word文档内的一页：
将文本取出来，生成自定义格式的PDF文件：
从word取出文本时标题的标号和页码是取不出来的，要自己加。另外就是目录也要自己生成和添加：
代码和解释如下：
from reportlab.lib.styles import ParagraphStyle as PS# 段落格式from reportlab.platypus import PageBreak# 分页符from reportlab.platypus.paragraph import Paragraph# 生成段落用from reportlab.platypus.doctemplate import PageTemplate, BaseDocTemplate # 用于生成页面模版，文档模版from reportlab.platypus.tableofcontents import TableOfContents# 用于生成目录from reportlab.platypus.frames import Frame# 生成页面模版是定义页面内的框架framefrom reportlab.lib.units import cm, inch# 尺度单位# 注册中文字体from reportlab.pdfbase.ttfonts import TTFontfrom reportlab.pdfbase import pdfmetricspdfmetrics.registerFont(TTFont("lively", "/Library/Fonts/Chinese/ChaoZiSheZengYuBoShouShuJian-2.ttf"))pdfmetrics.registerFont(TTFont("apple", "/Library/Fonts/Chinese/XiaoHuYao-2.ttf"))# 定义标题、普通段落和代码的段落格式h1 = PS(name = "Heading1", fontSize = 16, leading = 24, fontName = "lively", spaceAfter = 15)h2 = PS(name = "Heading2", fontSize = 14, leading = 20, leftIndent = 10, fontName = "lively", spaceBefore = 10, spaceAfter = 10)h3 = PS(name = "Heading3", fontSize = 12, leading = 16, leftIndent = 20, fontName = "lively", spaceBefore = 10, spaceAfter = 10)normalText = PS(name = "normal", fontSize = 12, leading = 14, firstLineIndent = 25, fontName = "apple")code = PS(name = "code", fontSize = 10, leading = 14, leftIndent = 35,fontName = "apple")class MyDocTemplate(BaseDocTemplate):# 是BaseDocTemplate的子类def __init__(self, filename, **kw):BaseDocTemplate.__init__(self, filename, **kw)template = PageTemplate("normal", [Frame(2.5*cm, 2.5*cm, 15*cm, 25*cm,)], onPageEnd=self.footer)# 定义页面模版，页脚可有可无self.addPageTemplates(template)# 加入页面模版# 打开word取出文字内容，生成段落flowable放进storydef feedContent(self, filename, story):from docx import Document # 帮忙处理word文档docWord = Document(filename)# 打开word文档，生成word文档对象h1Num = 0; h2Num = 0; h3Num = 0# 因为要给标题加序号，三级序号，所以用变量记录所在层级的序号for para in docWord.paragraphs:# 遍历word文档的各个段落docStyle = para.style.name# 取出word文档中的段落格式if docStyle == "Heading 1":# 如果是第一级标题，先加上序号再填进storyh1Num += 1# 标记第一级标题的序号增1seq = str(h1Num) + "、 "# 第一级标题的格式为1、story.append(Paragraph(seq + para.text, h1)) # 生成段落followable加入storyelif docStyle == "Heading 2": # 第二级标题h2Num += 1# 标记第二级标题的序号增1seq = str(h1Num) + "." + str(h2Num) + " "# 第二级标题格式1.1story.append(Paragraph(seq + para.text, h2))elif docStyle == "Heading 3": # 第三级标题h3Num+=1#标记第三级标题的序号增1seq = str(h1Num) + "." + str(h2Num) + "." + str(h3Num) + " "# 第三级标题的序号1.1.1story.append(Paragraph(seq + para.text, h3))elif docStyle == "Code":# 普通段落和代码直接填进story，对代码的处理效果不理想story.append(Paragraph(para.text, code))else:story.append(Paragraph(para.text, normalText))# 生成一个flowable后判断是否为标题，是标题填进目录，二三级目录生成书签链接def afterFlowable(self, flowable): # 注册目录的条目if flowable.__class__.__name__ == "Paragraph":text = flowable.getPlainText()# 取出文字style = flowable.style.name # 取出段落格式if style == "Heading1": # 第一级标题self.notify("TOCEntry", (0, text, self.page))if style == "Heading2": # 第二级标题key = "h2-{}".format(self.seq.nextf("heading2")) # 生成书签名self.canv.bookmarkPage(key)# 生成书签页self.notify("TOCEntry", (1, text, self.page, key))# "TOCEntry"：通知类型；(1, text, self.page, key)：# （目录层级、文本内容、当前页数、可选的书签名）if style == "Heading3": # 第三级标题key = "h3-{}".format(self.seq.nextf("heading3"))self.canv.bookmarkPage(key)self.notify("TOCEntry", (2, text, self.page, key))# 页脚给出第几页def footer(self, myCanvas, myDoc):myCanvas.setFont("lively",10) # 设置字体myCanvas.drawRightString(7.6*inch,.5*inch, "{}".format(self.page))# 画页脚toc = TableOfContents()# 生成目录对象toc.levelStyles = [h1, h2, h3]# 定义目录的格式，三层，每层的格式用段落格式定义story = []# 列表story存放生成的各个flowablestory.append(toc)# 将目录对象填进story，此时目录只是架子，内容还没填进去story.append(PageBreak()) # 分页符docPDF = MyDocTemplate("mintoc.pdf")# 生成PDF文档对象docPDF.feedContent("excerpt.docx", story)# 打开word文档，取出内容生成flowable放进story中docPDF.multiBuild(story)# 这个文档的生成要过两遍，第一遍加了个目录的空架子，# 文档内容生成之后才能把目录内容填进去，所以用multiBuild()而不是build()
