python读取pdf文件获取pdf的文本内容

python处理pdf文件的所有库 , https://stackabuse.com/working-with-pdfs-in-python-reading-and-splitting-pages/
一下是我列举的几种我所使用的库的简单用法,供大家参考
安装PyPDF2 , pip install PyPDF2

import PyPDF2
from urllib.request import urlopen

file = open('D:/ltn20190716133.pdf', 'rb')

fileReader = PyPDF2.PdfFileReader(file)
#pdf page numbers totals
print(fileReader.numPages)
#get 172 page text
pageObj = fileReader.getPage(172)
print(pageObj.extractText())

安装pdfplumber, pip install pdfplumber
一些常用的方法
.extract_text() 用来提页面中的文本，将页面的所有字符对象整理为的那个字符串
.extract_words() 返回的是所有的单词及其相关信息
.extract_tables() 提取页面的表格
.to_image() 用于可视化调试时，返回PageImage类的一个实例

import pdfplumber

with pdfplumber.open("D:\\com.pdf") as pdf:
    page_count = len(pdf.pages)
    print(page_count)
    for page in pdf.pages:
        print('---------- 第[%d]页 ----------' % page.page_number)
        print(page.extract_text())

import pdfplumber
path = 'D:/ltn201904301249.pdf'
pdf = pdfplumber.open(path)
for page in pdf.pages:
     # 获取当前页面的全部文本信息，包括表格中的文字
     print(page.extract_text())
pdf.close()

安装PyMuPDF, pip install PyMuPDF
参考文档:https://pymupdf.readthedocs.io/en/latest/document/#document

import fitz

doc = fitz.open(r"D:\ltn20190906213.pdf")
print(doc.pageCount)  #获取总页数
print(doc.getPageText(12))  #获取pdf文件12页文本
for page in doc:
    t = page.getText()
    print(t)

pdfminer ,安装pip install pdfminer3k

from urllib.request import urlopen
from io import StringIO
from pdfminer.pdfinterp import PDFResourceManager, process_pdf
from pdfminer.converter import TextConverter
from pdfminer.layout import  LAParams
import logging
import re

def readPdf(pdf_file):
    logging.propagate = False
    logging.getLogger().setLevel(logging.ERROR)
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    laparams = LAParams()
    device = TextConverter(rsrcmgr=rsrcmgr, outfp=retstr, laparams=laparams)

    process_pdf(rsrcmgr=rsrcmgr, device=device, fp=pdf_file)
    device.close()

    content = retstr.getvalue()
    retstr.close()

    return content

url = "https://www1.sehk/2019/0430/ltn201904301249.pdf"
pdf_file = urlopen(url) # 也可以换成本地pdf文件，用open rb模式打开
print(pdf_file)
content = readPdf(pdf_file)
s = r'(\n|\r|\xa0|/s/|\t| |&#\d*;)'
body = re.sub(s,' ',content)
print(body.replace(' ',' '))
pdf_file.close()

下载网页pdf文件到本地的两种方法
第一种使用requests下载

import requests

url = 'https://www1.sehk/2019/0430/ltn201904301249.pdf'
r = requests.get(url)
pdf = r.content      
with open('aa.pdf','wb') as f:     
    f.write(pdf)

第二种使用urllib

import urllib.request
import re
import os



def getFile(url):
    file_name = url.split('/')[-1]
    u = urllib.request.urlopen(url)
    f = open(file_name, 'wb')

    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break

        f.write(buffer)
    f.close()
    print ("Sucessful to download" + " " + file_name)


getFile("https://www1.sehk/2019/0430/ltn201904301249.pdf")

windows下生成将pdf文件生成图片

-- coding: utf-8 --

"""
1、安装库  pip install pymupdf
2、直接运行
"""
import fitz

#  打开PDF文件，生成一个对象
doc = fitz.open(r'D:/简历/王.pdf')

for pg in range(doc.pageCount):
    page = doc[pg]
    rotate = int(0)
    # 每个尺寸的缩放系数为2，这将为我们生成分辨率提高四倍的图像。
    zoom_x = 2.0
    zoom_y = 2.0
    trans = fitz.Matrix(zoom_x, zoom_y).preRotate(rotate)
    pm = page.getPixmap(matrix=trans, alpha=False)
    pm.writePNG('%s.jpg' % pg)