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

import sys
import xlrd
reload(sys)
sys.setdefaultencoding(‘utf-8‘)


def pdf_transform_text():
    print "開始解析pdf" + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    content = ‘‘
    fp = open(‘tempPdfFile_new3.pdf‘, ‘rb‘)
    # 來創建一個pdf文檔分析器
    parser = PDFParser(fp)
    
 
# 創建一個PDF文檔對象存儲文檔結構
    document = PDFDocument(parser)
    # 檢查文件是否允許文本提取
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        # 創建一個PDF資源管理器對象來存儲共賞資源
        rsrcmgr = PDFResourceManager()
        # 設定參數進行分析
        laparams = LAParams()
        # 創建一個PDF設備對象
 

        # device=PDFDevice(rsrcmgr)
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        # 創建一個PDF解釋器對象
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        # 處理每一頁
        for page in PDFPage.create_pages(document):
            interpreter.process_page(page)
            # 接受該頁面的LTPage對象
            layout = device.get_result()
            for x in layout:
                if (isinstance(x, LTTextBoxHorizontal)):
                    content += x.get_text().encode(‘utf-8‘) + ‘\n‘
    print "解析pdf成功" + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    return content.decode("utf-8")

def parse_excel(url, filename):
    print ‘開始解析excel文檔‘, filename, url
    req = WebRequests()
    inputStream = req.get(url, timeout=180)
    # 寫入到本地暫存，方便解析成文本
    with open("tempExcelFile_new3.xls", "wb") as xls:
        xls.write(inputStream.content)
    data = xlrd.open_workbook("tempExcelFile_new3.xls")
    for i in range(len(data.sheets())):
        table = data.sheets()[i]
        print table.name
        print table.nrows
        for i in range(2, table.nrows):
            if len(table.row_values(i))>=12:
                result = {}
                result[‘company_name‘] = table.row_values(i)[1]
                result[‘province‘] = table.row_values(i)[2]
                result[‘industry‘] = table.row_values(i)[3]
                result[‘broker_company‘] = table.row_values(i)[4]
                result[‘broker_person‘] = table.row_values(i)[5]
                result[‘law_firm‘] = table.row_values(i)[6]
                result[‘laywyer‘] = table.row_values(i)[7]
                result[‘accounting_firm‘] = table.row_values(i)[8]
                result[‘accountant‘] = table.row_values(i)[9]
                # result[‘‘] = table.row_values(i)[10] #掛牌同時發行(（是/否）)
                result[‘progress‘] = table.row_values(i)[11]
                if len(table.row_values(i))==13:
                    result[‘receive_date‘] = table.row_values(i)[12]
                saveOrUpdateNew3CompanyBaseInfo(result)

註意：Excelt在解析時要看一下有沒有多個sheet。該pdf解析只能解析文本內容的pdf

Excel、PDF文檔解析