$ pip3 install pdfminer

Collecting pdfminerDownloading https://files.pythonhosted.org/packages/71/a3/155c5cde5f9c0b1069043b2946a93f54a41fd72cc19c6c100f6f2f5bdc15/pdfminer-20191125.tar.gz (4.2MB)|████████████████████████████████| 4.2MB 2.8MB/s
Collecting pycryptodome (from pdfminer)Downloading https://files.pythonhosted.org/packages/cc/a6/f7e09ad45296eff20bd1db5aa14b1c9ea06826dd68eb2a7a27572c71d581/pycryptodome-3.9.4-cp37-cp37m-macosx_10_6_intel.whl (10.1MB)|████████████████████████████████| 10.1MB 1.6MB/s
Building wheels for collected packages: pdfminerBuilding wheel for pdfminer (setup.py) ... doneStored in directory: /Users/mjg/Library/Caches/pip/wheels/e1/00/af/720a55d74ba3615bb4709a3ded6dd71dc5370a586a0ff6f326
Successfully built pdfminer
Installing collected packages: pycryptodome, pdfminer
Successfully installed pdfminer-20191125 pycryptodome-3.9.4

# pdf_1.py# 导入库
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator# 设置文档密码
password = ''#打开pdf文件
fp = open('pdfminer.pdf','rb')#从文件句柄创建一个pdf解析对象
parser = PDFParser(fp)#创建pdf文档对象，存储文档结构
document = PDFDocument(parser,password)#创建一个pdf资源管理对象，存储共享资源
rsrcmgr = PDFResourceManager()#创建一个device对象
device = PDFDevice(rsrcmgr)#创建一个解释对象
interpreter = PDFPageInterpreter(rsrcmgr, device)#处理包含在文档中的每一页
for page in PDFPage.create_pages(document):interpreter.process_page(page)

# pdf_2.py# 导入库
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfpage import PDFPage
from pdfminer.pdfpage import PDFTextExtractionNotAllowed
from pdfminer.pdfinterp import PDFResourceManager
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import *
from pdfminer.converter import PDFPageAggregator# 提供初始密码
password = ''
# 没有密码可以初始密码
# document.initialize()#打开pdf文件
fp = open('pdfminer.pdf','rb')#从文件句柄创建一个pdf解析对象
parser = PDFParser(fp)#创建pdf文档对象，存储文档结构
document = PDFDocument(parser, password)#创建一个pdf资源管理对象，存储共享资源
rsrcmgr = PDFResourceManager()laparams = LAParams()#创建一个device对象
device = PDFPageAggregator(rsrcmgr, laparams=laparams)#创建一个解释对象
interpreter = PDFPageInterpreter(rsrcmgr, device)#处理包含在文档中的每一页
for page in PDFPage.create_pages(document):interpreter.process_page(page)layout = device.get_result()for x in layout:# 获取文本对象if isinstance(x, LTTextBox):print(x.get_text().strip())# 获取图片对象if isinstance(x,LTImage):print('这里获取到一张图片')# 获取 figure 对象if isinstance(x,LTFigure):print('这里获取到一个 figure 对象')