pdfgen.py 文件源码

def pdfgen(relevant_extracts, sector, keywords):
    today = datetime.datetime.today()
    today.replace(second=0, microsecond=0)

    outputdir = join('..', 'output')
    if not exists(outputdir):
        mkdir(outputdir)
    chdir(outputdir)

    doc = SimpleDocTemplate('%s_%s.pdf' % (sector, today.strftime("%Y-%m-%d_%H.%M")))
    template = PageTemplate('normal', [Frame(2.5*cm, 2.5*cm, 15*cm, 25*cm, id='F1')])
    doc.addPageTemplates(template)

    Story = [Spacer(1,0.5*inch)]
    styleSheet=getSampleStyleSheet()
    style = styleSheet['BodyText']
    title = Paragraph('<para align=center><b>%s Industry Earnings Call Transcripts Report</b></para>' % sector,
                      style)
    Story.append(title)
    subtitle = Paragraph('<para align=center>Keywords: %s</para>' % ", ".join(keywords),
                         style)
    Story.append(subtitle)
    Story.append(Spacer(1,0.5*inch))


    for extract in relevant_extracts:
        Story.append(Paragraph("From %s" % extract["title"], h1))
        Story.append(Paragraph("Published on %s at %s" % (extract["date"], extract["time"]), h1))
        text = Preformatted(extract["bodyContent"].encode('utf8'), style, maxLineLength=100)
        Story.append(text)
        Story.append(Spacer(1,0.2*inch))

    doc.build(Story)