Excel、PDF文档解析

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 "开始解析pdf" + datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    content = ''
    fp = open('tempPdfFile_new3.pdf', 'rb')
    # 来创建一个pdf文档分析器
    parser = PDFParser(fp)
    # 创建一个PDF文档对象存储文档结构
    document = PDFDocument(parser)
    # 检查文件是否允许文本提取
    if not document.is_extractable:
        raise PDFTextExtractionNotAllowed
    else:
        # 创建一个PDF资源管理器对象来存储共赏资源
        rsrcmgr = PDFResourceManager()
        # 设定参数进行分析
        laparams = LAParams()
        # 创建一个PDF设备对象
        # device=PDFDevice(rsrcmgr)
        device = PDFPageAggregator(rsrcmgr, laparams=laparams)
        # 创建一个PDF解释器对象
        interpreter = PDFPageInterpreter(rsrcmgr, device)
        # 处理每一页
        for page in PDFPage.create_pages(document):
            interpreter.process_page(page)
            # 接受该页面的LTPage对象
            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 '开始解析excel文档', filename, url
    req = WebRequests()
    inputStream = req.get(url, timeout=180)
    # 写入到本地暂存，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] #挂牌同时发行(（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)

注意：Excelt在解析时要看一下有没有多个sheet。该pdf解析只能解析文本内容的pdf