Python多線程Threading爬取圖片，保存本地，openpyxl批量插入圖片到Excel表中

之前用過openpyxl庫保存數據到Excel文件寫入不了，換用xlsxwriter

批量插入圖片到Excel表中

import os
import requests
import re
from openpyxl import load_workbook
import xlsxwriter
from multiprocessing.dummy import Pool as ThreadPool
from openpyxl.drawing.image import Image

def spider(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'}
    html = requests.get(url, headers, timeout=None)
    pic_url = re.findall('class="product-image">.*?<img src="(.*?)"  height="', html.text, re.S)
    sku = re.findall('q=(\d+)', url, re.S)#正則匹配鏈接后面的sku
    if pic_url != []:
        print('正在下載'+sku[0]+'圖片，圖片地址：' + pic_url[0])
        pic = requests.get(pic_url[0])
        dir = cwd + '\\images\\' + sku[0] + '.jpg'
        # print(dir)
        with open(dir, 'wb') as file:
            file.write(pic.content)
    else:
        if sku !=[]:
            print('沒有找到' + sku[0]+'產品')
            No_images.append(sku[0])
#之前用過openpyxl創建新的Excel文件，但是寫入不了，之后換用xlsxwriter保存數據到Excel
def save_excel(sku):
    print(sku)
    wb1 = xlsxwriter.Workbook(cwd + '\\' + 'No_images.xlsx')
    ws1 = wb1.add_worksheet()
    ws1.write(0, 0, 'No_images_sku')
    for i in range(1,len(sku)+1):
        ws1.write(i, 0, sku[i-1])
    wb1.close()
    print('保存沒有圖片的sku成功！')

#插入圖片到Excel
def insert_images(sku):
    wb = load_workbook(path)
    ws = wb.worksheets[0]
    img_path = cwd + '\\images\\'+sku+'.jpg'
    print(img_path)
    ws.column_dimensions['H'].width = 11#設置單元格列寬
    try:
        img = Image(img_path)
        #設置圖片大小
        img.width = 80
        img.height = 96
        # print(img)
        for i in range(1,ws.max_row+1):
            if ws.cell(i,2).value == int(sku):
                ws.row_dimensions[i].height = 88#設置單元格行高
                ws.add_image(img,'H'+str(i))
                wb.save(path)
    except(FileNotFoundError) as e:
        print(e)
    wb.close()#每次插入一張圖片需要關閉一次Excel表
    
if __name__ == '__main__':
    cwd=os.getcwd()
    path = cwd + '\\'+'圖片測試.xlsx'
    wb =load_workbook(path)
    ws = wb.worksheets[0]
    pool =ThreadPool(50)#開啟多少個進程，四核電腦
    urls = []
    No_images = []
    for i in range(1, ws.max_row+1):#通過循環將Excel數據讀取出來
        sku = ws.cell(i,2).value
        if sku !=None:
            print('正在爬取第'+str(i)+'個sku圖片')
            url = 'http://www.fulchic.com/catalogsearch/result/?q=' + str(sku)
            urls.append(url)
    pool.map(spider,urls)#多線程工作，其中，spider是爬蟲函數名，urls是個爬取鏈接列表
    pool.close()
    pool.join()
    #保存圖片到本地
    save_excel(No_images)
    #循環寫入保存圖片，並設置單元格和圖片大小
    for i in range(1, ws.max_row + 1):  # 通過循環將Excel數據讀取出來
        sku = ws.cell(i, 2).value
        if sku != None:
            print('正在保存第' + str(i) + '個sku圖片')
            insert_images(str(sku))