python3用pdfminer3k在線讀取pdf文件

 

 

import importlib
import sys
import random
from urllib.request import urlopen
from urllib.request import Request

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

'''
 解析pdf 文本，保存到txt文件中
'''
importlib.reload(sys)

user_agent = ['Mozilla/5.0 (Windows NT 10.0; WOW64)', 'Mozilla/5.0 (Windows NT 6.3; WOW64)',
              'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0',
              'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
              'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
              'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',
              'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',
              'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',
              'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',
              'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',
              'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
              'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',
              'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
              'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',
              'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',
              'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',
              'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',
              'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',
              'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',
              'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',
              'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',
              'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',
              'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']


def parse(_path):
    # fp = open(_path, 'rb')  # rb以二進制讀模式打開本地pdf文件
    request = Request(url=_path, headers={'User-Agent': random.choice(user_agent)})  # 隨機從user_agent列表中抽取一個元素
    fp = urlopen(request) #打開在線PDF文檔

    # 用文件對象來創建一個pdf文檔分析器
    praser_pdf = PDFParser(fp)

    # 創建一個PDF文檔
    doc = PDFDocument()

    # 連接分析器 與文檔對象
    praser_pdf.set_document(doc)
    doc.set_parser(praser_pdf)

    # 提供初始化密碼doc.initialize("123456")
    # 如果沒有密碼 就創建一個空的字符串
    doc.initialize()

    # 檢測文檔是否提供txt轉換，不提供就忽略
    if not doc.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        # 創建PDf資源管理器 來管理共享資源
        rsrcmgr = PDFResourceManager()

        # 創建一個PDF參數分析器
        laparams = LAParams()

        # 創建聚合器
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)

        # 創建一個PDF頁面解釋器對象
        interpreter = PDFPageInterpreter(rsrcmgr, device)

        # 循環遍歷列表，每次處理一頁的內容
        # doc.get_pages() 獲取page列表
        for page in doc.get_pages():
            # 使用頁面解釋器來讀取
            interpreter.process_page(page)

            # 使用聚合器獲取內容
            layout = device.get_result()

            # 這里layout是一個LTPage對象 里面存放着 這個page解析出的各種對象 一般包括LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等等 想要獲取文本就獲得對象的text屬性，
            for out in layout:
                # 判斷是否含有get_text()方法，圖片之類的就沒有
                # if hasattr(out,"get_text"):
                if isinstance(out, LTTextBoxHorizontal):

                    results = out.get_text()
                    print("results: " + results)
if __name__ == '__main__':
    url = "http://www.caac.gov.cn/XXGK/XXGK/TJSJ/201708/P020170821330916187824.pdf"
    parse(url)