python 使用pdfkit生成

用python生成pdf，记录一下。

import pdfkit
import json
import requests
import time
import os
from PyPDF2 import PdfFileReader, PdfFileWriter
from reportlab.lib.units import cm
from reportlab.pdfgen import canvas


# 将wkhtmltopdf.exe程序绝对路径传入config对象
path_wkthmltopdf = r'D:\\Program Files\\wkhtmltopdf\\bin\\wkhtmltopdf.exe'
config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)
pdfkit_options = {'encoding': 'UTF-8'}
filename="daytest.pdf"
str_content=""
contents=""
description=""
def start(offset_dynamic_id):
    global str_content,contents,description
    url="https://api.vc.bilibili.com/dynamic_svr/v1/dynamic_svr/space_history?visitor_uid=283857977&host_uid=192450084&offset_dynamic_id="+str(offset_dynamic_id)+"&need_top=1&platform=web"
    headers={
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"
    }
    r=requests.get(url,headers=headers)
    r.encoding="utf8"
    j=json.loads(r.text)
    lens_cards = len(j['data']['cards'])
    tmp=""
    for i in range(lens_cards-1,-1,-1):
        jj=json.loads(j['data']['cards'][i]['card'])
        if 'item' in jj:
            if 'timestamp' in jj['item']:
                timestamp=jj['item']['timestamp']
                timeArray = time.localtime(timestamp)
                formatTime = time.strftime("%Y-%m-%d", timeArray)
                print (formatTime)
            if 'upload_time' in jj['item']:
                timestamp=jj['item']['upload_time']
                timeArray = time.localtime(timestamp)
                formatTime = time.strftime("%Y-%m-%d", timeArray)
                print (formatTime)
            if 'content' in jj['item'] and "每日一题" in str(jj['item']['content']):
                contents=jj['item']['content'].replace("\n","<br>")
                print(contents)
            if 'description' in jj['item'] and "解析" in str(jj['item']['description']):
                description = jj['item']['description'].replace("\n","<br>")
                print(description)
            if 'pictures' in jj['item']:
                pictures= jj['item']['pictures']
                lens_pic=len(pictures)
                print(pictures[0]['img_src'])
                for pic in range(0,lens_pic):
                    pic_url=pictures[pic]['img_src']
                    print(pic_url)
                    savepic(formatTime,pic_url,pic)
            finalcontent = str(contents)+ '<br>' +str(description)+ '<br>'
            if finalcontent != tmp:
                str_content = str(str_content)+'<br>' + '<br>' + str(formatTime)+ '<br>' + str(finalcontent)
            tmp = finalcontent
            print('--------------------')
            time.sleep(2)
    pdfkit.from_string(str_content,filename,configuration=config, options=pdfkit_options)    

def savepic(filename,imgurl,picname):
    if os.path.exists("./jx/"+filename):
        print('exists file！！！')
    else:
        os.makedirs("./jx/"+filename)
    r=requests.get(imgurl).content
    with open("./jx/"+str(filename)+"/"+str(picname)+'.jpg',"wb") as f:
        f.write(r)


def create_watermark(content):
    """水印信息"""
    # 默认大小为21cm*29.7cm
    file_name = "mark.pdf"
    c = canvas.Canvas(file_name, pagesize=(21 * cm, 29.7 * cm))
    # 移动坐标原点(坐标系左下为(0,0))
    c.translate(5 * cm, 10 * cm)
 
    # 设置字体
    c.setFont("Helvetica", 80)
    # 指定描边的颜色
    c.setStrokeColorRGB(0, 1, 0)
    # 指定填充颜色
    c.setFillColorRGB(0, 1, 0)
    # 画一个矩形
    # c.rect(cm, cm, 7*cm, 17*cm, fill=1)
    # 旋转45度,坐标系被旋转
    c.rotate(30)
    # 指定填充颜色
    c.setFillColorRGB(0, 0, 0, 0.1)
    # 设置透明度,1为不透明
    # c.setFillAlpha(0.1)
    # 画几个文本,注意坐标系旋转的影响
    c.drawString(3 * cm, 0 * cm, content)
    c.setFillAlpha(0.6)
    # 关闭并保存pdf文件
    c.save()
    return file_name
 
 
def add_watermark(pdf_file_in, pdf_file_mark, pdf_file_out):
    """把水印添加到pdf中"""
    pdf_output = PdfFileWriter()
    input_stream = open(pdf_file_in, 'rb')
    pdf_input = PdfFileReader(input_stream, strict=False)
 
    # 获取PDF文件的页数
    pageNum = pdf_input.getNumPages()
 
    # 读入水印pdf文件
    pdf_watermark = PdfFileReader(open(pdf_file_mark, 'rb'), strict=False)
    # 给每一页打水印
    for i in range(pageNum):
        page = pdf_input.getPage(i)
        page.mergePage(pdf_watermark.getPage(0))
        page.compressContentStreams()  # 压缩内容
        pdf_output.addPage(page)
    pdf_output.write(open(pdf_file_out, 'wb'))
 
if __name__ == '__main__':
    offset_dynamic_id=[
    '596643666922248396',
    '597941412765972945',
    '599613099937925403','601272168487401677',
    '602762930168798777','603950931004835873',
    '605354350221887065','607034021734160739',
    '610773503734780835','612563418471648514',
    '613902958643821419','615852422824317201',
    '616876308669489985','618509839342691948',
    '620733258013494055','623340530794036514',
    '625219514568319250','627047177770485970',
    '628773067432125784','630017972369358854',
    '632081467918254103','634110127014674434',
    '635942952759197713','636984997739233283',
    '638180106740695049','640274045016735745',
    '642094170555547656','643378455991287863',
    '645447419045085191','646665497531645972',
    '648165540655792160','650078922962108425',
    '652285565245325316','0'
    ]
    for i in range(0,len(offset_dynamic_id)):
        start(offset_dynamic_id[i])
    pdf_file_in = filename
    pdf_file_out = filename+'_watermark.pdf'
    pdf_file_mark = create_watermark('marks')
    add_watermark(pdf_file_in, pdf_file_mark, pdf_file_out)

效果

唯一不理想的是，pdfkit不能自己在pdf中插入图片！