     find_element_by_partial_link_text

#     find_element_by_tag_name

#     find_element_by_class_name

#

#     find_element_by_css_selector

#     find_element_by_xpath

#     '''

#     driver = webdriver.Chrome()

#     wait=WebDriverWait(driver,3)

#     driver.get('https://www.baidu.com/')

#

#     # 1、find_element_by_id

#     # input_tag=driver.find_element_by_id('kw')

#     # print(input_tag.tag_name)

#     # print(input_tag.get_attribute('name'))

#     # print(input_tag.text)

#

#     # 2、find_element_by_link_text

#     # login=driver.find_element_by_link_text('登录')

#     # login.click()

#

#     # 3、find_element_by_partial_link_text

#     login=driver.find_element_by_partial_link_text('登')

#     login.click()

#

#     # 4、find_element_by_class_name

#     # login_for_user=driver.find_element_by_class_name('tang-pass-footerBarULogin')

#     # login_for_user=wait.until(EC.presence_of_element_located((By.CLASS_NAME,'tang-pass-footerBarULogin')))

#     login_for_user=wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'tang-pass-footerBarULogin')))

#     # print(login_for_user)

#     login_for_user.click()

#

#

#     #4、find_element_by_name

#     # input_user=driver.find_element_by_name('userName')

#     # input_pwd=driver.find_element_by_name('password')

#     # button=driver.find_element_by_id('TANGRAM__PSP_10__submit')

#     #

#     # input_user.send_keys('17094322519')

#     # input_pwd.send_keys('11111111111')

#     # button.click()

#

#

#

#     time.sleep(5)

# finally:

#     driver.close()

　以上这些只能够查找出来一个内容，如果想要加载相关的所有内容，将有血查找方式的element改成elements就可以了。如下

    find_elements_by_name

    find_elements_by_xpath

    find_elements_by_link_text

    find_elements_by_partial_link_text

    find_elements_by_tag_name

    find_elements_by_class_name

    find_elements_by_css_selector

　find_element（s）_by_xpath：如果在没有一个合适定位的方式的时候就可以使用这个

　　/：单斜杠，查找一个标签，可以从根标签一层一层的向内部查找。

　　//：双斜杠，从当前页面查找出相对用的所有的标签。

　　[数字]：确定查找到哪一个标签。

　　[@属性=“属性值”]：属性的查找方式

　　[locntains(@属性=“属性值的部分内容”)]：属性模糊查找

　　//*：所有的标签

　　[标签/@属性=“属性值”]：查找有这个标签的标签的值

　　..：两个点，代表的是上一级

#Xpath选择器

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

import time

try:

    driver = webdriver.Chrome()

    # wait = WebDriverWait(driver, 3)

    driver.implicitly_wait(3)

    driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html')

    #1、//与/

    # tag=driver.find_element_by_xpath('/html/body/div/a')

    # print(tag.tag_name)

    # print(tag.text)

    # print(tag.get_attribute('href'))

    # tag=driver.find_elements_by_xpath('//a')

    # print(tag)

    # tag=driver.find_elements_by_xpath('//div//a')

    # tag=driver.find_elements_by_css_selector('div a')

    # print(len(tag))

    #2、查找第几个

    # tag=driver.find_elements_by_xpath('//div//a[5]')

    # print(tag[0].text)

    #3、按照属性查找

    # tag1=driver.find_element_by_xpath('//a[@href="image4.html"]')

    # tag2=driver.find_element_by_xpath('//a[4]')

    # tag3=driver.find_element_by_xpath('//a[contains(@href,"image4")]')

    #

    # print(tag1.text)

    # print(tag2.text)

    # print(tag3.text)

    #4、其他

    # driver.find_elements_by_xpath('//*[@class="xxxxx"]')

    # driver.find_elements_by_xpath('//div[@class="xxxxx"][@class="yyyyy"]')

    # print(driver.find_element_by_xpath('//a[img/@src="data:image2_thumb.jpg"]').text)

    # print(driver.find_element_by_xpath('//a/..').tag_name)

    # print([tag.tag_name for tag in driver.find_elements_by_xpath('//img//..')])

    img=driver.find_element_by_xpath('//img')

    print(img.location)

    print(img.size)

    time.sleep(5)

finally:

    driver.close()

五交互操作

　location：坐标，横：x；竖：y

　size：大小，也就是内容的长宽

　impicitly_wait：隐式等待。

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()

　显式等待：

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()

　execute_script：直接写js代码

　clear：清空输入框

　iframe：在一个页面中嵌套一个页面

　switch_to.frame：切换到子页面

　awitch_to.parent_frame：切换到父页面

　Action chains（浏览器对象）：拖动

　drag_aand_drop（源，目标）：从源拖动到目标

　perform（）：开始执行

　click_and_hold：点击不松手

　move_by_offset：偏移量

　release：松开鼠标

# 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

# import time

#

#

# try:

#     driver=webdriver.Chrome()

#     driver.get('https://www.jd.com/')

#     driver.implicitly_wait(3)

#

#     input_tag=driver.find_element_by_id('key')

#     input_tag.send_keys('iphoneX')

#     input_tag.send_keys(Keys.ENTER)

#

#     time.sleep(3)

#     input_tag = driver.find_element_by_id('key')

#     input_tag.clear()

#     input_tag.send_keys('mac pro')

#     input_tag.send_keys(Keys.ENTER)

#

#

#     time.sleep(5)

# finally:

#     driver.close()

#ActionChains

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

import time

try:

    driver=webdriver.Chrome()

    driver.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')

    driver.implicitly_wait(3)

    driver.execute_script('alert("hahha")')

    # driver.switch_to.frame('iframeResult')

    # driver.switch_to.parent_frame()

    # 方式一：基于一条链，从头一下移动到尾部

    # source = driver.find_element_by_id('draggable')

    # target = driver.find_element_by_id('droppable')

    # actions=ActionChains(driver)

    # actions.drag_and_drop(source,target)

    # actions.perform()

    # 方式二：基于不同ActionChains，可以控制移动的位移

    # source = driver.find_element_by_id('draggable')

    # target = driver.find_element_by_id('droppable')

    # distance=target.location['x'] - source.location['x']

    #

    # ActionChains(driver).click_and_hold(source).perform()

    # ActionChains(driver).move_by_offset(xoffset=distance,yoffset=0).perform()

    # ActionChains(driver).release().perform()

    #

    # res=0

    # while res < distance:

    #     ActionChains(driver).move_by_offset(xoffset=1,yoffset=0).perform()

    #     res+=1

    # ActionChains(driver).release().perform()

    #

    time.sleep(5)

finally:

    driver.close()

六浏览器的前进和后退：

　back：后退

　forword：前进

#浏览器的前进后退

# import time

# from selenium import webdriver

#

# browser=webdriver.Chrome()

# browser.get('https://www.baidu.com')

# browser.get('https://www.taobao.com')

# browser.get('http://www.python.org/')

#

# time.sleep(3)

# browser.back()

# time.sleep(3)

# browser.forward()

# browser.close()

七 cookies

　get_cookies：获取cookies里面的信息。

#cookies

from selenium import webdriver

browser=webdriver.Chrome()

browser.get('https://www.zhihu.com/explore')

print(browser.get_cookies())

browser.add_cookie({'k1':'xxx','k2':'yyy'})

print(browser.get_cookies())

# browser.delete_all_cookies()

八异常处理

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()

九选项卡管理

#选项卡管理：切换选项卡，有js的方式windows.open,有windows快捷键：ctrl+t等，最通用的就是js的方式

import time

from selenium import webdriver

browser=webdriver.Chrome()

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

browser.execute_script('window.open()')

print(browser.window_handles) #获取所有的选项卡

browser.switch_to.window(browser.window_handles[1])

browser.get('https://www.taobao.com')

time.sleep(10)

browser.switch_to.window(browser.window_handles[0])

browser.get('https://www.sina.com.cn')

browser.close()

十练习

#注意：网站都策略都是在不断变化的，精髓在于学习流程。下述代码生效与2017-11-7，不能保证永久有效

from selenium import webdriver

from selenium.webdriver import ActionChains

from selenium.webdriver.common.by import By

from selenium.webdriver.common.keys import Keys

from selenium.webdriver.support import expected_conditions as EC

from selenium.webdriver.support.wait import WebDriverWait

browser=webdriver.Chrome()

try:

    browser.get('http://mail.163.com/')

    wait=WebDriverWait(browser,5)

    frame=wait.until(EC.presence_of_element_located((By.ID,'x-URS-iframe')))

    browser.switch_to.frame(frame)

    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'.m-container')))

    inp_user=browser.find_element_by_name('email')

    inp_pwd=browser.find_element_by_name('password')

    button=browser.find_element_by_id('dologin')

    inp_user.send_keys('')

    inp_pwd.send_keys('xxxx')

    button.click()

    #如果遇到验证码，可以把下面一小段打开注释

    # import time

    # time.sleep(10)

    # button = browser.find_element_by_id('dologin')

    # button.click()

    wait.until(EC.presence_of_element_located((By.ID,'dvNavTop')))

    write_msg=browser.find_elements_by_css_selector('#dvNavTop li')[1] #获取第二个li标签就是“写信”了

    write_msg.click()

    wait.until(EC.presence_of_element_located((By.CLASS_NAME,'tH0')))

    recv_man=browser.find_element_by_class_name('nui-editableAddr-ipt')

    title=browser.find_element_by_css_selector('.dG0 .nui-ipt-input')

    recv_man.send_keys('378533872@qq.com')

    title.send_keys('圣旨')

    print(title.tag_name)

    frame=wait.until(EC.presence_of_element_located((By.CLASS_NAME,'APP-editor-iframe')))

    browser.switch_to.frame(frame)

    body=browser.find_element(By.CSS_SELECTOR,'body')

    body.send_keys('egon很帅，可以加工资了')

    browser.switch_to.parent_frame() #切回他爹

    send_button=browser.find_element_by_class_name('nui-toolbar-item')

    send_button.click()

    #可以睡时间久一点别让浏览器关掉，看看发送成功没有

    import time

    time.sleep(10000)

except Exception as e:

    print(e)

finally:

    browser.close()

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

import time

def get_goods(driver):

    try:

        goods=driver.find_elements_by_class_name('gl-item')

        for good in goods:

            detail_url=good.find_element_by_tag_name('a').get_attribute('href')

            p_name=good.find_element_by_css_selector('.p-name em').text.replace('\n','')

            price=good.find_element_by_css_selector('.p-price i').text

            p_commit=good.find_element_by_css_selector('.p-commit a').text

            msg = '''

            商品 : %s

            链接 : %s

            价钱 ：%s

            评论 ：%s

            ''' % (p_name,detail_url,price,p_commit)

            print(msg,end='\n\n')

        button=driver.find_element_by_partial_link_text('下一页')

        button.click()

        time.sleep(1)

        get_goods(driver)

    except Exception:

        pass

def spider(url,keyword):

    driver = webdriver.Chrome()

    driver.get(url)

    driver.implicitly_wait(3)  # 使用隐式等待

    try:

        input_tag=driver.find_element_by_id('key')

        input_tag.send_keys(keyword)

        input_tag.send_keys(Keys.ENTER)

        get_goods(driver)

    finally:

        driver.close()

if __name__ == '__main__':

    spider('https://www.jd.com/',keyword='iPhone8手机')

#coding=utf-8

from selenium import webdriver

# from selenium import fire

from selenium.webdriver.common.keys import Keys

import re

from selenium.webdriver.support.ui import Select

import time

from pyquery import PyQuery as pq

from xlwt import *

import calendar

from collections import OrderedDict

def openurl(num):

    browser = webdriver.Chrome(executable_path=r"H:\chromedriver_win32\chromedriver.exe")

    browser.get("https://finsix.com/#section-compatibility")

    html = browser.page_source  # 获取网站源码

    data = browser.page_source  # str() 函数将对象转化为适于人阅读的形式。

    lis = [['product','version','title','status','tags','info']]

    re_rule_1 = r'<select class="section-compatibility__manufacturers select2-hidden-accessible" tabindex="-1" aria-hidden="true">(.*?)</select>'

    data_list = re.findall(re_rule_1,data, re.S)

    data = data_list[0]

    re_rule = r'<option value=".*?">(.*?)</option>'

    datalist = re.findall(re_rule, data, re.S)

    print datalist

    for i in range(1, len(datalist)):

        try:

            browser.find_element_by_class_name('select2-selection__arrow').click()

        except :

            browser.find_element_by_class_name('section-compatibility__message__close').click()

            browser.find_element_by_class_name('select2-selection__arrow').click()

        s1 = Select(browser.find_element_by_class_name('section-compatibility__manufacturers'))

        s2 = s1.options[i]

        # s1.select_by_index(i)

        s3= s2.text

        print s3

        s2.click()

        try:

            browser.find_element_by_class_name('select2-selection__arrow').click()

        except :

            browser.find_element_by_class_name('section-compatibility__message__close').click()

            browser.find_element_by_class_name('select2-selection__arrow').click()

            s2.click()

            browser.find_element_by_class_name('select2-selection__arrow').click()

        time.sleep(2)

        rule1 = r'<select class="section-compatibility__models select2-hidden-accessible" tabindex="-1" aria-hidden="true">(.*?)</select>'

        data = browser.page_source

        if '<select class="section-compatibility__models select2-hidden-accessible" tabindex="-1" aria-hidden="true">' not in data:

            rule1 =  '<select class="section-compatibility__models select2-hidden-accessible" disabled="" tabindex="-1" aria-hidden="true">(.*?)</select>'

        bullish = re.findall(rule1,data , re.S)

        # print len(bullish),bullish

        if len(bullish)>0:

            bullish = bullish[0]

        else:

            print len(bullish), bullish

            lis.append([s3,'','','','',''])

            continue

        re_rule = r'<option value=".*?">(.*?)</option>'

        bullish = re.findall(re_rule, bullish, re.S)

        print bullish

        for j in range(0,len(bullish)):

            btn = browser.find_elements_by_class_name('select2-selection')

            try:

                btn[1].click()

            except :

                try:

                    browser.find_element_by_class_name('section-compatibility__message__close').click()

                    btn[1].click()

                except:

                    # btn[1].click()

                    browser.find_element_by_class_name('section-compatibility__message__close').click()

                    btn[1].click()

            s4=Select(browser.find_element_by_class_name('section-compatibility__models'))

            s5 = s4.options[j]

            s6=s5.text

            print s6

            s5.click()

            try:

                btn[1].click()

            except:

                try:

                    browser.find_element_by_class_name('section-compatibility__message__close').click()

                    btn[1].click()

                except:

                    hdata = browser.page_source

                    try:

                        t = browser.find_element_by_class_name('section-compatibility__message__title').text

                    except:

                        t = ''

                    print t

                    b1 = r'<div class="section-compatibility__message__tip"> <strong>(.*?): </strong><span>(.*?)</span> </div>'

                    bk = re.findall(b1, hdata, re.S)

                    print bk

                    try:

                        status = bk[0][0]

                    except:

                        status = ''

                    try:

                        tag = bk[0][1]

                    except:

                        tag = ''

                    # i1 = r'<div class="section-compatibility__message__body"><p>(.*?)</p>.*?</div>'

                    # info = re.findall(i1,hdata,re.S)

                    try:

                        info = browser.find_element_by_class_name(

                            'section-compatibility__message__body').find_element_by_tag_name('p').text

                    except:

                        info = ''

                    print info

                    lis.append([s3, s6, t, status, tag, info])

                    continue

            hdata = browser.page_source

            try:

                t = browser.find_element_by_class_name('section-compatibility__message__title').text

            except:

                t=''

            print t

            b1 =  r'<div class="section-compatibility__message__tip"> <strong>(.*?): </strong><span>(.*?)</span> </div>'

            bk = re.findall(b1,hdata,re.S)

            print bk

            try:

                status = bk[0][0]

            except:status=''

            try:

                tag = bk[0][1]

            except:tag=''

            # i1 = r'<div class="section-compatibility__message__body"><p>(.*?)</p>.*?</div>'

            # info = re.findall(i1,hdata,re.S)

            try:

                info = browser.find_element_by_class_name('section-compatibility__message__body').find_element_by_tag_name('p').text

            except:info=''

            print info

            lis.append([s3,s6,t,status, tag,info])

            try:

                browser.find_element_by_class_name('section-compatibility__message__close').click()

            except:

                # btn[1].click()

                try:

                    browser.find_element_by_class_name('section-compatibility__message__close').click()

                except:

                    try:

                        btn[1].click()

                        s5.click()

                        btn[1].click()

                        browser.find_element_by_class_name('section-compatibility__message__close').click()

                    except:

                        continue

    return lis

def zhizuo(lis):

    file = Workbook(encoding='utf-8')

    table = file.add_sheet('data')

    for i, p in enumerate(lis):

        for j, q in enumerate(p):

            table.write(i, j, q)

    file.save( 'product_info.csv')

    return 'success'

url = 'https://www.xuangubao.cn/'

lis = openurl(3)

print(lis)

zhizuo(lis)

# f=open("F:\\text.txt","a")

# for key,values in  dict.items():

# f.write((key+"\t"))

# print(key,values)

# f.close()

爬取finsix

破解滑动验证：

　http://www.cnblogs.com/fangjie0410/p/8269219.html

码农公寓

相关文章