一、前提

　　上一篇，我寫了下載Excel2003的博文，這裏寫下載Excel2007的博文的原因有三：

　　　　第一、Excel2003基本已經淘汰了

　　　　第二、Excel2003下載文件太大，不利於網絡傳輸

　　　　第三、xlwt這個庫有個Bug，就是它不支持單元格字符串長度超過32767【這裏，有興趣的同學可以查看下源碼】

　　好了，廢話不多說了，我們進入正題。

二、安裝

　　本文使用的是pandas，引入庫的方式：pip install pandas

三、使用

　　首先、引入該庫，例如：import pandas

　　其次、

　　　　創建Excel文檔：

　　　　　　out = BytesIO()

　　　　　　excel = pandas.ExcelWriter(out, engine = ‘xlsxwriter‘) 這裏使用xlsxwriter引擎創建, 創建的文件直接關聯到輸出流out，安裝xlsxwriter也很簡單，如： pip install xlsxwriter

　　　　創建Sheet：

　　　　　　summary_df = pandas.DataFrame({})　　這裏使用空對象創建，下面代碼生成的sheet會是一個空sheet

　　　　　　summary_df.to_excel(excel, sheet_name = "Summary", index = False, header = False)

　　　　獲取sheet：worksheet = excel.sheets["Summary"]　　獲取sheet名稱為summary的sheet名

　　　　設置列寬：worksheet.set_column(‘D:D‘, 18, long_text_format)　　設置第四列寬度為18，使用樣式long_text_format【這個樣式需要自己提前定義】

　　　　保存Excel：excel.save()

　　　　　　Excel文件會直接輸出上面創建的輸出流out。

第四、輸出

response = HttpResponse(out.getvalue(), content_type = ‘application/vnd.ms-excel‘)
    dt = datetime.datetime.now()
    response[‘Content-Disposition‘] = ‘attachment;filename={} {}.xlsx‘.format(urlquote(domain_name), dt.strftime(‘%Y-%m-%d %H-%M-%S‘))
    print("End downloading...")
    return response

貼下源碼：

def download_report(request, task_id, domain_name = ‘全部‘):
    print("start downloading xlsx...", task_id)
    print("start downloading...", domain_name)

    domains = [{‘domain_name‘: domain_name}]
    ai_task = AITask.objects.get(id = task_id)
    if domain_name == ‘全部‘:
        if 1 == ai_task.type:
            domains = Classification.objects.values(‘domain_name‘).distinct().filter(type = 1).order_by("domain_name")
        elif 2 == ai_task.type:
            domains = Classification.objects.values(‘domain_name‘).distinct().filter(type = 2).order_by("domain_name")

    out = BytesIO()
    excel = pandas.ExcelWriter(out, engine = ‘xlsxwriter‘)

    summary_title = [‘Domain‘, ‘Pass‘, ‘Fail‘]
    summary_dict = {title: [] for title in summary_title}
    domain_title = [‘Domain‘, ‘One level‘, ‘Two level‘, ‘Semantic‘, ‘Priority‘, ‘Intent group‘, ‘Intent‘, ‘Result‘,
                    ‘Handle time‘, ‘Response time‘, ‘Server Domain‘, ‘Detail‘]

    summary_df = pandas.DataFrame({})
    summary_df.to_excel(excel, sheet_name = "Summary", index = False, header = False)

    workbook = excel.book
    body_format = workbook.add_format(style.body_style)
    header_format = workbook.add_format(style.head_style)
    long_text_format = workbook.add_format(style.long_text_style)
    large_text_format = workbook.add_format(style.large_text_style)

    sheet_data = {}
    for domain in domains:
        dmain_name = domain["domain_name"]
        sheet_data[dmain_name] = {column_name: [] for column_name in domain_title}
        reports = ai_task.report.filter(semantic__classification__domain_name__exact = dmain_name)

        if len(reports):
            pass_no = fail_no = 0
            for report in reports:
                semantic = report.semantic
                classification = semantic.classification

                sheet_data[dmain_name][domain_title[0]].append(classification.domain_name)
                sheet_data[dmain_name][domain_title[1]].append(classification.first_classification)
                sheet_data[dmain_name][domain_title[2]].append(classification.second_classification)
                sheet_data[dmain_name][domain_title[3]].append(semantic.name)
                sheet_data[dmain_name][domain_title[4]].append(classification.semantic_property)
                sheet_data[dmain_name][domain_title[5]].append(classification.intent_group)
                sheet_data[dmain_name][domain_title[6]].append(classification.intent)
                sheet_data[dmain_name][domain_title[7]].append(report.result)
                sheet_data[dmain_name][domain_title[8]].append(report.in_handle_time)
                sheet_data[dmain_name][domain_title[9]].append(report.ex_handle_time)
                sheet_data[dmain_name][domain_title[10]].append(report.server_domain)
                sheet_data[dmain_name][domain_title[11]].append(report.description)

                if "pass" == report.result:
                    pass_no += 1
                elif "fail" == report.result:
                    fail_no += 1
            sheet_df = pandas.DataFrame(sheet_data[dmain_name])
            sheet_df.to_excel(excel, sheet_name = dmain_name, index = False, header = False, startrow = 1)

            worksheet = excel.sheets[dmain_name]
            worksheet.set_column(‘A:C‘, None, body_format)
            worksheet.set_column(‘D:D‘, 18, long_text_format)
            worksheet.set_column(‘E:E‘, None, body_format)
            worksheet.set_column(‘F:G‘, 30, long_text_format)
            worksheet.set_column(‘H:H‘, None, body_format)
            worksheet.set_column(‘I:K‘, None, body_format)
            worksheet.set_column(‘L:L‘, 50, large_text_format)

            for col, title in enumerate(sheet_df.columns.values):
                worksheet.write(0, col, title, header_format)

            sheet_data.clear()  #回收內存

            summary_dict[summary_title[0]].append(dmain_name)
            summary_dict[summary_title[1]].append(pass_no)
            summary_dict[summary_title[2]].append(fail_no)

    summary_df = pandas.DataFrame(summary_dict)
    summary_df.to_excel(excel, sheet_name = ‘Summary‘, index = False, header = False, startrow = 1)
    worksheet = excel.sheets[‘Summary‘]
    for col, title in enumerate(summary_df.columns.values):
        worksheet.write(0, col, title, header_format)
        for row in range(len(summary_dict[title])):
            worksheet.write(row + 1, col, summary_dict[title][row], body_format)
    excel.save()

    response = HttpResponse(out.getvalue(), content_type = ‘application/vnd.ms-excel‘)
    dt = datetime.datetime.now()
    response[‘Content-Disposition‘] = ‘attachment;filename={} {}.xlsx‘.format(urlquote(domain_name), dt.strftime(‘%Y-%m-%d %H-%M-%S‘))
    print("End downloading...")
    return response

Python/Django 下載Excel2007