robotframework 测试工具添加PDF文件内容匹配插件

robotframework  这个需要了解的请度娘。本文实现的是一个小功能。大体分为如下几个步骤

1）给定一个pdf文件。

2）读取pdf文件内容，并解析为文本内容。

3）通过给定的内容，比对pdf文件内容。

4）输出测试结果。

5）发送结果到指定邮件。

其中读取pdf文件内容，使用的是pdfminer

其他的就是自己包装。

涉及到部分隐私内容，部分代码如下：

# -*- coding: UTF-8 -*-
# coding=utf-8
#from __future__ import unicode_literals
import sys
import os

import subprocess
import time
import re
from robot.libraries.BuiltIn import BuiltIn
from mailcommon import mailcommon
from pdfminer.pdfdocument import PDFDocument
from pdfminer.pdfparser import PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfdevice import PDFDevice, TagExtractor
from pdfminer.pdfpage import PDFPage
from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter
from pdfminer.cmapdb import CMapDB
from pdfminer.layout import LAParams
from pdfminer.image import ImageWriter
import cStringIO
#reload(sys)
#sys.setdefaultencoding('utf-8')

class pdfContentKeywords(object):
    ROBOT_LIBRARY_SCOPE = 'Global'

    root = os.path.abspath(os.path.join(__file__, '..'))


    def __init__(self):
        self.builtin = BuiltIn()


    

    def handlepdf(self, path, param_dict,email, fail=True):
        ''' Reads a specified directory pdf file and diff ...

        `path`: pdf file path

        `param_dict`: Require comparison data

        `fail`:  If there are differences it will throw an exception and test will fail
                 defaults to True, if False test's will continue '''
        param_dict=eval(param_dict)
        self.builtin.log("pdf: %s" %path)
        self.builtin.log("param: %s" %param_dict)

        fail = self.builtin.convert_to_boolean(fail)
        result=dict
        if fail:
            result=self._diffContent(path, param_dict)
        else:
            try:
                result=self._diffContent(path, param_dict)
            except Exception, e:
                self.builtin.log(e)
        msg=''
        for i in result:
            print u"result:%s=" % i,result[i]
            #print self.builtin.log(i) 
            msg+="=>".join([i,str("检验通过" if result[i]==1 else "检验没通过")])
        mail_obj=mailcommon()
        print u"mail MSG:%s" % msg
        maillist=[]
        maillist.append(email)
        mail_obj.send_mail(maillist,'测试结果分析',msg);
        self.builtin.log("End")

    def _readPdf(self,path):
        caching = False
        password = ''
        pagenos = set()
        maxpages = 0
        # output option
        outfile = None
        outtype = None
        imagewriter = None
        rotation = 0
        layoutmode = 'normal'
        codec = 'utf-8'
        pageno = 1
        scale = 1
        showpageno = True
        laparams = LAParams()
        content=''
        outfp=cStringIO.StringIO()
        try:
            rsrcmgr = PDFResourceManager(caching=caching)
            
            device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams,
                                       imagewriter=imagewriter)
            fp = file(path, 'rb')
            interpreter = PDFPageInterpreter(rsrcmgr, device)
            for page in PDFPage.get_pages(fp, pagenos,
                                            maxpages=maxpages, password=password,
                                            caching=caching, check_extractable=True):
                page.rotate = (page.rotate+rotation) % 360
                interpreter.process_page(page)
            fp.close()  
            device.close()
            content= outfp.getvalue()
            outfp.close()
        except Exception, e:
            print "Exception:%s",e
            self.builtin.log(e)
        content=content.replace('
','').replace('	','').strip('
')
        print u"pdf file content:%s"% content#.encode('utf-8').strip()
        return content

        
    def _diffContent(self,path,p_dict):
        result=dict()
        try:
            pdfContent=self._readPdf(path)
            fail=0
            for i in p_dict: 
              print "dict[%s]=" % i,p_dict[i] 
              if re.search(r''+i+p_dict[i] ,pdfContent,re.I | re.M|re.X):
                fail=1   
              result[i+p_dict[i]]=fail
        except Exception, e:
            print "Exception:%s",e
            self.builtin.log(e)
        return result

    

if __name__ == "__main__":
    d = pdfContentKeywords()
    print d.handlepdf("C:\Print.pdf",{"船名/航次:":"CMACGMFIDELIO/B14WESVLC/VALENCIA"},'roger_he@5uzh.com',False)
    #d._readPdf("")