python - ReportLab 是否有可流动的 matplotlib？

Question

我想将 matplotlib 图表直接嵌入到 ReportLab 生成的 PDF 中——即不先保存为 PNG，然后将 PNG 嵌入到 PDF 中（我想我会得到更好的输出质量）。

有谁知道是否有可用于 ReportLab 的 matplotlib？

谢谢

Answer 1

这是使用pdfrw的解决方案：

#!/usr/bin/env python
# encoding: utf-8
"""matplotlib_example.py
   An simple example of how to insert matplotlib generated figures
   into a ReportLab platypus document.
"""

import matplotlib
matplotlib.use('PDF')
import matplotlib.pyplot as plt
import cStringIO

from pdfrw import PdfReader
from pdfrw.buildxobj import pagexobj
from pdfrw.toreportlab import makerl

from reportlab.platypus import Flowable
from reportlab.lib.enums import TA_LEFT, TA_CENTER, TA_RIGHT
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.rl_config import defaultPageSize
from reportlab.lib.units import inch

PAGE_HEIGHT=defaultPageSize[1]; PAGE_WIDTH=defaultPageSize[0]
styles = getSampleStyleSheet()

class PdfImage(Flowable):
    """PdfImage wraps the first page from a PDF file as a Flowable
which can be included into a ReportLab Platypus document.
Based on the vectorpdf extension in rst2pdf (http://code.google.com/p/rst2pdf/)"""

    def __init__(self, filename_or_object, width=None, height=None, kind='direct'):
        from reportlab.lib.units import inch
        # If using StringIO buffer, set pointer to begining
        if hasattr(filename_or_object, 'read'):
            filename_or_object.seek(0)
        page = PdfReader(filename_or_object, decompress=False).pages[0]
        self.xobj = pagexobj(page)
        self.imageWidth = width
        self.imageHeight = height
        x1, y1, x2, y2 = self.xobj.BBox

        self._w, self._h = x2 - x1, y2 - y1
        if not self.imageWidth:
            self.imageWidth = self._w
        if not self.imageHeight:
            self.imageHeight = self._h
        self.__ratio = float(self.imageWidth)/self.imageHeight
        if kind in ['direct','absolute'] or width==None or height==None:
            self.drawWidth = width or self.imageWidth
            self.drawHeight = height or self.imageHeight
        elif kind in ['bound','proportional']:
            factor = min(float(width)/self._w,float(height)/self._h)
            self.drawWidth = self._w*factor
            self.drawHeight = self._h*factor

    def wrap(self, aW, aH):
        return self.drawWidth, self.drawHeight

    def drawOn(self, canv, x, y, _sW=0):
        if _sW > 0 and hasattr(self, 'hAlign'):
            a = self.hAlign
            if a in ('CENTER', 'CENTRE', TA_CENTER):
                x += 0.5*_sW
            elif a in ('RIGHT', TA_RIGHT):
                x += _sW
            elif a not in ('LEFT', TA_LEFT):
                raise ValueError("Bad hAlign value " + str(a))

        xobj = self.xobj
        xobj_name = makerl(canv._doc, xobj)

        xscale = self.drawWidth/self._w
        yscale = self.drawHeight/self._h

        x -= xobj.BBox[0] * xscale
        y -= xobj.BBox[1] * yscale

        canv.saveState()
        canv.translate(x, y)
        canv.scale(xscale, yscale)
        canv.doForm(xobj_name)
        canv.restoreState()

Title = "Hello world"
pageinfo = "platypus example"
def myFirstPage(canvas, doc):
    canvas.saveState()
    canvas.setFont('Times-Bold',16)
    canvas.drawCentredString(PAGE_WIDTH/2.0, PAGE_HEIGHT-108, Title)
    canvas.setFont('Times-Roman',9)
    canvas.drawString(inch, 0.75 * inch, "First Page / %s" % pageinfo)
    canvas.restoreState()


def myLaterPages(canvas, doc):
    canvas.saveState()
    canvas.setFont('Times-Roman',9)
    canvas.drawString(inch, 0.75 * inch, "Page %d %s" % (doc.page, pageinfo))
    canvas.restoreState()

def go():
    fig = plt.figure(figsize=(4, 3))
    plt.plot([1,2,3,4])
    plt.ylabel('some numbers')
    imgdata = cStringIO.StringIO()
    fig.savefig(imgdata,format='PDF')
    doc = SimpleDocTemplate("document.pdf")
    Story = [Spacer(1,2*inch)]
    style = styles["Normal"]
    for i in range(5):
        bogustext = ("This is Paragraph number %s.  " % i) *20
        p = Paragraph(bogustext, style)
        Story.append(p)
        Story.append(Spacer(1,0.2*inch))
        pi = PdfImage(imgdata)
        Story.append(pi)
        Story.append(Spacer(1,0.2*inch))
    doc.build(Story, onFirstPage=myFirstPage, onLaterPages=myLaterPages)


if __name__ == '__main__':
    go()

Answer 2

没有，但我自己使用带有 ReportLab 的 MatPlotLib 时所做的是生成 PNG，然后嵌入 PNG，这样我就不需要也使用 PIL。但是，如果您确实使用 PIL，我相信您应该能够使用 MatPlotLib 和 ReportLab 生成和嵌入 EPS。

Answer 3

pdfrw 的作者Patrick Maupin在另一个问题中提供了一个更简单、更简单的答案。（感谢他对我之前的回答的客气话。）他还提到，在使用 pdfrw 提取它们之前将 matplotlib 图形保存到多页 PDF 将通过减少重复资源来减小最终 reportlab PDF 的大小。因此，这是对他的代码示例的修改，该示例演示了如何通过首先写入多页 matplotlib PDF 来减小 PDF 文件的大小。对于此示例，文件大小减少了大约 80%。

注意：这是专门用于 matplotlib 图形的。

import os
from matplotlib import pyplot as plt
from matplotlib.backends.backend_pdf import PdfPages
from reportlab.platypus import Paragraph, SimpleDocTemplate, Spacer, Flowable
from reportlab.lib.units import inch
from reportlab.lib.styles import getSampleStyleSheet

from pdfrw import PdfReader, PdfDict
from pdfrw.buildxobj import pagexobj
from pdfrw.toreportlab import makerl

try:
    from cStringIO import StringIO as BytesIO
except ImportError:
    from io import BytesIO

styles = getSampleStyleSheet()
style = styles['Normal']


class PdfImage(Flowable):
    """
    Generates a reportlab image flowable for matplotlib figures. It is initialized
    with either a matplotlib figure or a pointer to a list of pagexobj objects and
    an index for the pagexobj to be used.
    """
    def __init__(self, fig=None, width=200, height=200, cache=None, cacheindex=0):
        self.img_width = width
        self.img_height = height
        if fig is None and cache is None:
            raise ValueError("Either 'fig' or 'cache' must be provided")
        if fig is not None:
            imgdata = BytesIO()
            fig.savefig(imgdata, format='pdf')
            imgdata.seek(0)
            page, = PdfReader(imgdata).pages
            image = pagexobj(page)
            self.img_data = image
        else:
            self.img_data = None
        self.cache = cache
        self.cacheindex = cacheindex

    def wrap(self, width, height):
        return self.img_width, self.img_height

    def drawOn(self, canv, x, y, _sW=0):
        if _sW > 0 and hasattr(self, 'hAlign'):
            a = self.hAlign
            if a in ('CENTER', 'CENTRE', TA_CENTER):
                x += 0.5*_sW
            elif a in ('RIGHT', TA_RIGHT):
                x += _sW
            elif a not in ('LEFT', TA_LEFT):
                raise ValueError("Bad hAlign value " + str(a))
        canv.saveState()
        if self.img_data is not None:
            img = self.img_data
        else:
            img = self.cache[self.cacheindex]
        if isinstance(img, PdfDict):
            xscale = self.img_width / img.BBox[2]
            yscale = self.img_height / img.BBox[3]
            canv.translate(x, y)
            canv.scale(xscale, yscale)
            canv.doForm(makerl(canv, img))
        else:
            canv.drawImage(img, x, y, self.img_width, self.img_height)
        canv.restoreState()


class PdfImageCache(object):
    """
    Saves matplotlib figures to a temporary multi-page PDF file using the 'savefig'
    method. When closed the images are extracted and saved to the attribute 'cache'.
    The temporary PDF file is then deleted. The 'savefig' returns a PdfImage object
    with a pointer to the 'cache' list and an index for the figure. Use of this
    cache reduces duplicated resources in the reportlab generated PDF file.

    Use is similar to matplotlib's PdfPages object. When not used as a context
    manager, the 'close()' method must be explictly called before the reportlab
    document is built.
    """
    def __init__(self):
        self.pdftempfile = '_temporary_pdf_image_cache_.pdf'
        self.pdf = PdfPages(self.pdftempfile)
        self.cache = []
        self.count = 0

    def __enter__(self):
        return self

    def __exit__(self, *args):
        self.close()

    def close(self, *args):
        self.pdf.close()
        pages = PdfReader(self.pdftempfile).pages
        pages = [pagexobj(x) for x in pages]
        self.cache.extend(pages)
        os.remove(self.pdftempfile)

    def savefig(self, fig, width=200, height=200):
        self.pdf.savefig(fig)
        index = self.count
        self.count += 1
        return PdfImage(width=width, height=height, cache=self.cache, cacheindex=index)


def make_report(outfn, nfig=5):
    """
    Makes a dummy report with nfig matplotlib plots.
    """

    doc = SimpleDocTemplate(outfn)
    style = styles["Normal"]
    story = [Spacer(0, inch)]

    for j in range(nfig):

        fig = plt.figure(figsize=(4, 3))
        plt.plot([1, 2, 3, 4], [1, 4, 9, 26])
        plt.ylabel('some numbers')
        plt.title('My Figure %i' % (j+1))
        img = PdfImage(fig, width=400, height=400)
        plt.close()

        for i in range(10):
            bogustext = ("Paragraph number %s. " % i)
            p = Paragraph(bogustext, style)
            story.append(p)
            story.append(Spacer(1, 0.2*inch))

        story.append(img)

        for i in range(10):
            bogustext = ("Paragraph number %s. " % i)
            p = Paragraph(bogustext, style)
            story.append(p)
            story.append(Spacer(1, 0.2*inch))

    doc.build(story)


def make_report_cached_figs(outfn, nfig=5):
    """
    Makes a dummy report with nfig matplotlib plots using PdfImageCache
    to reduce PDF file size.
    """

    doc = SimpleDocTemplate(outfn)
    style = styles["Normal"]
    story = [Spacer(0, inch)]

    with PdfImageCache() as pdfcache:
        for j in range(nfig):

            fig = plt.figure(figsize=(4, 3))
            plt.plot([1, 2, 3, 4], [1, 4, 9, 26])
            plt.ylabel('some numbers')
            plt.title('My Figure %i' % (j+1))
            img = pdfcache.savefig(fig, width=400, height=400)
            plt.close()

            for i in range(10):
                bogustext = ("Paragraph number %s. " % i)
                p = Paragraph(bogustext, style)
                story.append(p)
                story.append(Spacer(1, 0.2*inch))

            story.append(img)

            for i in range(10):
                bogustext = ("Paragraph number %s. " % i)
                p = Paragraph(bogustext, style)
                story.append(p)
                story.append(Spacer(1, 0.2*inch))

    doc.build(story)


make_report("hello_pdf.pdf", 50)
make_report_cached_figs("hello_pdf_cached_figs.pdf", 50)

由于 matplotlib 的 PdfPages 仅将文件路径作为输入，因此 PdfImageCache 对象将多页 PDF 写入临时文件。尝试在内存中执行此操作将需要更多的工作。

Answer 4

Python 3 的解决方案，并将 matplotlib 图嵌入为矢量图像（无光栅化）

import matplotlib.pyplot as plt
from io import BytesIO
from reportlab.pdfgen import canvas
from reportlab.graphics import renderPDF
from svglib.svglib import svg2rlg

fig = plt.figure(figsize=(4, 3))
plt.plot([1,2,3,4])
plt.ylabel('some numbers')

imgdata = BytesIO()
fig.savefig(imgdata, format='svg')
imgdata.seek(0)  # rewind the data

drawing=svg2rlg(imgdata)

c = canvas.Canvas('test2.pdf')
renderPDF.draw(drawing,c, 10, 40)
c.drawString(10, 300, "So nice it works")
c.showPage()
c.save()

svglib可从 conda-forge 获得。