Python爬蟲學(xué)習(xí)教程：天貓商品數(shù)據(jù)爬蟲

# -*- coding: utf-8 -*-
from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver import ActionChainsfrom pyquery import PyQuery as pqfrom time import sleep

#定義一個(gè)taobao類class taobao_infos:
    #對(duì)象初始化    def __init__(self):        url = 'https://login.taobao.com/member/login.jhtml'        self.url = url
        options = webdriver.ChromeOptions()        options.add_experimental_option("prefs", {"profile.managed_default_content_settings.images": 2}) # 不加載圖片,加快訪問速度        options.add_experimental_option('excludeSwitches', ['enable-automation']) # 此步驟很重要，設(shè)置為開發(fā)者模式，防止被各大網(wǎng)站識(shí)別出來使用了Selenium
        self.browser = webdriver.Chrome(executable_path=chromedriver_path, options=options)        self.wait = WebDriverWait(self.browser, 10) #超時(shí)時(shí)長為10s

    #延時(shí)操作,并可選擇是否彈出窗口提示    def sleep_and_alert(self,sec,message,is_alert):
        for second in range(sec):            if(is_alert):                alert = "alert(\"" + message + ":" + str(sec - second) + "秒\")"                self.browser.execute_script(alert)                al = self.browser.switch_to.alert                sleep(1)                al.accept()            else:                sleep(1)

    #登錄淘寶    def login(self):
        # 打開網(wǎng)頁        self.browser.get(self.url)
        # 自適應(yīng)等待，點(diǎn)擊密碼登錄選項(xiàng)        self.browser.implicitly_wait(30) #智能等待，直到網(wǎng)頁加載完畢，最長等待時(shí)間為30s        self.browser.find_element_by_xpath('//*[@class="forget-pwd J_Quick2Static"]').click()
        # 自適應(yīng)等待，點(diǎn)擊微博登錄宣傳        self.browser.implicitly_wait(30)        self.browser.find_element_by_xpath('//*[@class="weibo-login"]').click()
        # 自適應(yīng)等待，輸入微博賬號(hào)        self.browser.implicitly_wait(30)        self.browser.find_element_by_name('username').send_keys(weibo_username)
        # 自適應(yīng)等待，輸入微博密碼        self.browser.implicitly_wait(30)        self.browser.find_element_by_name('password').send_keys(weibo_password)
        # 自適應(yīng)等待，點(diǎn)擊確認(rèn)登錄按鈕        self.browser.implicitly_wait(30)        self.browser.find_element_by_xpath('//*[@class="btn_tip"]/a/span').click()
        # 直到獲取到淘寶會(huì)員昵稱才能確定是登錄成功        taobao_name = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.site-nav-bd > ul.site-nav-bd-l > li#J_SiteNavLogin > div.site-nav-menu-hd > div.site-nav-user > a.site-nav-login-info-nick ')))        # 輸出淘寶昵稱        print(taobao_name.text)



    # 獲取天貓商品總共的頁數(shù)    def search_toal_page(self):
        # 等待本頁面全部天貓商品數(shù)據(jù)加載完畢        good_total = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#J_ItemList > div.product > div.product-iWrap')))
        #獲取天貓商品總共頁數(shù)        number_total = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.ui-page > div.ui-page-wrap > b.ui-page-skip > form')))        page_total = number_total.text.replace("共","").replace("頁，到第頁 確定","").replace("，","")
        return page_total

    # 翻頁操作    def next_page(self, page_number):        # 等待該頁面input輸入框加載完畢        input = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.ui-page > div.ui-page-wrap > b.ui-page-skip > form > input.ui-page-skipTo')))
        # 等待該頁面的確定按鈕加載完畢        submit = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.ui-page > div.ui-page-wrap > b.ui-page-skip > form > button.ui-btn-s')))
        # 清除里面的數(shù)字        input.clear()
        # 重新輸入數(shù)字        input.send_keys(page_number)
        # 強(qiáng)制延遲1秒，防止被識(shí)別成機(jī)器人        sleep(1)
        # 點(diǎn)擊確定按鈕        submit.click()

    # 模擬向下滑動(dòng)瀏覽    def swipe_down(self,second):        for i in range(int(second/0.1)):            js = "var q=document.documentElement.scrollTop=" + str(300+200*i)            self.browser.execute_script(js)            sleep(0.1)        js = "var q=document.documentElement.scrollTop=100000"        self.browser.execute_script(js)        sleep(0.2)

    # 爬取天貓商品數(shù)據(jù)    def crawl_good_data(self):
        # 對(duì)天貓商品數(shù)據(jù)進(jìn)行爬蟲        self.browser.get("https://list.tmall.com/search_product.htm?q=羽毛球")        err1 = self.browser.find_element_by_xpath("http://*[@id='content']/div/div[2]").text        err1 = err1[:5]        if(err1 == "喵~沒找到"):            print("找不到您要的")            return        try:            self.browser.find_element_by_xpath("http://*[@id='J_ComboRec']/div[1]")            err2 = self.browser.find_element_by_xpath("http://*[@id='J_ComboRec']/div[1]").text            #print(err2)                        err2 = err2[:5]
            if(err2 == "我們還為您"):                print("您要查詢的商品書目太少了")                return        except:            print("可以爬取這些信息")        # 獲取天貓商品總共的頁數(shù)        page_total = self.search_toal_page()        print("總共頁數(shù)" + page_total)
        # 遍歷所有頁數(shù)        for page in range(2,int(page_total)):
            # 等待該頁面全部商品數(shù)據(jù)加載完畢            good_total = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#J_ItemList > div.product > div.product-iWrap')))
            # 等待該頁面input輸入框加載完畢            input = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.ui-page > div.ui-page-wrap > b.ui-page-skip > form > input.ui-page-skipTo')))
            # 獲取當(dāng)前頁            now_page = input.get_attribute('value')            print("當(dāng)前頁數(shù)" + now_page + ",總共頁數(shù)" + page_total)
            # 獲取本頁面源代碼            html = self.browser.page_source
            # pq模塊解析網(wǎng)頁源代碼            doc = pq(html)
            # 存儲(chǔ)天貓商品數(shù)據(jù)            good_items = doc('#J_ItemList .product').items()
            # 遍歷該頁的所有商品            for item in good_items:                good_title = item.find('.productTitle').text().replace('\n',"").replace('\r',"")                good_status = item.find('.productStatus').text().replace(" ","").replace("筆","").replace('\n',"").replace('\r',"")                good_price = item.find('.productPrice').text().replace("￥", "").replace(" ", "").replace('\n', "").replace('\r', "")                good_url = item.find('.productImg').attr('href')                print(good_title + "   " + good_status + "   " + good_price + "   " + good_url + '\n')

            # 精髓之處，大部分人被檢測為機(jī)器人就是因?yàn)檫M(jìn)一步模擬人工操作            # 模擬人工向下瀏覽商品，即進(jìn)行模擬下滑操作，防止被識(shí)別出是機(jī)器人            self.swipe_down(2)
            # 翻頁，下一頁            self.next_page(page)
            # 等待滑動(dòng)驗(yàn)證碼出現(xiàn),超時(shí)時(shí)間為5秒，每0.5秒檢查一次            # 大部分情況不會(huì)出現(xiàn)滑動(dòng)驗(yàn)證碼，所以如果有需要可以注釋掉下面的代碼            # sleep(5)            WebDriverWait(self.browser, 5, 0.5).until(EC.presence_of_element_located((By.ID, "nc_1_n1z"))) #等待滑動(dòng)拖動(dòng)控件出現(xiàn)            try:                swipe_button = self.browser.find_element_by_id('nc_1_n1z') #獲取滑動(dòng)拖動(dòng)控件
                #模擬拽托                action = ActionChains(self.browser) # 實(shí)例化一個(gè)action對(duì)象                action.click_and_hold(swipe_button).perform() # perform()用來執(zhí)行ActionChains中存儲(chǔ)的行為                action.reset_actions()                action.move_by_offset(580, 0).perform() # 移動(dòng)滑塊
            except Exception as e:                print ('get button failed: ', e)

if __name__ == "__main__":
    # 使用之前請(qǐng)先查看當(dāng)前目錄下的使用說明文件README.MD    # 使用之前請(qǐng)先查看當(dāng)前目錄下的使用說明文件README.MD    # 使用之前請(qǐng)先查看當(dāng)前目錄下的使用說明文件README.MD
    chromedriver_path = "/Users/bird/Desktop/chromedriver.exe" #改成你的chromedriver的完整路徑地址    weibo_username = "改成你的微博賬號(hào)" #改成你的微博賬號(hào)    weibo_password = "改成你的微博密碼" #改成你的微博密碼
    a = taobao_infos()    a.login() #登錄    a.crawl_good_data() #爬取天貓商品數(shù)據(jù)