vlambda博客
学习文章列表

#-*- coding: GBK -*-from lxml import etree as ETfrom mailmerge import MailMergeimport base64import timeimport docximport regbs=[]# INCLUDEPICTURE "{ MERGEFIELD "zp" }" \* MERGEFORMAT def parsexml(): tree=ET.parse("xmldata/A01.xml") i=0 #for box in tree.xpath('//NewDataSet/Table/A0101[text()="潘琳琳"]/parent::Table'): #for box in tree.xpath('//NewDataSet/Table/A0101[contains(text(),"秦")]/parent::Table'): for box in tree.xpath('//NewDataSet/Table'): pid=box.find('A00').text  xm =box.find('A0101').text zy='' if not box.find('A0130') is None: zy=box.find('A0130').text sr=box.find('A0107').text[0:10] xrzw='' if not box.find('BJXA0102B') is None: xrzw=getDw(box.find('BJXA0102B').text) zp=box.find('BJXA0106').text i=i+1  print(i,xm,xrzw)  gb={ 'xm':xm, 'zy':zy, 'sr':sr, 'xrzw':xrzw, 'zp':'E:/mypy/xmltest/xmldata/pic/'+zp, 'jtgx':getjtgx(pid), 'grll':getlvli(pid) } gbs.append(gb) print("") if i>1940: time.sleep(11)
 def getjtgx(cpid): jtgx='' tree1=ET.parse("xmldata/A36.xml")  ctj='//NewDataSet/Table/A00[text()="%s"]/parent::Table'%cpid for box in tree1.xpath(ctj):  xm =box.find('A3601').text nl='' if not box.find('A3607') is None: nl =box.find('A3607').text[0:10] dw='' if not box.find('A3611A') is None: if not box.find('A3611A').text is None: dw =box.find('A3611A').text print("==>",xm,nl,dw)  jtgx=jtgx+xm+'\t'+dw+'\n' return jtgx
def getlvli(cpid): grll='' tree1=ET.parse("xmldata/A16.xml")  ctj='//NewDataSet/Table/A00[text()="%s"]/parent::Table'%cpid for box in tree1.xpath(ctj):  sjq =box.find('A1601').text[0:10] sjz ='' if not box.find('A1604') is None: sjz=box.find('A1604').text[0:10] dw =box.find('A1607').text print(" ",sjq,"~",sjz,dw)  grll=grll+sjq+'-'+sjz+'\t'+dw+'\n' return grll #查找单位def getDw(cpid): tree1=ET.parse("xmldata/B01.xml")  ctj='//NewDataSet/Table/B00[text()="%s"]/parent::Table'%cpid dw='' for box in tree1.xpath(ctj):  dw =box.find('B0101').text   return dw  def saveword(filename,picname,gbt): document = docx.Document('E:/mypy/xmltest/aa.docx') run = document.paragraphs[0].add_run()  run.add_picture(picname, width=None, height=None)  run.add_break(break_type=6)  document.add_paragraph(gbt['xm']) document.add_paragraph(gbt['xrzw']) document.add_paragraph(gbt['zy']) document.save(filename) def mergeWord(lst): temple='aa.docx' doc=MailMerge(temple) doc.merge(xm=lst['xm'],zy=lst['zy'],sr=lst['sr'],xrzw=lst['xrzw'],zp=lst['zp'],jtgx=lst['jtgx'],grll=lst['grll']) doc.write('E:/mypy/ry/%s.docx'%lst['xm']) def regWord(cstr,keyWord): return len(re.findall(keyWord,cstr))   def main(): parsexml()  keys='研发|博士|教授|高级|美国|英国|瑞士' for gb in gbs: #print(gb['xm'],gb['zy'],gb['zp']) if len(gb['zp'])>10: #saveword('E:/mypy/ry/'+gb['xm']+'.docx','E:/mypy/xmltest/xmldata/pic/'+gb['zp'],gb) if regWord(gb['jtgx'],keys): mergeWord(gb)
   if __name__ == '__main__': main()