python讀取pdf文檔

python讀取txt

# coding=utf-8

import requests
# 爬蟲規則
url = "https://en.wikipedia.org/robots.txt"
# 讀取網絡資源
res = requests.get(url).text
# 打印
print(res)

讀取pdf

# coding=utf-8

from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice
from pdfminer.layout import LAParams
from pdfminer.converter import PDFPageAggregator
import requests

# pip install pdfminer3k

# 獲取文檔對象，示例pdf在 https://pypi.org/project/pdfminer3k/1.0.1/#files  下載后的文件夾中 pdfminer3k-master\samples\nonfree
fp = open("naacl06-shinyama.pdf", "rb")

# print(type(fp))

# 創建一個與文檔關聯的解釋器
parser = PDFParser(fp)

# PDF 文檔的對象
doc = PDFDocument()

# 連接解釋器與文檔對象
parser.set_document(doc)
doc.set_parser(parser)

# 初始化文檔
doc.initialize("")

# 創建PDF資源管理器
resource = PDFResourceManager()

# 參數分析器
laparam = LAParams()

# 創建一個聚合器
device = PDFPageAggregator(resource, laparams = laparam)

# 頁面解釋器
interpreter = PDFPageInterpreter(resource, device)

# 使用文檔對象得到頁面的集合
for page in doc.get_pages():
    # 使用頁面解釋器來讀取
    interpreter.process_page(page)

    # 使用聚合器獲得內容
    layout = device.get_result()

    for out in layout:

        if hasattr(out, "get_text"):
            print(out.get_text())