zoukankan      html  css  js  c++  java
  • Python3.x:PDFMiner3k在线、本地解析pdf

    Python3.x:PDFMiner3k在线、本地解析pdf

    安装

    pip install pdfminer3k

    示例一:在线解析pdf

    '''
        Demo:pdf2htmlex解析pdf
        Datetime:2018-02-22 15:30:00
    '''
    
    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以二进制读模式打开本地pdf文件
        request = Request(url=_path, headers={'User-Agent': random.choice(user_agent)})  # 随机从user_agent列表中抽取一个元素
        fp = urlopen(request) #打开在线PDF文档
        # 用文件对象来创建一个pdf文档分析器
        praser_pdf = PDFParser(fp)
        # 创建一个PDF文档
        doc = PDFDocument()
        # 连接分析器 与文档对象
        praser_pdf.set_document(doc)
        doc.set_parser(praser_pdf)
        # 提供初始化密码doc.initialize("123456")
        # 如果没有密码 就创建一个空的字符串
        doc.initialize()
    
        # 检测文档是否提供txt转换,不提供就忽略
        if not doc.is_extractable:
            raise PDFTextExtractionNotAllowed
        else:
            # 创建PDf资源管理器 来管理共享资源
            rsrcmgr = PDFResourceManager()
            # 创建一个PDF参数分析器
            laparams = LAParams()
            # 创建聚合器
            device = PDFPageAggregator(rsrcmgr, laparams=laparams)
            # 创建一个PDF页面解释器对象
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            # 循环遍历列表,每次处理一页的内容
            # doc.get_pages() 获取page列表
            for page in doc.get_pages():
                # 使用页面解释器来读取
                interpreter.process_page(page)
    
                # 使用聚合器获取内容
                layout = device.get_result()
    
                # 这里layout是一个LTPage对象 里面存放着 这个page解析出的各种对象 一般包括LTTextBox, LTFigure, LTImage, LTTextBoxHorizontal 等等 想要获取文本就获得对象的text属性,
                for out in layout:
                    # 判断是否含有get_text()方法,图片之类的就没有
                    # if hasattr(out,"get_text"):
                    if isinstance(out, LTTextBoxHorizontal):
    
                        results = out.get_text()
                        print("results: " + results)
    if __name__ == '__main__':
        url = "http://******/201707/P020170717564197883913.pdf"
        parse(url)

    示例二:解析本地pdf

    '''
        Demo:pdf2htmlex解析pdf
        Datetime:2018-02-22 15:30:00
        Author:lizm
    '''
    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)
    
    def parseLocal(path_):
        fp = open(path_, 'rb')  # 以二进制读模式打开
        # 用文件对象来创建一个pdf文档分析器
        praser_pdf = PDFParser(fp)
        # 创建一个PDF文档
        doc = PDFDocument()
        # 连接分析器 与文档对象
        praser_pdf.set_document(doc)
        doc.set_parser(praser_pdf)
        # 提供初始化密码doc.initialize("123456")
        # 如果没有密码 就创建一个空的字符串
        doc.initialize()
        # 检测文档是否提供txt转换,不提供就忽略
        if not doc.is_extractable:
            raise PDFTextExtractionNotAllowed
        else:
            # 创建PDf资源管理器 来管理共享资源
            rsrcmgr = PDFResourceManager()
            # 创建一个PDF参数分析器
            laparams = LAParams()
            # 创建聚合器
            device = PDFPageAggregator(rsrcmgr, laparams=laparams)
            # 创建一个PDF页面解释器对象
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            pageCount = 0
            # 循环遍历列表,每次处理一页的内容
            # doc.get_pages() 获取page列表
            for page in doc.get_pages():
                # 使用页面解释器来读取
                interpreter.process_page(page)
                pageCount = pageCount +1
                # 使用聚合器获取内容
                layout = device.get_result()
                count = 0
                # 这里layout是一个LTPage对象 里面存放着 这个page解析出的各种对象 一般包括LTTextBox, LTFigure,
                # LTImage, LTTextBoxHorizontal 等等 想要获取文本就获得对象的text属性,
                for out in layout:
                    count = count + 1
                    # 判断是否含有get_text()方法,图片之类的就没有
                    # if hasattr(out,"get_text"):
                    if isinstance(out, LTTextBoxHorizontal):
                        results = out.get_text()
                        results = results.strip().replace(' ', '').replace(',', '').replace('
    ', '|')
                        print("results:(%s/%s):%s " % (count, pageCount,results))
    
    if __name__ == '__main__':
        path_ = 'E:SublimeWorksprojectdemoP020170717564197883913.pdf'
        parseLocal(path_)

    注意:PDFMiner3k对表格数据支持不太友好,可以用pdf2htmlwx(非python第三方库)将pdf转为html,然后在解析html;

    使用过程中出现:

    pdfminer与日志配置代码有冲突:
    #日志配置代码
    logger = logging.getLogger()
    #set loghandler
    file = logging.FileHandler(sys.path[0]+"py_sac_log"+time.strftime("%Y%m%d")+".log")
    logger.addHandler(file)
    #set formater
    formatter = logging.Formatter("%(asctime)s %(levelname)s %(message)s")
    file.setFormatter(formatter) 
    #set log level
    logger.setLevel(logging.NOTSET)
    #还未找到原因
  • 相关阅读:
    东驴西磨
    深入理解计算机系统 第二章信息的表示和处理(笔记小结)
    Amdahl 阿姆达尔定律(系统优化)
    想你的夜——葱油饼
    TypeScript and AWS Lambda practicing road map
    "Silicon Valley-like" companies think of engineers as value generators
    original intentions
    Canopy is hiring Postgres SQL Engineer
    在多线程中 feign 调用,服务提供方拿不到 request 的错误
    CF1542D
  • 原文地址:https://www.cnblogs.com/lizm166/p/8459293.html
Copyright © 2011-2022 走看看