python通过第三方库操作PDF文件的几种常见方法

目录

• 前言
• 一、文本内容提取
• 1.1、pdfplumber提取文本内容
• 1.2、pdfminer提取文本内容
• 二、表格内容提取
• 三、内容拆分
• 四、内容合并
• 五、通过命令工具生成pdf文档
• 5.1 网页内容生成pdf
• 5.2 本地网页内容生成pdf
• 5.3 字符串内容生成pdf
• 总结 

# 安装模块
pip install pdfplumber

import pdfplumber
import os

path = os.getcwd()
filepath = os.path.join(path,"原则.pdf")

with pdfplumber.open(filepath) as pdf:
    for i in range(len(pdf.pages)):
        page = pdf.pages[i]
        print(page.extract_text())

pip install pdfminer3k
pip install pdfminer.six

from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument

fp = open("原则.pdf","rb")
pdfparser = PDFParser(fp)
doc = PDFDocument(pdfparser)

from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams

#pdf资源管理器
resource = PDFResourceManager()

#参数分析器
laparam  = LAParams()

#页面聚合器
device = PDFPageAggregator(resource,laparams=laparam)

#页面解释器
interpreter  = PDFPageInterpreter(resource,device)

from pdfminer.pdfpage import PDFPage

for page in PDFPage.create_pages(doc):
    #使用页面解释器读取
    interpreter.process_page(page)
    
    #使用聚合器来获取内容
    layout = device.get_result()
    
    for out in layout:
        #需要注意的是pdf文件不仅文字，还有图片等内容，
        # 为了避免错误，我们判断是否为文本
        if(hasattr(out,'get_text')):
            print(out.get_text())

import os
import pandas as pd
import pdfplumber

path = os.getcwd()

pdf = pdfplumber.open(os.path.join(path,"table.pdf"))
p0 = pdf.pages[0]
table = p0.extract_table()
df = pd.DataFrame(table[1:],columns=table[0])

print(df)

from PyPDF2 import PdfWriter,PdfReader

def split_pdf(infn,outfn,start,end):
    '''
    :param infn 源pdf路径
    :param outfn 目的pdf路径
    :param start 开始页面
    :param end 结束页面
    return
    '''
    pdf_output = PdfWriter()
    pdf_input = PdfReader(open(infn,"rb"))
    page_count = len(pdf_input.pages)
    
    if end  > page_count:
        end = page_counte
    
    #分割pdf页面，输出新的内容
    for i in range(start,end):
        pdf_output.add_page(pdf_input.pages[i])
    
    pdf_output.write(open(outfn,'wb'))

split_pdf("原则.pdf","原则2.pdf",5,10)

from PyPDF2 import PdfMerger,PdfReader

def merge_pdf(filenames,merge_name,password=None):
    '''
    :param filenames 传递一个文件列表
    :param merge_name 合并后的文件
    :param password 对应的密码列表
    return
    '''
    files = len(filenames)
    pdf_merge = PdfMerger(False)
    
    for i in range(files):
        pdf_reader = PdfReader(open(filenames[i],"rb"))
        if(not pdf_reader):
            return
        pdf_merge.append(pdf_reader)
    
    pdf_merge.write(open(merge_name,"wb"))

merge_pdf(['原则1.pdf','原则2.pdf'],'原则3.pdf')

# 安装pdfkit库
pip install pdfkit

import pdfkit

def url_to_pdf(url, to_file):
    # 将wkhtmltopdf.exe程序绝对路径传入config对象
    path_wkthmltopdf = r'D:\\tool\\wkhtmltopdf\\bin\\wkhtmltopdf.exe'
    config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)
    # 生成pdf文件，to_file为文件路径
    pdfkit.from_url(url, to_file, configuration=config)

    print('完成')

url_to_pdf('https://www.baidu.com','D:\baidu.pdf')

#避免乱码在html文件中，<meta charset="UTF-8">
def html_to_pdf(html, to_file):
    # 将wkhtmltopdf.exe程序绝对路径传入config对象
    path_wkthmltopdf = r'D:\\tool\\wkhtmltopdf\\bin\\wkhtmltopdf.exe'
    config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)
    # 生成pdf文件，to_file为文件路径
    pdfkit.from_file(html, to_file, configuration=config)

html_to_pdf('sample.html','out_2.pdf')

'''将字符串生成pdf文件'''
def str_to_pdf(string, to_file):
    # 将wkhtmltopdf.exe程序绝对路径传入config对象
    path_wkthmltopdf = r'D:\\tool\\wkhtmltopdf\\bin\\wkhtmltopdf.exe'
    config = pdfkit.configuration(wkhtmltopdf=path_wkthmltopdf)
    # 生成pdf文件，to_file为文件路径
    pdfkit.from_string(string, to_file, configuration=config)
    print('完成')

str_to_pdf('This is test!','out_3.pdf')