python獲取阿里巴巴國際站商家信息

from selenium.webdriver import ChromeOptionsfrom selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.support.wait import WebDriverWaitimport reimport timefrom lxml import etreeimport csv

# 完成登錄 登陸class Chrome_drive():    def __init__(self):
        option = ChromeOptions()        option.add_experimental_option('excludeSwitches', ['enable-automation'])        option.add_experimental_option('useAutomationExtension', False)        NoImage = {"profile.managed_default_content_settings.images": 2}  # 控制 沒有圖片        option.add_experimental_option("prefs", NoImage)        # option.add_argument(f'user-agent={ua.chrome}')  # 增加瀏覽器頭部        # chrome_options.add_argument(f"--proxy-server=http://{self.ip}")  # 增加IP地址。。        # option.add_argument('--headless')  #無頭模式 不彈出瀏覽器        self.browser = webdriver.Chrome(executable_path="./chromedriver", options=option)        self.browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument', {            'source': 'Object.defineProperty(navigator,"webdriver",{get:()=>undefined})'        })  #去掉selenium的驅(qū)動(dòng)設(shè)置
        self.browser.set_window_size(1200,768)        self.wait = WebDriverWait(self.browser, 12)
    def get_login(self):        url='https://passport.alibaba.com/icbu_login.htm'
        self.browser.get(url)        #self.browser.maximize_window()  # 在這里登陸的中國大陸的郵編        #這里進(jìn)行人工登陸。        k = input("輸入1")        if 'Your Alibaba.com account is temporarily unavailable' in self.browser.page_source:            self.browser.close()        while k == 1:            break        self.browser.refresh()  # 刷新方法 refres        return

#獲取判斷網(wǎng)頁文本的內(nèi)容：    def index_page(self,page,wd):        """        抓取索引頁        :param page: 頁碼        """        print('正在爬取第', page, '頁')
        url = f'https://www.alibaba.com/trade/search?page={page}&keyword={wd}&f1=y&indexArea=company_en&viewType=L&n=38'        js1 = f" window.open('{url}')"  # 執(zhí)行打開新的標(biāo)簽頁        print(url)        self.browser.execute_script(js1)  # 打開新的網(wǎng)頁標(biāo)簽            # 執(zhí)行打開新一個(gè)標(biāo)簽頁。        self.browser.switch_to.window(self.browser.window_handles[-1])  # 此行代碼用來定位當(dāng)前頁面窗口        self.buffer()  # 網(wǎng)頁滑動(dòng)  成功切換            #等待元素加載出來        time.sleep(3)
        self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#J-items-content')))            #獲取網(wǎng)頁的源代碼        html =  self.browser.page_source
        self.get_products(wd,html)
        self.close_window()
    def get_products(self, wd, html_text):        """        提取商品數(shù)據(jù)        """        e = etree.HTML(html_text)        item_main = e.xpath('//div[@id="J-items-content"]//div[@class="item-main"]')        items = e.xpath('//div[@id="J-items-content"]//div[@class="item-main"]')        print('公司數(shù) ', len(items))        for li in items:            company_name = ''.join(li.xpath('./div[@class="top"]//h2[@class="title ellipsis"]/a/text()'))  # 公司名稱            company_phone_page = ''.join(li.xpath('./div[@class="top"]//a[@class="cd"]/@href'))  # 公司電話連接            product = ''.join(li.xpath('.//div[@class="value ellipsis ph"]/text()'))  # 主要產(chǎn)品            Attrs = li.xpath('.//div[@class="attrs"]//span[@class="ellipsis search"]/text()')            length = len(Attrs)            counctry = ''            total_evenue = ''            sell_adress = ''            product_img = ''            if length > 0:                counctry = ''.join(Attrs[0])  # 國家            if length > 1:                total_evenue = ''.join(Attrs[1])  # Total 收入            if length > 2:                sell_adress = ''.join(Attrs[2])  # 主要銷售地            if length > 3:                sell_adress += '、' + ''.join(Attrs[3])  # 主要銷售地            if length > 4:                sell_adress += '、' + ''.join(Attrs[4])  # 主要銷售地            product_img_list = li.xpath('.//div[@class="product"]/div/a/img/@src')            if len(product_img_list) > 0:                product_img = ','.join(product_img_list)  # 產(chǎn)品圖片            self.browser.get(company_phone_page)            phone = ''            address = ''            mobilePhone = ''            try:                if 'Your Alibaba.com account is temporarily unavailable' in self.browser.page_source:                    self.browser.close()                self.browser.find_element_by_xpath('//div[@class="sens-mask"]/a').click()                phone = ''.join(re.findall('Telephone:(.*?)', self.browser.page_source, re.S))                mobilePhone = ''.join(re.findall('Mobile Phone:(.*?)', self.browser.page_source, re.S))                address = ''.join(re.findall('Address:(.*?)', self.browser.page_source, re.S))            except:                print("該公司沒有電話")            all_down = [wd, company_name, company_phone_page, product, counctry, phone, mobilePhone, address,                        total_evenue, sell_adress, product_img]            save_csv(all_down)            print(company_name, company_phone_page, product, counctry, phone, mobilePhone, address, total_evenue,                  sell_adress, product_img)

  def buffer(self): #滑動(dòng)網(wǎng)頁的        for i in range(33):            time.sleep(0.5)            self.browser.execute_script('window.scrollBy(0,380)', '')  # 向下滑行300像素。
    def close_window(self):        length=self.browser.window_handles        if  len(length) > 3:            self.browser.switch_to.window(self.browser.window_handles[1])            self.browser.close()            time.sleep(1)            self.browser.switch_to.window(self.browser.window_handles[-1])

def save_csv(lise_line):    file = csv.writer(open("./alibaba_com_img.csv", 'a', newline="", encoding="utf-8"))    file.writerow(lise_line)
def main():    """    遍歷每一頁    """    run = Chrome_drive()    run.get_login() #先登錄    wd ='henan'    for i in range(1,32):        run.index_page(i, wd)
if __name__ == '__main__':    csv_title = 'wd,company_name,company_phone_page,product,counctry,phone,mobilePhone,address,total_evenue,sell_adress,product_img'.split(        ',')    save_csv(csv_title)    main()

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

import requestsimport pandas as pddef open_requests(img, img_name):    img_url ='https:'+ img    res=requests.get(img_url)    with open(f"./downloads_picture/{img_name}", 'wb') as fn:        fn.write(res.content)
df1=pd.read_csv('./alibaba_com_img.csv',)for imgs in df1["product_img"]:    imgList = str(imgs).split(',')    if len(imgList) > 0:        img = imgList[0]        img_name = img[24:]        print(img, img_name)        open_requests(img, img_name)

# -*- coding: utf-8 -*-
from PIL import Imageimport osimport xlwings as xwpath='alibaba_com.xlsx'app = xw.App(visible=True, add_book=False)wb = app.books.open(path)
sht = wb.sheets['Sheet1']img_list=sht.range("L2").expand('down').valueprint(len(img_list))

def write_pic(cell,img_name):    path=f'./downloads_picture/{img_name}'    print(path)    fileName = os.path.join(os.getcwd(), path)    img = Image.open(path).convert("RGB")    print(img.size)    w, h = img.size    x_s = 70  # 設(shè)置寬 excel中，我設(shè)置了200x200的格式    y_s = h * x_s / w  #  等比例設(shè)置高    sht.pictures.add(fileName, left=sht.range(cell).left, top=sht.range(cell).top, width=x_s, height=y_s)

if __name__ == '__main__':
    for index,imgs in enumerate(img_list):        cell="C"+str(index + 2)        imgsList = str(imgs).split(',')        if len(imgsList) > 0:            img = imgsList[0]            img_name = img[24:]            try:                write_pic(cell,img_name)                print(cell,img_name)            except:                print("沒有找到這個(gè)img_name的圖片",img_name)
    wb.save()    wb.close()    app.quit()