{"id":1664,"date":"2020-06-22T04:09:14","date_gmt":"2020-06-21T20:09:14","guid":{"rendered":"http:\/\/39.97.231.10\/?p=1664"},"modified":"2020-06-22T04:09:14","modified_gmt":"2020-06-21T20:09:14","slug":"python%e9%87%8c%e8%af%bb%e5%86%99excel%e7%ad%89%e6%95%b0%e6%8d%ae%e6%96%87%e4%bb%b6%e7%9a%84%e5%87%a0%e7%a7%8d%e5%b8%b8%e7%94%a8%e6%96%b9%e5%bc%8f","status":"publish","type":"post","link":"http:\/\/www.weijing.co\/?p=1664","title":{"rendered":"python\u91cc\u8bfb\u5199excel\u7b49\u6570\u636e\u6587\u4ef6\u7684\u51e0\u79cd\u5e38\u7528\u65b9\u5f0f"},"content":{"rendered":"<div>\npython\u5904\u7406\u6570\u636e\u6587\u4ef6\u7b2c\u4e00\u6b65\u662f\u8981\u8bfb\u53d6\u6570\u636e\uff0c\u6587\u4ef6\u7c7b\u578b\u4e3b\u8981\u5305\u62ec\u6587\u672c\u6587\u4ef6\uff08csv\u3001txt\u7b49\uff09\u3001excel\u6587\u4ef6\u3001\u6570\u636e\u5e93\u6587\u4ef6\u3001api\u7b49\u3002<br \/>\n\u4e0b\u9762\u6574\u7406\u4e0bpython\u6709\u54ea\u4e9b\u65b9\u5f0f\u53ef\u4ee5\u8bfb\u53d6\u6570\u636e\u6587\u4ef6\u3002<\/p>\n<h2>1. python\u5185\u7f6e\u65b9\u6cd5\uff08read\u3001readline\u3001readlines\uff09<\/h2>\n<ul>\n<li>read() \uff1a \u4e00\u6b21\u6027\u8bfb\u53d6\u6574\u4e2a\u6587\u4ef6\u5185\u5bb9\u3002\u63a8\u8350\u4f7f\u7528read(size)\u65b9\u6cd5\uff0csize\u8d8a\u5927\u8fd0\u884c\u65f6\u95f4\u8d8a\u957f<\/li>\n<li>readline() \uff1a\u6bcf\u6b21\u8bfb\u53d6\u4e00\u884c\u5185\u5bb9\u3002\u5185\u5b58\u4e0d\u591f\u65f6\u4f7f\u7528\uff0c\u4e00\u822c\u4e0d\u592a\u7528<\/li>\n<li>readlines() \uff1a\u4e00\u6b21\u6027\u8bfb\u53d6\u6574\u4e2a\u6587\u4ef6\u5185\u5bb9\uff0c\u5e76\u6309\u884c\u8fd4\u56de\u5230list\uff0c\u65b9\u4fbf\u6211\u4eec\u904d\u5386<\/li>\n<\/ul>\n<h2>2. \u5185\u7f6e\u6a21\u5757\uff08csv\uff09<\/h2>\n<p>python\u5185\u7f6e\u4e86csv\u6a21\u5757\u7528\u4e8e\u8bfb\u5199csv\u6587\u4ef6\uff0ccsv\u662f\u4e00\u79cd\u9017\u53f7\u5206\u9694\u7b26\u6587\u4ef6\uff0c\u662f\u6570\u636e\u79d1\u5b66\u4e2d\u6700\u5e38\u89c1\u7684\u6570\u636e\u5b58\u50a8\u683c\u5f0f\u4e4b\u4e00\u3002<br \/>\ncsv\u6a21\u5757\u80fd\u8f7b\u677e\u5b8c\u6210\u5404\u79cd\u4f53\u91cf\u6570\u636e\u7684\u8bfb\u5199\u64cd\u4f5c\uff0c\u5f53\u7136\u5927\u6570\u636e\u91cf\u9700\u8981\u4ee3\u7801\u5c42\u9762\u7684\u4f18\u5316\u3002<\/p>\n<ul>\n<li>csv\u6a21\u5757\u8bfb\u53d6\u6587\u4ef6<\/li>\n<\/ul>\n<div>\n<pre># \u8bfb\u53d6csv\u6587\u4ef6\nimport csv\nwith open(\\'test.csv\\',\\'r\\') as myFile:\n    lines=csv.reader(myFile)\n    for line in lines:\n        print (line)\n<\/pre>\n<\/div>\n<ul>\n<li>csv\u6a21\u5757\u5199\u5165\u6587\u4ef6<\/li>\n<\/ul>\n<div>\n<pre>import csv\nwith open(\\'test.csv\\',\\'w+\\') as myFile:\n    myWriter=csv.writer(myFile)\n    # writerrow\u4e00\u884c\u4e00\u884c\u5199\u5165\n    myWriter.writerow([7,8,9])\n    myWriter.writerow([8,\\'h\\',\\'f\\'])\n    # writerow\u591a\u884c\u5199\u5165\n    myList=[[1,2,3],[4,5,6]]\n    myWriter.writerows(myList)\n<\/pre>\n<\/div>\n<h2>3. \u4f7f\u7528numpy\u5e93\uff08loadtxt\u3001load\u3001fromfile\uff09<\/h2>\n<ul>\n<li>loadtxt\u65b9\u6cd5<br \/>\nloadtxt\u7528\u6765\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\uff08\u5305\u542btxt\u3001csv\u7b49\uff09\u4ee5\u53ca.gz \u6216.bz2\u683c\u5f0f\u538b\u7f29\u6587\u4ef6\uff0c\u524d\u63d0\u662f\u6587\u4ef6\u6570\u636e\u6bcf\u4e00\u884c\u5fc5\u987b\u8981\u6709\u6570\u91cf\u76f8\u540c\u7684\u503c\u3002<\/li>\n<\/ul>\n<div>\n<pre>import numpy as np\n# loadtxt()\u4e2d\u7684dtype\u53c2\u6570\u9ed8\u8ba4\u8bbe\u7f6e\u4e3afloat\n# \u8fd9\u91cc\u8bbe\u7f6e\u4e3astr\u5b57\u7b26\u4e32\u4fbf\u4e8e\u663e\u793a\nnp.loadtxt(\\'test.csv\\',dtype=str)\n# out\uff1aarray([\\'1,2,3\\', \\'4,5,6\\', \\'7,8,9\\'], dtype=\\'&lt;U5\\')\n<\/pre>\n<\/div>\n<ul>\n<li>load\u65b9\u6cd5<br \/>\nload\u7528\u6765\u8bfb\u53d6numpy\u4e13\u7528\u7684.npy, .npz \u6216\u8005pickled\u6301\u4e45\u5316\u6587\u4ef6\u3002<\/li>\n<\/ul>\n<div>\n<pre>import numpy as np\n# \u5148\u751f\u6210npy\u6587\u4ef6\nnp.save(\\'test.npy\\', np.array([[1, 2, 3], [4, 5, 6]]))\n# \u4f7f\u7528load\u52a0\u8f7dnpy\u6587\u4ef6\nnp.load(\\'test.npy\\')\n\\'\\'\\'\nout:array([[1, 2, 3],\n       [4, 5, 6]])\n\\'\\'\\'\n<\/pre>\n<\/div>\n<ul>\n<li>fromfile\u65b9\u6cd5<br \/>\nfromfile\u65b9\u6cd5\u53ef\u4ee5\u8bfb\u53d6\u7b80\u5355\u7684\u6587\u672c\u6570\u636e\u6216\u4e8c\u8fdb\u5236\u6570\u636e\uff0c\u6570\u636e\u6765\u6e90\u4e8etofile\u65b9\u6cd5\u4fdd\u5b58\u7684\u4e8c\u8fdb\u5236\u6570\u636e\u3002\u8bfb\u53d6\u6570\u636e\u65f6\u9700\u8981\u7528\u6237\u6307\u5b9a\u5143\u7d20\u7c7b\u578b\uff0c\u5e76\u5bf9\u6570\u7ec4\u7684\u5f62\u72b6\u8fdb\u884c\u9002\u5f53\u7684\u4fee\u6539\u3002<\/li>\n<\/ul>\n<div>\n<pre>import numpy as np\nx = np.arange(9).reshape(3,3)\nx.tofile(\\'test.bin\\')\nnp.fromfile(\\'test.bin\\',dtype=np.int)\n# out:array([0, 1, 2, 3, 4, 5, 6, 7, 8])\n<\/pre>\n<\/div>\n<h2>4. \u4f7f\u7528pandas\u5e93\uff08read_csv\u3001read_excel\u7b49\uff09<\/h2>\n<p>pandas\u662f\u6570\u636e\u5904\u7406\u6700\u5e38\u7528\u7684\u5206\u6790\u5e93\u4e4b\u4e00\uff0c\u53ef\u4ee5\u8bfb\u53d6\u5404\u79cd\u5404\u6837\u683c\u5f0f\u7684\u6570\u636e\u6587\u4ef6\uff0c\u4e00\u822c\u8f93\u51fadataframe\u683c\u5f0f\u3002<br \/>\n\u5982\uff1atxt\u3001csv\u3001excel\u3001json\u3001\u526a\u5207\u677f\u3001\u6570\u636e\u5e93\u3001html\u3001hdf\u3001parquet\u3001pickled\u6587\u4ef6\u3001sas\u3001stata\u7b49\u7b49<\/p>\n<ul>\n<li>read_csv\u65b9\u6cd5<br \/>\nread_csv\u65b9\u6cd5\u7528\u6765\u8bfb\u53d6csv\u683c\u5f0f\u6587\u4ef6\uff0c\u8f93\u51fadataframe\u683c\u5f0f\u3002<\/li>\n<\/ul>\n<div>\n<pre>import pandas as pd\npd.read_csv(\\'test.csv\\')\n<\/pre>\n<\/div>\n<ul>\n<li>read_excel\u65b9\u6cd5<br \/>\n\u8bfb\u53d6excel\u6587\u4ef6\uff0c\u5305\u62ecxlsx\u3001xls\u3001xlsm\u683c\u5f0f<\/li>\n<\/ul>\n<div>\n<pre>import pandas as pd\npd.read_excel(\\'test.xlsx\\')\n<\/pre>\n<\/div>\n<ul>\n<li>read_table\u65b9\u6cd5<br \/>\n\u901a\u8fc7\u5bf9sep\u53c2\u6570\uff08\u5206\u9694\u7b26\uff09\u7684\u63a7\u5236\u6765\u5bf9\u4efb\u4f55\u6587\u672c\u6587\u4ef6\u8bfb\u53d6<\/li>\n<li>read_json\u65b9\u6cd5<br \/>\n\u8bfb\u53d6json\u683c\u5f0f\u6587\u4ef6<\/li>\n<\/ul>\n<div>\n<pre>df = pd.DataFrame([[\\'a\\', \\'b\\'], [\\'c\\', \\'d\\']],index=[\\'row 1\\', \\'row 2\\'],columns=[\\'col 1\\', \\'col 2\\'])\nj = df.to_json(orient=\\'split\\')\npd.read_json(j,orient=\\'split\\')\n<\/pre>\n<\/div>\n<ul>\n<li>read_html\u65b9\u6cd5<br \/>\n\u8bfb\u53d6html\u8868\u683c<\/li>\n<li>read_clipboard\u65b9\u6cd5<br \/>\n\u8bfb\u53d6\u526a\u5207\u677f\u5185\u5bb9<\/li>\n<li>read_pickle\u65b9\u6cd5<br \/>\n\u8bfb\u53d6plckled\u6301\u4e45\u5316\u6587\u4ef6<\/li>\n<li>read_sql\u65b9\u6cd5<br \/>\n\u8bfb\u53d6\u6570\u636e\u5e93\u6570\u636e\uff0c\u8fde\u63a5\u597d\u6570\u636e\u5e93\u540e\uff0c\u4f20\u5165sql\u8bed\u53e5\u5373\u53ef<\/li>\n<li>read_dhf\u65b9\u6cd5<br \/>\n\u8bfb\u53d6hdf5\u6587\u4ef6\uff0c\u9002\u5408\u5927\u6587\u4ef6\u8bfb\u53d6<\/li>\n<li>read_parquet\u65b9\u6cd5<br \/>\n\u8bfb\u53d6parquet\u6587\u4ef6<\/li>\n<li>read_sas\u65b9\u6cd5<br \/>\n\u8bfb\u53d6sas\u6587\u4ef6<\/li>\n<li>read_stata\u65b9\u6cd5<br \/>\n\u8bfb\u53d6stata\u6587\u4ef6<\/li>\n<li>read_gbq\u65b9\u6cd5<br \/>\n\u8bfb\u53d6google bigquery\u6570\u636e<\/li>\n<\/ul>\n<h2>5\u3001\u8bfb\u5199excel\u6587\u4ef6\uff08xlrd\u3001xlwt\u3001openpyxl\u7b49\uff09<\/h2>\n<p>python\u7528\u4e8e\u8bfb\u5199excel\u6587\u4ef6\u7684\u5e93\u6709\u5f88\u591a\uff0c\u9664\u4e86\u524d\u9762\u63d0\u5230\u7684pandas\uff0c\u8fd8\u6709xlrd\u3001xlwt\u3001openpyxl\u3001xlwings\u7b49\u7b49\u3002<br \/>\n\u4e3b\u8981\u6a21\u5757\uff1a<\/p>\n<ul>\n<li>xlrd\u5e93\uff1a\u4eceexcel\u4e2d\u8bfb\u53d6\u6570\u636e\uff0c\u652f\u6301xls\u3001xlsx<\/li>\n<li>xlwt\u5e93\uff1a\u5bf9excel\u8fdb\u884c\u4fee\u6539\u64cd\u4f5c\uff0c\u4e0d\u652f\u6301\u5bf9xlsx\u683c\u5f0f\u7684\u4fee\u6539<\/li>\n<li>xlutils\u5e93\uff1a\u5728xlw\u548cxlrd\u4e2d\uff0c\u5bf9\u4e00\u4e2a\u5df2\u5b58\u5728\u7684\u6587\u4ef6\u8fdb\u884c\u4fee\u6539<\/li>\n<li>openpyxl\uff1a\u4e3b\u8981\u9488\u5bf9xlsx\u683c\u5f0f\u7684excel\u8fdb\u884c\u8bfb\u53d6\u548c\u7f16\u8f91<\/li>\n<li>xlwings\uff1a\u5bf9xlsx\u3001xls\u3001xlsm\u683c\u5f0f\u6587\u4ef6\u8fdb\u884c\u8bfb\u5199\u3001\u683c\u5f0f\u4fee\u6539\u7b49\u64cd\u4f5c<\/li>\n<li>xlsxwriter\uff1a\u7528\u6765\u751f\u6210excel\u8868\u683c\uff0c\u63d2\u5165\u6570\u636e\u3001\u63d2\u5165\u56fe\u6807\u7b49\u8868\u683c\u64cd\u4f5c\uff0c\u4e0d\u652f\u6301\u8bfb\u53d6<\/li>\n<li>Microsoft Excel API\uff1a\u9700\u5b89\u88c5pywin32\uff0c\u76f4\u63a5\u4e0eExcel\u8fdb\u7a0b\u901a\u4fe1\uff0c\u53ef\u4ee5\u505a\u4efb\u4f55\u5728Excel\u91cc\u53ef\u4ee5\u505a\u7684\u4e8b\u60c5\uff0c\u4f46\u6bd4\u8f83\u6162<\/li>\n<\/ul>\n<h2>6. \u64cd\u4f5c\u6570\u636e\u5e93\uff08pymysql\u3001cx_Oracle\u7b49\uff09<\/h2>\n<p>python\u51e0\u4e4e\u652f\u6301\u5bf9\u6240\u6709\u6570\u636e\u5e93\u7684\u4ea4\u4e92\uff0c\u8fde\u63a5\u6570\u636e\u5e93\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528sql\u8bed\u53e5\u8fdb\u884c\u589e\u5220\u6539\u67e5\u3002<br \/>\n\u4e3b\u8981\u6a21\u5757\uff1a<\/p>\n<ul>\n<li>pymysql\uff1a\u7528\u4e8e\u548cmysql\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<li>sqlalchemy\uff1a\u7528\u4e8e\u548cmysql\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<li>cx_Oracle\uff1a\u7528\u4e8e\u548coracle\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<li>sqlite3\uff1a\u5185\u7f6e\u5e93\uff0c\u7528\u4e8e\u548csqlite\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<li>pymssql\uff1a\u7528\u4e8e\u548csql server\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<li>pymongo\uff1a\u7528\u4e8e\u548cmongodb\u975e\u5173\u7cfb\u578b\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<li>redis\u3001pyredis\uff1a\u7528\u4e8e\u548credis\u975e\u5173\u7cfb\u578b\u6570\u636e\u5e93\u7684\u4ea4\u4e92<\/li>\n<\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>python\u5904\u7406\u6570\u636e\u6587\u4ef6\u7b2c\u4e00\u6b65\u662f\u8981\u8bfb\u53d6\u6570\u636e\uff0c\u6587\u4ef6\u7c7b\u578b\u4e3b\u8981\u5305\u62ec\u6587\u672c\u6587\u4ef6\uff08csv\u3001txt\u7b49\uff09\u3001excel\u6587\u4ef6\u3001\u6570\u636e &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"http:\/\/www.weijing.co\/?p=1664\"> <span class=\"screen-reader-text\">python\u91cc\u8bfb\u5199excel\u7b49\u6570\u636e\u6587\u4ef6\u7684\u51e0\u79cd\u5e38\u7528\u65b9\u5f0f<\/span> \u67e5\u770b\u5168\u6587 &raquo;<\/a><\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"default","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":""},"categories":[106,126],"tags":[],"uagb_featured_image_src":{"full":false,"thumbnail":false,"medium":false,"medium_large":false,"large":false,"1536x1536":false,"2048x2048":false,"mailpoet_newsletter_max":false,"woocommerce_thumbnail":false,"woocommerce_single":false,"woocommerce_gallery_thumbnail":false,"shop_catalog":false,"shop_single":false,"shop_thumbnail":false},"uagb_author_info":{"display_name":"weijing","author_link":"http:\/\/www.weijing.co\/?author=4"},"uagb_comment_info":0,"uagb_excerpt":"python\u5904\u7406\u6570\u636e\u6587\u4ef6\u7b2c\u4e00\u6b65\u662f\u8981\u8bfb\u53d6\u6570\u636e\uff0c\u6587\u4ef6\u7c7b\u578b\u4e3b\u8981\u5305\u62ec\u6587\u672c\u6587\u4ef6\uff08csv\u3001txt\u7b49\uff09\u3001excel\u6587\u4ef6\u3001\u6570\u636e&hellip;","_links":{"self":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/posts\/1664"}],"collection":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1664"}],"version-history":[{"count":0,"href":"http:\/\/www.weijing.co\/index.php?rest_route=\/wp\/v2\/posts\/1664\/revisions"}],"wp:attachment":[{"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1664"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1664"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.weijing.co\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1664"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}