Python读取pdf文件的简单代码示例

pip install pdfminer3K

import sys
import importlib
importlib.reload(sys)

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import  PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal, LAParams
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed

import sys
import importlib

importlib.reload(sys)

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LTTextBoxHorizontal, LAParams
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
import os

def read_pdf(path, toPath):
    # 以二进制方式打开pdf文件
    f = open(path, 'rb')

    # 创建一个pdf文档分析器
    parser = PDFParser(f)
    # 创建pdf文档
    pdfFile = PDFDocument()
    # 链接分析器与文档对象
    parser.set_document(pdfFile)
    pdfFile.set_parser(parser)
    # 提供初始化密码
    pdfFile.initialize()

    # 检测文档是否提供txt转换
    if not pdfFile.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        # 解析数据
        # 数据管理器
        manager = PDFResourceManager()
        # 创建一个PDF设备对象
        laparams = LAParams()
        device = PDFPageAggregator(manager, laparams=laparams)
        # 解释器对象
        interpreter = PDFPageInterpreter(manager, device)
        for page in pdfFile.get_pages():
            interpreter.process_page(page)
            layout = device.get_result()
            for x in layout:
                if isinstance(x, LTTextBoxHorizontal):
                    with open(toPath, 'a', encoding='utf-8') as f:
                        print(x.get_text())
                        f.write(x.get_text() + "\n")

path = os.path.join(os.getcwd(), 'test_1.pdf')
toPath = os.path.join(os.getcwd(), 'test_2.txt')
read_pdf(path, toPath)

import pdfplumber  # 导入库
import jieba
from wordcloud import WordCloud
import numpy as np
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
# 用pdf文件解析器读取文件
with pdfplumber.open('中华文化.pdf') as f:
    # 用for循环读取文件中的每一页
    for page in f.pages:
        text = page.extract_text()
        txt_f = open(r'中华文化.txt', mode='a', encoding='utf-8')  # 创建txt文件
        txt_f.write(text)  # 写入txt文件
 
file = open('中华文化.txt',encoding='utf-8')
file = file.read()  #读取txt文件
txtlist = jieba.lcut(file) 
string = " ".join(txtlist) 
stop_words = {}  
counts = {}  
for txt in txtlist:
    if len(txt) == 1:  
        stop_words[txt] = stop_words.get(txt, 0) + 1
    else:
        counts[txt] = counts.get(txt, 0) + 1 
items = list(counts.items())
items.sort(key=lambda x: x[1], reverse=True)  
y1 = []
labels = []
for i in range(1,10):
    y1.append(items[i][1])
    labels.append(items[i][0])
# plt.figure(figsize=(8,4))
width = 0.3
x = np.arange(len(y1))
a = [i for i in range(0,9)]
plt.xticks(a,labels,rotation = 30)
plt.bar(x=x,height=y1,width=width)
plt.title('PDF文件中热词统计分析')
plt.savefig("热词统计分析.png")
plt.show()
print("-------热词统计分析完成！-------")
stoplist=[]   
item = list(stop_words.items())
for i in range(len(item)): 
    txt,count = item[i]
    stoplist.append(txt)  
#print(stoplist)
setlist = set(stoplist)  
wcd = WordCloud(width=1000, height=700, background_color='white', font_path='msyh.ttc', scale=15, stopwords=setlist)
wcd.generate(string)
wcd.to_image()
print("-------热词词云生成完成！-------")
wcd.to_file('词云.png')  # 导出图片