{"id":417,"date":"2016-01-26T21:29:46","date_gmt":"2016-01-26T13:29:46","guid":{"rendered":"http:\/\/dachengge.com\/?p=417"},"modified":"2016-01-26T21:29:46","modified_gmt":"2016-01-26T13:29:46","slug":"%e4%bd%bf%e7%94%a8python%e7%99%bb%e9%99%86%e7%bd%91%e7%ab%99%e8%af%bb%e5%8f%96%e8%a1%a8%e6%a0%bc%e6%95%b0%e6%8d%ae","status":"publish","type":"post","link":"http:\/\/dachengge.com\/?p=417","title":{"rendered":"\u4f7f\u7528Python\u767b\u9646\u7f51\u7ad9\u8bfb\u53d6\u8868\u683c\u6570\u636e"},"content":{"rendered":"<p>\u8fd1\u671f\u6709\u7ecf\u5e38\u4f7f\u7528\u7684\u6570\u636e\uff0c\u9700\u8981\u767b\u9646\u5230\u67d0\u4e2a\u7f51\u7ad9\uff0c\u5c06\u5176\u4e2d\u7684\u8868\u683c\u6570\u636e\u8bfb\u53d6\u51fa\u6765\uff0c\u4e3a\u4e86\u63d0\u9ad8\u6548\u7387\u8282\u7701\u5de5\u4f5c\u65f6\u95f4\uff0c\u51b3\u5b9a\u5199\u4e00\u4e2a\u7a0b\u5e8f\uff0c\u4f7f\u7528Python\u81ea\u52a8\u767b\u9646\u5230\u8be5\u7f51\u7ad9\u7136\u540e\u5c06\u67d0\u65e5\uff08\u53c2\u6570\uff09\u7684\u6570\u636e\u8bfb\u53d6\u5e76\u5b58\u653e\u4e8eexcel\u8868\u683c\u4e2d\u3002<!--more--><br \/>\n<strong>1 <\/strong><strong>\u767b\u9646\u7f51\u7ad9<br \/>\n<\/strong><br \/>\n\u901a\u8fc7IE\u7b49\u6d4f\u89c8\u5668\u767b\u9646\u5230\u4e00\u4e2a\u7f51\u7ad9\u6bd4\u8f83\u7b80\u5355\uff0c\u8f93\u5165\u8d26\u53f7\u3001\u5bc6\u7801\uff0c\u70b9\u51fb\u786e\u5b9a\u5c31\u767b\u9646\u5230\u4e86\u4e00\u4e2a\u7f51\u7ad9\uff0c\u4f46\u662f\u5982\u679c\u60f3\u5b9e\u73b0\u81ea\u52a8\u5316\uff0c\u5c31\u5fc5\u987b\u5f97\u901a\u8fc7http\u534f\u8bae\u4e0e\u670d\u52a1\u5668\u8fdb\u884c\u901a\u4fe1\u3002\u5e38\u89c1\u7684http\u534f\u8bae\u5de5\u5177\u6709curl\uff0c\u7531\u4e8ecurl\u4f7f\u7528\u6bd4\u8f83\u9ebb\u70e6\uff0c\u5f97\u81ea\u5df2\u5904\u7406\u50cfcookie\u4e4b\u7c7b\u7684\u7ec6\u8282\uff0c\u8fd9\u91cc\u5c31\u76f4\u63a5\u4f7f\u7528Python\u7684urllib\u5e93\u3002<br \/>\n\u9996\u5148\u4f7f\u7528wireShark\u6293\u5305\u5de5\u5177\uff0c\u5206\u6790\u767b\u9646\u8fc7\u7a0b\u4e2d\u4f20\u8f93\u7684\u6570\u636e\uff0c\u767b\u9646\u7f51\u7ad9\u65f6\u662f\u5c06\u7528\u6237\u540d\u548c\u5bc6\u7801\uff08\u901a\u5e38\u4e3aMD5\u52a0\u5bc6\u7684\u5bc6\u7801\uff09post\u5230\u4e00\u4e2a\u76ee\u6807\u9875\u9762\u8fdb\u884c\u5904\u7406\uff0c\u5982\u679c\u7528\u6237\u540d\u548c\u5bc6\u7801\u6b63\u786e\uff0c\u5c31\u4f1aredirect\u5230\u6210\u529f\u9875\u9762\u3002\u767b\u9646\u6210\u529f\u540e\uff0c\u8fd4\u56de\u7684header\u4e2d\u5305\u62ec\u4e00\u4e2acookie\uff0c\u5fc5\u987b\u5bf9\u8be5cookie\u6b63\u786e\u5904\u7406\uff0c\u624d\u80fd\u6b63\u5e38\u8bbf\u95ee\u767b\u9646\u6210\u529f\u540e\u7684\u7f51\u7ad9\u5185\u5bb9\u3002<br \/>\nimport urllib<br \/>\nimport urllib2<br \/>\nimport cookielib<br \/>\nfrom bs4 import BeautifulSoup<br \/>\n#\u767b\u9646\u65f6\u68c0\u9a8c\u8d26\u6237\u7684\u9875\u9762<br \/>\nauth_url = &#8216;http:\/\/localhost\/check.php&#8217;<br \/>\n#\u6240\u9700\u6570\u636e\u7684\u9875\u9762<br \/>\ndata_url = &#8216; http:\/\/localhost\/data.php&#8217;<br \/>\n#\u7528\u6237\u540d\u548c\u5bc6\u7801<br \/>\npara={\u201cname\u201d:\u201duser\u201d,\u201dpassword\u201d:123}<br \/>\n#\u5bf9\u53c2\u6570\u8fdb\u884c\u7f16\u7801\uff08\u5e38\u7528\u4e8e\u6c49\u5b57\uff09<br \/>\npost_data=urllib.urlencode(para)<br \/>\n#\u81ea\u52a8\u5904\u7406cookie\u7684\u7c7b<br \/>\ncookieJar=cookielib.CookieJar()<br \/>\nopener=urllib2.build_opener(urllib2.HTTPCookieProcessor(cookieJar))<br \/>\nreq=urllib2.Request(auth_url,post_data)<br \/>\nresult = opener.open(req)<br \/>\n\u5230\u6b64\uff0c\u5c31\u7b97\u767b\u9646\u6210\u529f\u5e76\u4fdd\u5b58\u767b\u9646\u540e\u7684cookie\u4e86\uff0c\u4e3a\u4e86\u4ee5\u9632\u4e07\u4e00\uff0c\u53ef\u4ee5\u6253\u5370result.status\u548cresult.reason\uff0c\u5982\u679c\u4e00\u529f\u6b63\u5e38\uff0c\u90a3\u4e48result.status\u5c31\u662f200\uff0cresult.reason\u5c31\u662fOK\u3002<br \/>\n<strong>2 <\/strong><strong>\u63d0\u4f9b\u53c2\u6570\u8bbf\u95ee\u67d0\u9875\u9762<\/strong><br \/>\n\u4e0a\u4e00\u6b65\u5df2\u7ecf\u767b\u9646\u6210\u529f\uff0c\u6839\u636e\u53c2\u6570\u8bbf\u95ee\u6570\u636e\u9875\u9762\uff0c\u4e5f\u662f\u8981\u5c06\u6570\u636e\u63d0\u4ea4\u5230\u4e00\u4e2a\u5177\u4f53\u7684\u9875\u9762\uff0c\u901a\u8fc7\u89c2\u5bdf\u6570\u636e\u7684\u4f20\u8f93\uff0c\u53ef\u4ee5\u53d1\u73b0\u8981\u4f20\u9012\u7684\u53c2\u6570\u3002<br \/>\npara={\u201cdate\u201d:\u201d2015-11-10\u201d}<br \/>\npost_data=urllib.urlencode(para)<br \/>\npost_data=urllib.urlencode(post_data)<br \/>\nresult = opener.open(data_url +\u201d?\u201d+post_data)<br \/>\n\u5230\u6b64\uff0c\u901a\u8fc7\u53c2\u6570\u5c31\u80fd\u6253\u5f00\u5177\u4f53\u7684\u6570\u636e\u9875\u9762\u4e86\uff0c\u5982\u679c\u8fd8\u4e0d\u653e\u5fc3\uff0c\u540c\u4e0a\u9762\u4e00\u6837\uff0c\u6253\u5370result.status\u548cresult.reason\uff0c\u770b\u8fd4\u56de\u7684\u7ed3\u679c\u3002<br \/>\n<strong>3 <\/strong><strong>\u89e3\u6790\u7f51\u9875\u4e2d\u8868\u683c\u7684\u6570\u636e<\/strong><br \/>\n\u76ee\u6807\u9875\u9762\u6bd4\u8f83\u7b80\u5355\uff0c\u5c31\u4e00\u4e2a\u8868\u683c(\u4f7f\u7528\u7684\u662f\u4f20\u7edf\u7684table\u6807\u7b7e\uff0c\u800c\u4e0d\u662fdiv)\uff0c\u4e3a\u4e86\u987a\u5229\u5f97\u5230\u91cc\u9762\u7684\u6570\u636e\uff0c\u6bd4\u5982\u7b2c\u51e0\u884c\u7b2c\u51e0\u5217\uff0c\u90a3\u4e48\u5c31\u5f97\u4f7f\u7528\u89e3\u6790html\u7684\u5de5\u5177\uff0c\u7f51\u53cb\u63a8\u8350\u7684\u662fBeautifulSoup\u8fd9\u4e2a\u5305\uff0c\u5229\u7528\u8fd9\u4e2a\u5305\u6765\u5206\u6790html\u6587\u6863\u7684\u6811\u5f62\u7ed3\u6784\uff0c\u5f88\u5bb9\u6613\u53d6\u5f97\u9875\u9762\u7684\u67d0\u4e2a\u6570\u636e\u3002\u524d\u9762\u5df2\u7ecf\u5bfc\u5165\u4e86\u8fd9\u4e2a\u5305\uff0c\u767b\u9646\u6210\u529f\uff0c\u5e76\u4e14\u63d0\u4ea4\u53c2\u6570\u6253\u5f00\u4e86\u6240\u9700\u6570\u636e\u7684\u9875\u9762\uff0c\u73b0\u5728\u5c31\u5bf9\u8fd9\u4e2a\u9875\u9762\u8fdb\u884c\u89e3\u6790\uff1a<br \/>\n#\u76ee\u6807\u9875\u9762\u662fGB2312\u7f16\u7801\uff0c\u800cPython\u9ed8\u8ba4\u662fUTF-8\u7684\u7f16\u7801\uff0c\u6240\u4ee5\u8981\u6307\u5b9a\u7f16\u7801<br \/>\nsoup = BeautifulSoup(result.read(), &#8216;html.parser&#8217;,from_encoding=&#8217;gb2312&#8242;)<br \/>\ndataDict={}\u00a0\u00a0\u00a0 #\u7528\u4e8e\u5b58\u653e\u8bfb\u53d6\u6570\u636e\u7684\u5b57\u5178<br \/>\niRow=1\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 #\u7528\u4e8e\u5ffd\u7565\u7b2c\u4e00\u884c\u6807\u9898\u884c\u7684\u5185\u5bb9<br \/>\nfor item in soup.find_all(&#8216;tr&#8217;):<br \/>\n\u00a0\u00a0\u00a0 if iRow!=1:<br \/>\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0if item.contents[1] not in list(dataDict): #\u7b2c\u4e00\u5217\u4e3a\u59d3\u540d\u4e0d\u80fd\u91cd\u590d<br \/>\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 dataDict[item.contents[1]]= (item.contents[2], item.contents[3])<br \/>\n\u00a0\u00a0\u00a0 iRow=iRow+1<br \/>\n\u5b9e\u6218\u4e2d\u53d1\u73b0\uff0citem.contents\u91cc\u9762\u5e26\u7684\u8fd8\u6709&lt;td&gt;\u6807\u7b7e\uff0c\u663e\u7136\u4e0d\u662f\u6240\u60f3\u8981\u7684\uff0c\u56e0\u6b64\u9700\u8981\u5c06\u8fd9\u91cc\u7684html\u6807\u7b7e\u53bb\u6389\uff0c\u76f4\u63a5\u81ea\u5b9a\u4e49\u4e00\u4e2a\u51fd\u6570\u5c31\u6ee1\u8db3\u9700\u8981\u4e86\uff1a<br \/>\ndef myReplace(data=None):<br \/>\n\u00a0\u00a0\u00a0 dataStr=&#8221;&#8221;<br \/>\n\u00a0\u00a0\u00a0 if data is None:<br \/>\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 print &#8220;Error!&#8221;<br \/>\n\u00a0\u00a0\u00a0 else:<br \/>\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 for i in data:<br \/>\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 if i not in (&#8216;&lt;&#8216;,&#8217;&gt;&#8217;,&#8217;t&#8217;,&#8217;d&#8217;,&#8217;\/&#8217;):<br \/>\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 dataStr=dataStr+i<br \/>\n\u00a0\u00a0\u00a0 return dataStr.strip()<br \/>\n\u81f3\u6b64\uff0c\u8868\u683c\u4e2d\u6240\u6709\u884c\u7684\u7b2c\u4e00\u3001\u4e8c\u3001\u4e09\u5217\u90fd\u5b58\u5165dataDict\u5b57\u5178\u4e2d\uff0c\u5176\u4e2d\u7b2c\u4e00\u5217\u4e3a\u59d3\u540d\uff0c\u6bd4\u8f83\u91cd\u8981\uff0c\u4e5f\u4e0d\u91cd\u590d\uff0c\u6240\u4ee5\u5f53key\uff0c\u7b49\u5f85\u5199\u5165excel\u8868\u683c\u4e2d\u3002<br \/>\n<strong>4 <\/strong><strong>\u5199\u5165excel<\/strong><strong>\u4e2d<\/strong><br \/>\n\u8bfb\u53d6\u5e76\u5199\u5165excel\u8868\u683c\uff0c\u7f51\u4e0a\u6709\u5f88\u591a\u4ecb\u7ecd\u7684\u5305\uff0c\u6bd4\u5982xlrd\/xlwt\/openpyxl\uff0c\u5b9e\u6218\u4e2d\u53d1\u73b0\u524d\u4e24\u4e2a\u5305\u4e00\u4e2a\u53ea\u80fd\u8bfb\u4e00\u4e2a\u53ea\u80fd\u5199\uff0c\u5373\u4f7f\u6709xlutils\u6765\u8fde\u63a5\u8fd9\u4e24\u4e2a\u5305\uff0c\u4f46\u8fd8\u662f\u4e0d\u65b9\u4fbf\uff1bopenpyxl\u80fd\u8bfb\u80fd\u5199\u5c31\u8ddfvba\u4e00\u6837\uff0c\u4f46\u662f\u751f\u6210\u7684\u8868\u683c\u7535\u8111\u4e0a\u770b\u6b63\u5e38\u770b\uff0c\u624b\u673a\u4e0a\u4e0d\u77e5\u9053\u4e3a\u4ec0\u4e48\u6253\u4e0d\u5f00\uff08\u6700\u7ec8\u8981\u5728\u624b\u673a\u4e0a\u770b\uff09\uff0c\u6240\u4ee5\u6700\u7ec8\u4f7f\u7528win32com\u5305\u901a\u8fc7com\u7684\u65b9\u5f0f\u8c03\u7528excel\uff0c\u4e00\u5207\u6b63\u5e38\uff1a<br \/>\n#\u6700\u524d\u9762\u522b\u5fd8\u4e86\u5bfc\u5165\u4e0b\u9762\u7684\u4e24\u4e2a\u5305\uff1a<br \/>\nimport win32com.client<br \/>\nfrom win32com.client import Dispatch<br \/>\n#\u64cd\u4f5cexcel\u7684\u7c7b\u7f51\u4e0a\u662f\u73b0\u6210\u7684\uff0c\u8fd9\u91cc\u5c31\u4e0d\u590d\u5236\u4ee3\u7801\u4e86\uff0c\u7c7b\u7684\u540d\u5b57\u662f<strong>easyExcel<\/strong>\uff0c\u590d\u5236\u4e0b\u6765\u76f4\u63a5\u4f7f\u7528\uff0c\u4f1a\u6bd4\u8f83\u7701\u4e8b\uff1a<br \/>\n#\u6253\u5f00\u6a21\u677f\uff08\u5df2\u7ecf\u505a\u597d\u4e86\u683c\u5f0f\uff0c\u5199\u597d\u4e86\u8868\u5934\uff0c\u7b2c\u4e00\u5217\u662f\u59d3\u540d\uff09<br \/>\nxls = easyExcel(&#8216;template.xlsx&#8217;)<br \/>\nfor i in range(2,28):\u00a0 #\u7b2c\u4e00\u884c\u4e3a\u6807\u9898\uff0c\u4ece\u7b2c\u4e8c\u884c\u5f00\u59cb\u5199\u5165\uff1b\u7b2c\u4e00\u5217\u662f\u59d3\u540d\uff0c\u56e0\u6b64\u6570\u636e\u4e0d\u80fd\u9519\u884c\u3002<br \/>\n\u00a0\u00a0\u00a0 xls.setCell(u&#8217;Sheet1&#8242;,i,1, dataDict [xls.getCell(u&#8217;Sheet1&#8242;,i,1)][0])<br \/>\n\u00a0\u00a0\u00a0 xls.setCell(u&#8217;Sheet1&#8242;,i,2, dataDict [xls.getCell(u&#8217;Sheet1&#8242;,i,1)][1])<br \/>\n\u00a0\u00a0\u00a0 xls.setCell(u&#8217;Sheet1&#8242;,i,3 ,dataDict [xls.getCell(u&#8217;Sheet1&#8242;,i,1)][2])<br \/>\nxls.save(newfilename) #\u53e6\u5b58\u4e3a\u65b0\u7684\u6587\u4ef6<br \/>\nxls.close()<br \/>\n\u6700\u540e\u4e00\u5207\u987a\u5229\uff0c\u5c06\u6570\u636e\u6210\u529f\u8bfb\u53d6\u5e76\u4fdd\u5b58\u5230\u4e86excel\u6587\u4ef6\u4e2d\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u8fd1\u671f\u6709\u7ecf\u5e38\u4f7f\u7528\u7684\u6570\u636e\uff0c\u9700\u8981\u767b\u9646\u5230\u67d0\u4e2a\u7f51\u7ad9\uff0c\u5c06\u5176\u4e2d\u7684\u8868\u683c\u6570\u636e\u8bfb\u53d6\u51fa\u6765\uff0c\u4e3a\u4e86\u63d0\u9ad8\u6548\u7387\u8282\u7701\u5de5\u4f5c\u65f6\u95f4\uff0c\u51b3\u5b9a\u5199\u4e00\u4e2a\u7a0b\u5e8f\uff0c &hellip; <a href=\"http:\/\/dachengge.com\/?p=417\" class=\"more-link\">\u7ee7\u7eed\u9605\u8bfb<span class=\"screen-reader-text\">\u4f7f\u7528Python\u767b\u9646\u7f51\u7ad9\u8bfb\u53d6\u8868\u683c\u6570\u636e<\/span> <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11],"tags":[43,69,94,667],"views":6313,"_links":{"self":[{"href":"http:\/\/dachengge.com\/index.php?rest_route=\/wp\/v2\/posts\/417"}],"collection":[{"href":"http:\/\/dachengge.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/dachengge.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/dachengge.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/dachengge.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=417"}],"version-history":[{"count":0,"href":"http:\/\/dachengge.com\/index.php?rest_route=\/wp\/v2\/posts\/417\/revisions"}],"wp:attachment":[{"href":"http:\/\/dachengge.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=417"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/dachengge.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=417"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/dachengge.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=417"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}