python 读取PDF内容（推荐pdfplumber）

环境python2.7 

# coding=utf-8
import PyPDF2


def read_pdf_test1(file_path):
    with open(file_path, 'rb') as f:
        reader = PyPDF2.PdfFileReader(f)
        if reader.isEncrypted:
            reader.decrypt('')
        page_num = reader.getNumPages()
        contents = ''
        for page_num in xrange(page_num):
            contents += reader.getPage(page_num).extractText()
    contents = contents.replace('\n', '').replace(' ', '').replace('\r', '')
    print("contents = {}".format(contents))


def test2(file_path):
    import pdfplumber  # pdfplumber==0.5.13
    contents = ''
    with pdfplumber.open(file_path) as pdf:
        # page_count = len(pdf.pages)
        # print(page_count)  # 得到页数
        for page in pdf.pages:
            print('---------- 第[%d]页 ----------' % page.page_number)
            # 获取当前页面的全部文本信息，包括表格中的文字
            contents += page.extract_text()
    print("contents = {}".format(contents))


if __name__ == "__main__":
    # file_path = './dlp_dengxian.pdf'
    # file_path = './dlp_yuanyue.pdf'
    file_path = './dlp_yuanyue2.pdf'
    # read_pdf_test1(file_path)
    pass
    test2(file_path)