本节学习目标
学完这一节，你就能搞定这些事儿：
- 明白自动化报告到底能用在哪儿、值不值得学
- 上手
python-pptx库，自己能创建和编辑PPT - 把数据分析结果——表格、图表、图片——一键塞进PPT
- 用
reportlab或FPDF生成像样的PDF报告 - 搭一套模板化报告系统，以后动动手指就能出活
- 理解怎么用定时任务把整个流程串起来，实现全自动
为什么学这个
先脑补一个场景：你是个数据分析师，每周一早上都要给部门交上周的业务数据报告。日常工作流大概是：
- 从数据库导出数据
- Pandas做数据处理
- Matplotlib/Seaborn画图
- 手动打开PPT，一张张粘贴图表、调整格式、更新数据
- 导出PDF，发邮件
前几步你已经很溜了，但第四步——手动做PPT——可能一搞就是两三个小时。更要命的是，每周都得重复这套动作。
如果这个过程能自动跑起来呢？ 代码写好之后，每周一早上，一份排版漂亮、数据最新的PPT报告自动生成，你只要过一遍、发出去就行。这就是这一节要带你去的地方。
打个比方：数据分析好比“做菜”，报告自动化就是“自动上菜系统”。菜做得再好，上菜又慢又丑，客人体验也打折。而有了这套系统，你只管把菜做好，上菜的事交给机器。
核心知识点讲解
python-pptx 基础
安装与基本用法
# 安装: pip install python-pptx
from pptx import Presentation
from pptx.util import Inches, Pt, Emu
from pptx.enum.text import PP_ALIGN
from pptx.dml.color import RGBColor
import os
# 创建一个空白演示文稿
prs = Presentation()
# 设置幻灯片尺寸（16:9 宽屏）
prs.slide_width = Inches(13.333)
prs.slide_height = Inches(7.5)
# 添加一张空白幻灯片
blank_layout = prs.slide_layouts[6] # 6 = 空白版式
slide = prs.slides.add_slide(blank_layout)
# 添加标题
title_box = slide.shapes.add_textbox(
Inches(1), Inches(2), Inches(11.333), Inches(1.5)
)
title_frame = title_box.text_frame
title_frame.word_wrap = True
p = title_frame.paragraphs[0]
p.text = "2024年第一季度业务数据报告"
p.font.size = Pt(36)
p.font.bold = True
p.font.color.rgb = RGBColor(0x2C, 0x3E, 0x50)
p.alignment = PP_ALIGN.CENTER
# 添加副标题
subtitle_box = slide.shapes.add_textbox(
Inches(1), Inches(4), Inches(11.333), Inches(1)
)
subtitle_frame = subtitle_box.text_frame
subtitle_frame.word_wrap = True
p2 = subtitle_frame.paragraphs[0]
p2.text = "自动生成 | 数据分析部"
p2.font.size = Pt(20)
p2.font.color.rgb = RGBColor(0x7F, 0x8C, 0x8D)
p2.alignment = PP_ALIGN.CENTER
# 保存
output_path = "业务报告_模板演示.pptx"
prs.sa ve(output_path)
print(f"演示文稿已保存至: {output_path}")
文本框与段落格式化
# 演示各种文本格式设置
prs = Presentation()
slide_layout = prs.slide_layouts[6]
slide = prs.slides.add_slide(slide_layout)
# 创建一个多段落文本框
textbox = slide.shapes.add_textbox(
Inches(1), Inches(1), Inches(11), Inches(5)
)
tf = textbox.text_frame
tf.word_wrap = True
# 第一段：标题
p = tf.paragraphs[0]
p.text = "业务摘要"
p.font.size = Pt(28)
p.font.bold = True
p.font.color.rgb = RGBColor(0xE7, 0x4C, 0x3C)
p.space_after = Pt(12)
# 第二段：正文
p2 = tf.add_paragraph()
p2.text = "本季度销售额同比增长15.3%，主要得益于新产品线的成功推广。"
p2.font.size = Pt(16)
p2.font.color.rgb = RGBColor(0x2C, 0x3E, 0x50)
p2.space_after = Pt(8)
# 第三段：要点
key_points = [
"线上渠道贡献了62%的销售额",
"复购率提升至38%，较去年提高5个百分点",
"客户满意度评分4.5/5.0，达到历史新高"
]
for point in key_points:
p = tf.add_paragraph()
p.text = f"• {point}"
p.font.size = Pt(14)
p.font.color.rgb = RGBColor(0x34, 0x49, 0x5E)
p.level = 0
p.space_before = Pt(4)
prs.sa ve("文本格式化示例.pptx")
print("文本格式化示例已保存")
添加表格
import pandas as pd
# 创建示例数据
sales_data = pd.DataFrame({
"产品类别": ["电子产品", "服装鞋帽", "食品饮料", "家居用品", "图书文具"],
"销售额(万元)": [580, 420, 310, 260, 95],
"同比增长": ["+18.5%", "+12.3%", "+8.7%", "+22.1%", "+5.2%"],
"占比": ["34.8%", "25.2%", "18.6%", "15.6%", "5.7%"]
})
prs = Presentation()
slide = prs.slides.add_slide(prs.slide_layouts[6])
# 添加标题
title_box = slide.shapes.add_textbox(Inches(0.5), Inches(0.3), Inches(12), Inches(0.8))
title_tf = title_box.text_frame
title_tf.paragraphs[0].text = "各产品销售数据"
title_tf.paragraphs[0].font.size = Pt(24)
title_tf.paragraphs[0].font.bold = True
title_tf.paragraphs[0].font.color.rgb = RGBColor(0x2C, 0x3E, 0x50)
# 添加表格
rows, cols = len(sales_data) + 1, len(sales_data.columns)
table_shape = slide.shapes.add_table(rows, cols, Inches(1), Inches(1.5), Inches(10), Inches(3))
table = table_shape.table
# 设置列宽
col_widths = [Inches(2.5), Inches(2.5), Inches(2.5), Inches(2.5)]
for i, width in enumerate(col_widths):
table.columns[i].width = width
# 填充表头
for j, col_name in enumerate(sales_data.columns):
cell = table.cell(0, j)
cell.text = col_name
for paragraph in cell.text_frame.paragraphs:
paragraph.font.size = Pt(14)
paragraph.font.bold = True
paragraph.font.color.rgb = RGBColor(0xFF, 0xFF, 0xFF)
paragraph.alignment = PP_ALIGN.CENTER
# 设置表头背景色
cell_fill = cell.fill
cell_fill.solid()
cell_fill.fore_color.rgb = RGBColor(0x2C, 0x3E, 0x50)
# 填充数据行
for i, row in sales_data.iterrows():
for j, value in enumerate(row):
cell = table.cell(i + 1, j)
cell.text = str(value)
for paragraph in cell.text_frame.paragraphs:
paragraph.font.size = Pt(12)
paragraph.alignment = PP_ALIGN.CENTER
# 增长率大于15%的用绿色，否则用红色
if j == 1 and i == 0: # 销售额最高行
paragraph.font.bold = True
cell.fill.solid()
cell.fill.fore_color.rgb = RGBColor(0xEA, 0xFA, 0xEA)
prs.sa ve("表格示例_销售数据.pptx")
print("表格示例已保存")
在PPT中插入图表和图片
生成分析图表并插入PPT
import matplotlib.pyplot as plt
import matplotlib
matplotlib.use("Agg") # 无GUI环境使用
# 生成销售趋势图
fig, ax = plt.subplots(figsize=(10, 5))
months = ["1月", "2月", "3月"]
sales = [520, 480, 665] # 万元
bars = ax.bar(months, sales, color=["#3498db", "#2ecc71", "#e74c3c"], width=0.5)
for bar, val in zip(bars, sales):
ax.text(bar.get_x() + bar.get_width()/2, bar.get_height() + 10,
f"{val}万", ha="center", fontweight="bold", fontsize=12)
ax.set_title("季度销售额趋势", fontsize=14, fontweight="bold")
ax.set_ylabel("销售额（万元）")
ax.set_ylim(0, 800)
plt.tight_layout()
plt.sa vefig("sales_chart.png", dpi=150, bbox_inches="tight")
plt.close()
# 将图表插入PPT
prs = Presentation()
slide = prs.slides.add_slide(prs.slide_layouts[6])
# 标题
title_box = slide.shapes.add_textbox(Inches(0.5), Inches(0.3), Inches(12), Inches(0.8))
title_box.text_frame.paragraphs[0].text = "Q1销售额趋势分析"
title_box.text_frame.paragraphs[0].font.size = Pt(24)
title_box.text_frame.paragraphs[0].font.bold = True
# 插入图表图片
slide.shapes.add_picture(
"sales_chart.png",
Inches(0.5), Inches(1.2),
Inches(12), Inches(5)
)
# 添加数据解读
insight_box = slide.shapes.add_textbox(Inches(1), Inches(6.3), Inches(10), Inches(1))
insight_tf = insight_box.text_frame
insight_tf.word_wrap = True
p = insight_tf.paragraphs[0]
p.text = "数据解读：3月销售额显著增长，主要受春季促销活动拉动，环比2月增长38.5%。"
p.font.size = Pt(14)
p.font.color.rgb = RGBColor(0x7F, 0x8C, 0x8D)
prs.sa ve("图表插入示例.pptx")
print("图表插入示例已保存")
添加形状和装饰元素
from pptx.util import Emu
from pptx.enum.shapes import MSO_SHAPE
prs = Presentation()
prs.slide_width = Inches(13.333)
prs.slide_height = Inches(7.5)
slide = prs.slides.add_slide(prs.slide_layouts[6])
# 添加顶部色块装饰
shape = slide.shapes.add_shape(
MSO_SHAPE.RECTANGLE,
Inches(0), Inches(0), Inches(13.333), Inches(1.2)
)
shape.fill.solid()
shape.fill.fore_color.rgb = RGBColor(0x2C, 0x3E, 0x50)
shape.line.fill.background()
# 在色块上添加标题
title_box = slide.shapes.add_textbox(Inches(0.5), Inches(0.2), Inches(12), Inches(0.8))
title_box.text_frame.paragraphs[0].text = "核心指标一览"
title_box.text_frame.paragraphs[0].font.size = Pt(28)
title_box.text_frame.paragraphs[0].font.bold = True
title_box.text_frame.paragraphs[0].font.color.rgb = RGBColor(0xFF, 0xFF, 0xFF)
# 添加4个KPI卡片
kpi_data = [
("总销售额", "1665万", "+15.3%", "#2ecc71"),
("活跃用户", "52.3万", "+8.7%", "#3498db"),
("转化率", "4.2%", "+0.5pp", "#f39c12"),
("客单价", "186元", "+3.1%", "#9b59b6")
]
card_width = Inches(2.8)
card_height = Inches(2)
gap = Inches(0.4)
start_x = Inches(1)
start_y = Inches(2)
for i, (label, value, change, color) in enumerate(kpi_data):
x = start_x + i * (card_width + gap)
# 卡片背景
card = slide.shapes.add_shape(
MSO_SHAPE.ROUNDED_RECTANGLE, x, start_y, card_width, card_height
)
card.fill.solid()
card.fill.fore_color.rgb = RGBColor(0xF8, 0xF9, 0xFA)
card.line.color.rgb = RGBColor(0xDE, 0xE2, 0xE6)
card.line.width = Pt(1)
# 顶部彩色条
bar = slide.shapes.add_shape(
MSO_SHAPE.RECTANGLE, x, start_y, card_width, Inches(0.1)
)
bar.fill.solid()
bar.fill.fore_color.rgb = RGBColor(
int(color[1:3], 16), int(color[3:5], 16), int(color[5:7], 16)
)
bar.line.fill.background()
# 指标标签
label_box = slide.shapes.add_textbox(x, start_y + Inches(0.3), card_width, Inches(0.5))
label_box.text_frame.paragraphs[0].text = label
label_box.text_frame.paragraphs[0].font.size = Pt(12)
label_box.text_frame.paragraphs[0].font.color.rgb = RGBColor(0x7F, 0x8C, 0x8D)
label_box.text_frame.paragraphs[0].alignment = PP_ALIGN.CENTER
# 指标数值
value_box = slide.shapes.add_textbox(x, start_y + Inches(0.7), card_width, Inches(0.6))
value_box.text_frame.paragraphs[0].text = value
value_box.text_frame.paragraphs[0].font.size = Pt(28)
value_box.text_frame.paragraphs[0].font.bold = True
value_box.text_frame.paragraphs[0].font.color.rgb = RGBColor(0x2C, 0x3E, 0x50)
value_box.text_frame.paragraphs[0].alignment = PP_ALIGN.CENTER
# 变化趋势
change_box = slide.shapes.add_textbox(x, start_y + Inches(1.4), card_width, Inches(0.4))
change_box.text_frame.paragraphs[0].text = f"环比 {change}"
change_box.text_frame.paragraphs[0].font.size = Pt(11)
change_box.text_frame.paragraphs[0].font.color.rgb = RGBColor(0x2E, 0xCC, 0x71)
change_box.text_frame.paragraphs[0].alignment = PP_ALIGN.CENTER
prs.sa ve("KPI卡片示例.pptx")
print("KPI卡片示例已保存")
模板化报告系统
设计报告模板
模板化报告的核心思想其实一句话就能说清楚：把报告的结构（模板）和数据（内容）拆开。结构固定下来，数据往里灌，报告就自动出来了。
# ========== 模板化报告生成系统 ==========
class ReportGenerator:
"""自动化报告生成器"""
def __init__(self, title="业务分析报告", author="数据分析部"):
self.prs = Presentation()
self.prs.slide_width = Inches(13.333)
self.prs.slide_height = Inches(7.5)
self.title = title
self.author = author
self._setup_colors()
def _setup_colors(self):
"""设置品牌色系"""
self.colors = {
"primary": RGBColor(0x2C, 0x3E, 0x50), # 深蓝灰
"secondary": RGBColor(0x34, 0x98, 0xDB), # 亮蓝
"accent": RGBColor(0xE7, 0x4C, 0x3C), # 红色
"success": RGBColor(0x2E, 0xCC, 0x71), # 绿色
"warning": RGBColor(0xF3, 0x9C, 0x12), # 橙色
"text": RGBColor(0x2C, 0x3E, 0x50), # 正文色
"light_text": RGBColor(0x7F, 0x8C, 0x8D), # 浅文字
"bg": RGBColor(0xF8, 0xF9, 0xFA), # 背景色
"white": RGBColor(0xFF, 0xFF, 0xFF)
}
def add_cover_slide(self):
"""添加封面页"""
slide = self.prs.slides.add_slide(self.prs.slide_layouts[6])
# 背景色块
bg = slide.shapes.add_shape(
MSO_SHAPE.RECTANGLE, Inches(0), Inches(0),
Inches(13.333), Inches(7.5)
)
bg.fill.solid()
bg.fill.fore_color.rgb = self.colors["primary"]
bg.line.fill.background()
# 装饰线条
line = slide.shapes.add_shape(
MSO_SHAPE.RECTANGLE, Inches(1), Inches(3.2),
Inches(2), Inches(0.05)
)
line.fill.solid()
line.fill.fore_color.rgb = self.colors["accent"]
line.line.fill.background()
# 标题
title_box = slide.shapes.add_textbox(
Inches(1), Inches(2.5), Inches(11), Inches(1)
)
title_box.text_frame.paragraphs[0].text = self.title
title_box.text_frame.paragraphs[0].font.size = Pt(40)
title_box.text_frame.paragraphs[0].font.bold = True
title_box.text_frame.paragraphs[0].font.color.rgb = self.colors["white"]
# 副标题
sub_box = slide.shapes.add_textbox(
Inches(1), Inches(3.5), Inches(11), Inches(0.8)
)
sub_box.text_frame.paragraphs[0].text = f"{self.author} | 自动生成"
sub_box.text_frame.paragraphs[0].font.size = Pt(18)
sub_box.text_frame.paragraphs[0].font.color.rgb = RGBColor(0xB0, 0xBE, 0xC5)
return slide
def add_kpi_slide(self, kpis):
"""添加KPI概览页"""
slide = self.prs.slides.add_slide(self.prs.slide_layouts[6])
# 标题栏
header = slide.shapes.add_shape(
MSO_SHAPE.RECTANGLE, Inches(0), Inches(0), Inches(13.333), Inches(1)
)
header.fill.solid()
header.fill.fore_color.rgb = self.colors["primary"]
header.line.fill.background()
title_box = slide.shapes.add_textbox(
Inches(0.5), Inches(0.15), Inches(12), Inches(0.7)
)
title_box.text_frame.paragraphs[0].text = "核心指标概览"
title_box.text_frame.paragraphs[0].font.size = Pt(24)
title_box.text_frame.paragraphs[0].font.bold = True
title_box.text_frame.paragraphs[0].font.color.rgb = self.colors["white"]
# KPI卡片
n = len(kpis)
card_width = Inches(2.8)
card_height = Inches(2.2)
gap = Inches(0.35)
start_x = (Inches(13.333) - n * card_width - (n-1) * gap) / 2
start_y = Inches(1.8)
for i, (label, value, change) in enumerate(kpis):
x = start_x + i * (card_width + gap)
card = slide.shapes.add_shape(
MSO_SHAPE.ROUNDED_RECTANGLE, x, start_y, card_width, card_height
)
card.fill.solid()
card.fill.fore_color.rgb = self.colors["bg"]
card.line.color.rgb = RGBColor(0xDE, 0xE2, 0xE6)
# 数值
val_box = slide.shapes.add_textbox(x, start_y + Inches(0.4), card_width, Inches(0.8))
val_box.text_frame.paragraphs[0].text = value
val_box.text_frame.paragraphs[0].font.size = Pt(30)
val_box.text_frame.paragraphs[0].font.bold = True
val_box.text_frame.paragraphs[0].font.color.rgb = self.colors["text"]
val_box.text_frame.paragraphs[0].alignment = PP_ALIGN.CENTER
# 标签
lbl_box = slide.shapes.add_textbox(x, start_y + Inches(1.2), card_width, Inches(0.4))
lbl_box.text_frame.paragraphs[0].text = label
lbl_box.text_frame.paragraphs[0].font.size = Pt(12)
lbl_box.text_frame.paragraphs[0].font.color.rgb = self.colors["light_text"]
lbl_box.text_frame.paragraphs[0].alignment = PP_ALIGN.CENTER
# 变化
chg_box = slide.shapes.add_textbox(x, start_y + Inches(1.6), card_width, Inches(0.4))
chg_box.text_frame.paragraphs[0].text = change
chg_box.text_frame.paragraphs[0].font.size = Pt(12)
chg_box.text_frame.paragraphs[0].font.color.rgb = self.colors["success"]
chg_box.text_frame.paragraphs[0].alignment = PP_ALIGN.CENTER
def add_table_slide(self, title_text, df):
"""添加数据表格页"""
slide = self.prs.slides.add_slide(self.prs.slide_layouts[6])
# 标题
title_box = slide.shapes.add_textbox(
Inches(0.5), Inches(0.3), Inches(12), Inches(0.7)
)
title_box.text_frame.paragraphs[0].text = title_text
title_box.text_frame.paragraphs[0].font.size = Pt(24)
title_box.text_frame.paragraphs[0].font.bold = True
title_box.text_frame.paragraphs[0].font.color.rgb = self.colors["text"]
# 表格
rows, cols = len(df) + 1, len(df.columns)
tbl_shape = slide.shapes.add_table(
rows, cols, Inches(0.8), Inches(1.3),
Inches(11.5), Inches(0.5 * rows)
)
tbl = tbl_shape.table
# 表头
for j, col in enumerate(df.columns):
cell = tbl.cell(0, j)
cell.text = col
cell.fill.solid()
cell.fill.fore_color.rgb = self.colors["primary"]
for p in cell.text_frame.paragraphs:
p.font.size = Pt(12)
p.font.bold = True
p.font.color.rgb = self.colors["white"]
p.alignment = PP_ALIGN.CENTER
# 数据行
for i, row in df.iterrows():
for j, val in enumerate(row):
cell = tbl.cell(i + 1, j)
cell.text = str(val)
for p in cell.text_frame.paragraphs:
p.font.size = Pt(11)
p.alignment = PP_ALIGN.CENTER
if i % 2 == 0:
cell.fill.solid()
cell.fill.fore_color.rgb = self.colors["bg"]
def add_chart_slide(self, title_text, chart_path, insight=""):
"""添加图表页"""
slide = self.prs.slides.add_slide(self.prs.slide_layouts[6])
title_box = slide.shapes.add_textbox(
Inches(0.5), Inches(0.3), Inches(12), Inches(0.7)
)
title_box.text_frame.paragraphs[0].text = title_text
title_box.text_frame.paragraphs[0].font.size = Pt(24)
title_box.text_frame.paragraphs[0].font.bold = True
title_box.text_frame.paragraphs[0].font.color.rgb = self.colors["text"]
slide.shapes.add_picture(
chart_path, Inches(0.5), Inches(1.2), Inches(12), Inches(4.5)
)
if insight:
ins_box = slide.shapes.add_textbox(
Inches(1), Inches(6), Inches(11), Inches(1)
)
ins_box.text_frame.word_wrap = True
ins_box.text_frame.paragraphs[0].text = f"数据解读：{insight}"
ins_box.text_frame.paragraphs[0].font.size = Pt(14)
ins_box.text_frame.paragraphs[0].font.color.rgb = self.colors["light_text"]
def add_summary_slide(self, summary_points):
"""添加总结页"""
slide = self.prs.slides.add_slide(self.prs.slide_layouts[6])
title_box = slide.shapes.add_textbox(
Inches(0.5), Inches(0.3), Inches(12), Inches(0.7)
)
title_box.text_frame.paragraphs[0].text = "总结与建议"
title_box.text_frame.paragraphs[0].font.size = Pt(24)
title_box.text_frame.paragraphs[0].font.bold = True
title_box.text_frame.paragraphs[0].font.color.rgb = self.colors["text"]
tf_box = slide.shapes.add_textbox(
Inches(1), Inches(1.5), Inches(11), Inches(5)
)
tf = tf_box.text_frame
tf.word_wrap = True
for i, point in enumerate(summary_points):
p = tf.paragraphs[0] if i == 0 else tf.add_paragraph()
p.text = f"{i+1}. {point}"
p.font.size = Pt(16)
p.font.color.rgb = self.colors["text"]
p.space_after = Pt(12)
def sa ve(self, filename):
"""保存报告"""
self.prs.sa ve(filename)
print(f"报告已保存至: {filename}")
使用模板生成完整报告
# 使用报告生成器创建完整报告
# 1. 准备数据
sales_data = pd.DataFrame({
"产品类别": ["电子产品", "服装鞋帽", "食品饮料", "家居用品", "图书文具"],
"销售额(万元)": [580, 420, 310, 260, 95],
"同比增长": ["+18.5%", "+12.3%", "+8.7%", "+22.1%", "+5.2%"],
"用户数(万)": [12.5, 18.3, 25.1, 8.7, 3.2]
})
# 2. 生成图表
fig, axes = plt.subplots(1, 2, figsize=(16, 5))
# 左图：类别销售额
axes[0].barh(
sales_data["产品类别"][::-1],
sales_data["销售额(万元)"][::-1],
color=["#3498db", "#2ecc71", "#f39c12", "#e74c3c", "#9b59b6"][::-1]
)
axes[0].set_title("各类别销售额对比", fontweight="bold")
axes[0].set_xlabel("销售额（万元）")
# 右图：用户数对比
axes[1].bar(
sales_data["产品类别"],
sales_data["用户数(万)"],
color="#3498db"
)
axes[1].set_title("各类别用户数对比", fontweight="bold")
axes[1].set_ylabel("用户数（万）")
axes[1].tick_params(axis="x", rotation=30)
plt.tight_layout()
plt.sa vefig("combined_chart.png", dpi=150, bbox_inches="tight")
plt.close()
# 3. 生成报告
report = ReportGenerator(
title="2024年第一季度业务分析报告",
author="数据分析部"
)
# 封面
report.add_cover_slide()
# KPI概览
report.add_kpi_slide([
("总销售额", "1665万", "同比 +15.3%"),
("活跃用户", "52.3万", "同比 +8.7%"),
("转化率", "4.2%", "提升 0.5pp"),
("客单价", "186元", "同比 +3.1%")
])
# 数据表格
report.add_table_slide("各产品类别详细数据", sales_data)
# 图表页
report.add_chart_slide(
"销售与用户分布分析",
"combined_chart.png",
"电子产品销售额最高（580万），家居用品增速最快（+22.1%）。食品饮料用户基数最大但客单价偏低。"
)
# 总结
report.add_summary_slide([
"整体销售额保持稳健增长，建议继续加大电子产品的库存投入",
"家居用品增速最快（+22.1%），值得重点关注和资源倾斜",
"食品饮料用户数最多但转化率低，建议优化商品详情页和推荐策略",
"下季度建议针对高增长品类加大营销预算，低增长品类优化用户体验"
])
# 保存
report.sa ve("2024Q1业务分析报告_自动生成.pptx")
生成PDF报告
使用 reportlab 生成PDF
# 安装: pip install reportlab
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import cm, mm
from reportlab.lib.colors import HexColor
from reportlab.platypus import (
SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle,
Image, PageBreak, KeepTogether
)
from reportlab.lib.enums import TA_LEFT, TA_CENTER, TA_RIGHT
# 创建PDF文档
doc = SimpleDocTemplate(
"数据分析报告_自动生成.pdf",
pagesize=A4,
rightMargin=2*cm,
leftMargin=2*cm,
topMargin=2*cm,
bottomMargin=2*cm
)
story = []
styles = getSampleStyleSheet()
# 自定义样式
styles.add(ParagraphStyle(
name="CustomTitle",
parent=styles["Title"],
fontSize=24,
textColor=HexColor("#2C3E50"),
spaceAfter=10*mm
))
styles.add(ParagraphStyle(
name="SectionHeader",
parent=styles["Heading2"],
fontSize=16,
textColor=HexColor("#3498DB"),
spaceBefore=8*mm,
spaceAfter=4*mm
))
styles.add(ParagraphStyle(
name="BodyChinese",
parent=styles["Normal"],
fontSize=11,
leading=18,
spaceAfter=4*mm
))
# 添加内容
story.append(Paragraph("2024年第一季度业务分析报告", styles["CustomTitle"]))
story.append(Spacer(1, 5*mm))
story.append(Paragraph("数据分析部 | 自动生成", styles["BodyChinese"]))
story.append(Spacer(1, 8*mm))
story.append(Paragraph("一、核心指标概览", styles["SectionHeader"]))
story.append(Paragraph(
"本季度总销售额1665万元，同比增长15.3%。活跃用户52.3万人，转化率提升至4.2%。"
"整体业务呈现良好的增长态势，其中家居用品类目表现最为突出。",
styles["BodyChinese"]
))
story.append(Paragraph("二、各品类销售明细", styles["SectionHeader"]))
# 创建表格数据
table_data = [["产品类别", "销售额(万元)", "同比增长", "用户数(万)"]]
for _, row in sales_data.iterrows():
table_data.append([str(row["产品类别"]), str(row["销售额(万元)"]),
str(row["同比增长"]), str(row["用户数(万)"])])
# 创建表格
tbl = Table(table_data, colWidths=[4*cm, 3*cm, 2.5*cm, 2.5*cm])
tbl.setStyle(TableStyle([
("BACKGROUND", (0, 0), (-1, 0), HexColor("#2C3E50")),
("TEXTCOLOR", (0, 0), (-1, 0), HexColor("#FFFFFF")),
("ALIGN", (0, 0), (-1, -1), "CENTER"),
("FONTSIZE", (0, 0), (-1, -1), 10),
("BOTTOMPADDING", (0, 0), (-1, 0), 8),
("TOPPADDING", (0, 0), (-1, 0), 8),
("ROWBACKGROUNDS", (0, 1), (-1, -1), [HexColor("#F8F9FA"), HexColor("#FFFFFF")]),
("GRID", (0, 0), (-1, -1), 0.5, HexColor("#DEE2E6")),
]))
story.append(tbl)
story.append(Paragraph("三、分析结论", styles["SectionHeader"]))
conclusions = [
"电子产品销售额最高（580万），是公司的核心收入来源",
"家居用品增速最快（+22.1%），建议加大投入",
"食品饮料用户基数最大，但转化率和客单价偏低，需优化产品策略",
"建议下季度重点关注高增长品类，优化低增长品类的用户体验"
]
for c in conclusions:
story.append(Paragraph(f"• {c}", styles["BodyChinese"]))
# 构建PDF
doc.build(story)
print("PDF报告已保存: 数据分析报告_自动生成.pdf")
自动化流程集成
定时任务调度
import schedule
import time
import os
from datetime import datetime
def generate_weekly_report():
"""每周一自动生成周报"""
print(f"[{datetime.now()}] 开始生成周报...")
# 1. 从数据库/文件获取最新数据
# df = pd.read_csv("weekly_data.csv")
# 或使用数据库连接获取数据
# 2. 执行数据分析
# ... 数据处理代码 ...
# 3. 生成图表
# fig.sa vefig("weekly_chart.png")
# 4. 生成报告
# report = ReportGenerator(title="周度业务报告")
# report.add_cover_slide()
# ...
# report.sa ve(f"Weekly_Report_{datetime.now().strftime('%Y-%m-%d')}.pptx")
print(f"[{datetime.now()}] 周报生成完成！")
# 设置定时任务
schedule.every().monday.at("08:00").do(generate_weekly_report)
print("定时任务已启动，每周一 08:00 自动生成周报")
# 运行调度器（在实际使用中会作为后台服务运行）
# while True:
# schedule.run_pending()
# time.sleep(60)
5.2 完整自动化脚本示例
#!/usr/bin/env python
"""
自动化业务报告生成脚本
运行方式: python auto_report.py
"""
import os
import pandas as pd
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
from datetime import datetime
import logging
# 配置日志
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s",
handlers=[
logging.FileHandler("report_generation.log"),
logging.StreamHandler()
]
)
def main():
logging.info("=" * 50)
logging.info("开始执行自动化报告生成流程")
logging.info("=" * 50)
try:
# Step 1: 数据加载
logging.info("Step 1: 加载数据...")
# df = pd.read_csv("data/latest_sales.csv")
# 这里用模拟数据
df = pd.DataFrame({
"date": pd.date_range("2024-01-01", periods=90),
"sales": np.random.normal(50, 10, 90)
})
# Step 2: 数据分析
logging.info("Step 2: 执行数据分析...")
total_sales = df["sales"].sum()
a vg_daily = df["sales"].mean()
max_day = df.loc[df["sales"].idxmax()]
# Step 3: 生成图表
logging.info("Step 3: 生成分析图表...")
fig, ax = plt.subplots(figsize=(10, 5))
ax.plot(df["date"], df["sales"], color="#3498db", linewidth=1)
ax.axhline(y=a vg_daily, color="red", linestyle="--", label=f"均值: {a vg_daily:.1f}")
ax.set_title("日销售趋势")
ax.legend()
plt.tight_layout()
chart_path = f"charts/chart_{datetime.now().strftime('%Y%m%d')}.png"
os.makedirs("charts", exist_ok=True)
plt.sa vefig(chart_path, dpi=150)
plt.close()
# Step 4: 生成报告
logging.info("Step 4: 生成PPT报告...")
report = ReportGenerator(
title=f"业务报告 - {datetime.now().strftime('%Y-%m-%d')}",
author="自动化系统"
)
report.add_cover_slide()
report.add_kpi_slide([
("总销售额", f"{total_sales:.0f}", ""),
("日均销售", f"{a vg_daily:.1f}", ""),
("峰值日期", max_day["date"].strftime("%m-%d"), f"{max_day['sales']:.0f}"),
("数据天数", "90", "")
])
report.add_chart_slide(
"销售趋势分析",
chart_path,
f"分析期间总销售额{total_sales:.0f}，日均{a vg_daily:.1f}"
)
output_dir = "reports"
os.makedirs(output_dir, exist_ok=True)
report.sa ve(f"{output_dir}/report_{datetime.now().strftime('%Y%m%d_%H%M%S')}.pptx")
logging.info("自动化报告生成完成！")
except Exception as e:
logging.error(f"报告生成失败: {str(e)}")
raise
if __name__ == "__main__":
main()
实战练习
题目： 用下面这份数据，自动生成一份包含封面、KPI卡片、数据表格和图表的PPT报告。
# 参考答案
# 使用本节提供的 ReportGenerator 类
# 练习数据
monthly_data = pd.DataFrame({
"月份": ["1月", "2月", "3月", "4月", "5月", "6月"],
"收入(万)": [45, 52, 48, 61, 55, 68],
"支出(万)": [30, 33, 31, 38, 35, 40],
"客户数": [120, 135, 128, 152, 140, 168]
})
# 生成趋势图
fig, ax = plt.subplots(figsize=(8, 4))
ax.plot(monthly_data["月份"], monthly_data["收入(万)"], "b-o", label="收入")
ax.plot(monthly_data["月份"], monthly_data["支出(万)"], "r-o", label="支出")
ax.fill_between(range(6), monthly_data["支出(万)"], monthly_data["收入(万)"],
alpha=0.2, color="green")
ax.set_title("月度收支对比")
ax.legend()
plt.tight_layout()
plt.sa vefig("exercise_chart.png", dpi=150)
plt.close()
# 生成报告
report = ReportGenerator(
title="2024上半年经营分析报告",
author="财务部"
)
report.add_cover_slide()
report.add_kpi_slide([
("总收入", "329万", "环比 +51%"),
("总支出", "207万", "环比 +33%"),
("净利润", "122万", "环比 +82%"),
("总客户", "843", "环比 +40%")
])
report.add_table_slide("月度经营明细", monthly_data)
report.add_chart_slide("月度收支趋势", "exercise_chart.png",
"收入持续增长，利润率逐月提升，6月达到最佳水平。")
report.add_summary_slide([
"上半年整体经营良好，收入与利润双增长",
"建议下半年保持当前增长势头，控制支出增速",
"客户增长稳定，建议加强客户留存策略"
])
report.sa ve("练习报告_上半年经营分析.pptx")
本节总结
这一节我们从头到尾走了一遍用Python自动生成专业分析报告的完整流程：
- python-pptx 基础：学会了怎么创建幻灯片、加文本框、格式化文字、插入表格和图表，这些都是基本功。
- 模板化报告系统：通过
ReportGenerator类把报告结构固定下来，以后给数据就能一键出报告，这才是自动化精髓。 - PDF报告生成：用
reportlab也能生成排版规整的PDF，适合需要打印或正式交付的场景。 - 自动化流程：配合
schedule库做定时任务，加上日志记录，整个脚本就能可靠地跑在服务器上，每周自动生成、甚至自动发送邮件。
关键收获：
- 自动化的核心就是“模板+数据”分离，结构固定，数据往里填。
- 好的报告模板既要好看，也要好维护——用颜色常量、方法封装来保持代码清爽。
- 自动化脚本必须带上异常处理和日志，不然出错了你都不知道问题出在哪一步。
