{"id":97,"date":"2024-12-16T00:57:55","date_gmt":"2024-12-15T16:57:55","guid":{"rendered":"http:\/\/www.luips.com\/?p=97"},"modified":"2024-12-16T00:57:55","modified_gmt":"2024-12-15T16:57:55","slug":"python%e6%95%b0%e6%8d%ae%e5%ad%98%e5%82%a8","status":"publish","type":"post","link":"https:\/\/www.luips.com\/index.php\/jinyanjiaocheng\/python\/python%e6%95%b0%e6%8d%ae%e5%ad%98%e5%82%a8\/","title":{"rendered":"Python\u6570\u636e\u5b58\u50a8"},"content":{"rendered":"<h1>\u6570\u636e\u5b58\u50a8<\/h1>\n<h4>\u5b66\u4e60\u76ee\u6807<\/h4>\n<ol>\n<li>\u638c\u63e1\u6587\u672c\u6570\u636e\u5b58\u50a8\u65b9\u5f0f<\/li>\n<li>\u638c\u63e1 json\u6570\u636e\u5b58\u50a8\u65b9\u5f0f<\/li>\n<li>\u719f\u6089\u8868\u683c\u6570\u636e\u5b58\u50a8<\/li>\n<li>\u638c\u63e1mysql\u5b58\u50a8<\/li>\n<li>\u638c\u63e1mongodb\u7684\u50a8\u5b58<\/li>\n<li>\u719f\u6089redis\u96c6\u5408\u7684\u4f7f\u7528<\/li>\n<li>\u638c\u63e1\u6570\u636e\u53bb\u91cd\u65b9\u6cd5<\/li>\n<\/ol>\n<p>\u200b   \u5b66\u4e60\u5b8c\u5982\u4f55\u5bf9\u6570\u636e\u8fdb\u884c\u63d0\u53d6\u4e4b\u540e\u63a5\u4e0b\u6765\u5c31\u8fdb\u5165\u5230\u6211\u4eec\u6570\u636e\u4fdd\u5b58\u7684\u73af\u8282\u4e86\uff0c\u6570\u636e\u7684\u5b58\u50a8\u591a\u79cd\u591a\u6837\uff0c\u53ef\u4ee5\u628a\u5b58\u50a8\u5927\u81f4\u5206\u4e3a\u6587\u672c\u6570\u636e\u5b58\u50a8\u548c\u6570\u636e\u5e93\u6570\u636e\u5b58\u50a8\uff0c\u5176\u4e2d\u6587\u672c\u6570\u636e\u5b58\u50a8\u9700\u8981\u638c\u63e1TXT\u6570\u636e\u3001json\u6570\u636e\u3001csv\u8868\u683c\u6570\u636e\uff1b\u6570\u636e\u5e93\u6570\u636e\u50a8\u5b58\u5230MySQL\u548cMongoDB<\/p>\n<h2>\u4e00\u3001\u6587\u672c\u6587\u4ef6\u6570\u636e\u5b58\u50a8<\/h2>\n<h3>1.\u6587\u672c\u5b58\u50a8<\/h3>\n<p><strong>\u6587\u4ef6\u6253\u5f00\u6a21\u5f0f<\/strong><\/p>\n<p>python\u4e2d\u6240\u6709open()\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\uff0c\u6587\u4ef6\u7684\u6253\u5f00\u6709\u5f88\u591a\u6a21\u5f0f\uff1a<\/p>\n<ul>\n<li>r:\u4ee5\u53ea\u8bfb\u65b9\u5f0f\u6253\u5f00\u6587\u4ef6,\u6587\u4ef6\u7684\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7684\u5f00\u5934,\u8fd9\u662f\u9ed8\u8ba4\u6a21\u5f0f\u3002<\/li>\n<li>rb:\u4ee5\u4e8c\u8fdb\u5236\u53ea\u8bfb\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\uff0c\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7684\u5f00\u5934\u3002<\/li>\n<li>r+:\u4ee5\u8bfb\u5199\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\uff0c\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7684\u5f00\u5934\u3002<\/li>\n<li>rb+: \u4ee5\u4e8c\u8fdb\u5236\u8bfb\u5199\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\uff0c\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7684\u5f00\u5934\u3002<\/li>\n<li>w:\u4ee5\u5199\u5165\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u5219\u5c06\u5176\u77bf\u76d6\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c\u5219\u521b\u5efa\u65b0\u6587\u4ef6\u3002<\/li>\n<li>wb\uff1a\u4ee5\u4e8c\u8fdb\u5236\u5199\u5165\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u5219\u5c06\u5176\u8986\u76d6\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c\u5219\u521b\u5efa\u65b0\u6587\u4ef6\u3002<\/li>\n<li>w+\uff1a\u4ee5\u8bfb\u5199\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u5219\u5c06\u5176\u8986\u76d6\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c\u5219\u521b\u5efa\u65b0\u6587\u4ef6\u3002<\/li>\n<li>wb+\uff1a\u4ee5\u4e8c\u8fdb\u5236\u8bfb\u5199\u683c\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u5219\u5c06\u5176\u8986\u76d6\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c \u5219\u521b\u5efa\u65b0\u6587\u4ef6\u3002<\/li>\n<li>a:\u4ee5\u8ffd\u52a0\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7ed3\u5c3e\u3002\u4e5f\u5c31\u662f\u8bf4\uff0c\u65b0\u7684\u5185\u5bb9\u5c06\u4f1a\u88ab\u5199\u5165\u5230\u5df2\u6709\u5185\u5bb9\u4e4b\u540e\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c \u5219\u521b\u5efa\u65b0\u6587\u4ef6\u6765\u5199\u5165\u3002<\/li>\n<li>ab:\u4ee5\u4e8c\u8fdb\u5236\u8ffd\u52a0\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u5219\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7ed3\u5c3e\u3002\u4e5f\u5c31\u662f\u8bf4\uff0c\u65b0\u7684\u5185\u5bb9\u5c06\u4f1a\u88ab\u5199\u5165\u5230\u5df1\u6709\u5185\u5bb9\u4e4b\u540e\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c\u5219\u521b\u5efa\u65b0\u6587\u4ef6\u6765\u5199\u5165\u3002<\/li>\n<li>a+\uff1a\u4ee5\u8bfb\u5199\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7684\u7ed3\u5c3e\u3002\u6587\u4ef6\u6253\u5f00\u65f6\u4f1a\u662f\u8ffd\u52a0\u6a21\u5f0f\uff1b\u5982\u679c\u7729\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c\u5219\u521b\u5efa\u65b0\u6587\u4ef6\u6765\u8bfb\u5199\u3002<\/li>\n<li>ab+\uff1a\u4ee5\u4e8c\u8fdb\u5236\u8ffd\u52a0\u65b9\u5f0f\u6253\u5f00\u4e00\u4e2a\u6587\u4ef6\u3002\u5982\u679c\u8be5\u6587\u4ef6\u5df2\u5b58\u5728\uff0c\u5219\u6587\u4ef6\u6307\u9488\u5c06\u4f1a\u653e\u5728\u6587\u4ef6\u7ed3\u5c3e\uff1b\u5982\u679c\u8be5\u6587\u4ef6\u4e0d\u5b58\u5728\uff0c\u5219\u521b\u5efa\u65b0\u6587\u4ef6\u7528\u4e8e\u8bfb\u5199\u3002<\/li>\n<\/ul>\n<h3>2.\u4ee5TXT\u6587\u672c\u5f62\u5f0f\u5b58\u50a8<\/h3>\n<p>TXT \u6587\u672c\u7684\u64cd\u4f5c\u975e\u5e38\u7b80\u5355\uff0c\u4e14\u5176\u51e0\u4e4e\u517c\u5bb9\u4efb\u4f55\u5e73\u53f0\uff0c\u4f46\u662f\u5b83\u6709\u4e2a\u7f3a\u70b9\uff0c\u90a3\u5c31\u662f\u4e0d\u5229\u4e8e\u68c0\u7d22\u3002<\/p>\n<p><strong>\u6848\u5217\uff1a<\/strong><\/p>\n<p>\u200b   \u83b7\u53d6\u5230\u77e5\u4e4e\u53d1\u73b0\u91cc\u7684\u95ee\u9898<\/p>\n<p>\u200b   \u7f51\u5740\uff1ahttps:\/\/www.zhihu.com\/explore<\/p>\n<pre><code class=\"language-python line-numbers\">import requests\nfrom bs4 import BeautifulSoup\n\nurl = 'https:\/\/www.zhihu.com\/explore'\n\nheaders = {\n'cookie': '',\n'User-Agent': 'Mozilla\/5.0 (Macintosh; Intel Mac OS 10114) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/52.0.2743.116 Safari\/537.36'\n\n}\n\nhtml = requests.get(url, headers=headers).text\n\nsoup = BeautifulSoup(html, 'lxml')\ntitle_list = soup.select('div .css-1g4zjtl a')\n# print(title_list)\nfor title in title_list:\n    print(title.get_text())\n    with open('data.txt', 'a', encoding='utf-8')as f:\n        f.write(title.get_text() + '\\n')\n<\/code><\/pre>\n<h2>\u4e8c\u3001json\u6587\u4ef6\u5b58\u50a8<\/h2>\n<p>JSON\uff0c\u5168\u79f0\u4e3a JavaScript Object Notation, \u4e5f\u5c31\u662f JavaScript \u5bf9\u8c61\u6807\u8bb0\uff0c\u5b83\u901a\u8fc7\u5bf9\u8c61\u548c\u6570\u7ec4\u7684\u7ec4\u5408\u6765\u8868\u793a\u6570\u636e\uff0c\u6784\u9020\u7b80\u6d01\u4f46\u662f\u7ed3\u6784\u5316\u7a0b\u5ea6\u975e\u5e38\u9ad8\uff0c\u662f\u4e00\u79cd\u8f7b\u91cf\u7ea7\u7684\u6570\u636e\u4ea4\u6362\u683c\u5f0f\u3002\u672c\u8282\u4e2d\uff0c\u6211\u4eec\u5c31\u6765\u4e86\u89e3\u5982\u4f55\u5229\u7528 Python \u4fdd\u5b58\u6570\u636e\u5230 JSON \u6587\u4ef6\u3002<\/p>\n<h3>1.\u5bf9\u8c61\u548c\u6570\u7ec4<\/h3>\n<p>\u200b   \u5728 JavaScript \u8bed\u8a00\u4e2d\uff0c\u4e00\u5207\u90fd\u662f\u5bf9\u8c61\u3002\u56e0\u6b64\uff0c\u4efb\u4f55\u652f\u6301\u7684\u7c7b\u578b\u90fd\u53ef\u4ee5\u901a\u8fc7 JSON \u6765\u8868\u793a\uff0c\u4f8b\u5982\u5b57\u7b26\u4e32\u3001\u6570\u5b57\u3001\u5bf9\u8c61\u3001\u6570\u7ec4\u7b49\uff0c\u4f46\u662f\u5bf9\u8c61\u548c\u6570\u7ec4\u662f\u6bd4\u8f83\u7279\u6b8a\u4e14\u5e38\u7528\u7684\u4e24\u79cd\u7c7b\u578b\uff0c\u4e0b\u9762\u7b80\u8981\u4ecb\u7ecd\u4e00\u4e0b\u5b83\u4eec\u3002<\/p>\n<ul>\n<li>\u5bf9\u8c61\uff1a\u5b83\u5728 JavaScript \u4e2d\u662f\u4f7f\u7528\u82b1\u62ec\u53f7 {} \u5305\u88f9\u8d77\u6765\u7684\u5185\u5bb9\uff0c\u6570\u636e\u7ed3\u6784\u4e3a {key1\uff1avalue1, key2\uff1avalue2,&#8230;} \u7684\u952e\u503c\u5bf9\u7ed3\u6784\u3002\u5728\u9762\u5411\u5bf9\u8c61\u7684\u8bed\u8a00\u4e2d\uff0ckey \u4e3a\u5bf9\u8c61\u7684\u5c5e\u6027\uff0cvalue \u4e3a\u5bf9\u5e94\u7684\u503c\u3002\u952e\u540d\u53ef\u4ee5\u4f7f\u7528\u6574\u6570\u548c\u5b57\u7b26\u4e32\u6765\u8868\u793a\u3002\u503c\u7684\u7c7b\u578b\u53ef\u4ee5\u662f\u4efb\u610f\u7c7b\u578b\u3002<\/li>\n<li>\u6570\u7ec4\uff1a\u6570\u7ec4\u5728 JavaScript \u4e2d\u662f\u65b9\u62ec\u53f7 [] \u5305\u88f9\u8d77\u6765\u7684\u5185\u5bb9\uff0c\u6570\u636e\u7ed3\u6784\u4e3a [&#8220;java&#8221;, &#8220;javascript&#8221;, &#8220;vb&#8221;, &#8230;] \u7684\u7d22\u5f15\u7ed3\u6784\u3002\u5728JavaScript \u4e2d\uff0c\u6570\u7ec4\u662f\u4e00\u79cd\u6bd4\u8f83\u7279\u6b8a\u7684\u6570\u636e\u7c7b\u578b\uff0c\u5b83\u4e5f\u53ef\u4ee5\u50cf\u5bf9\u8c61\u90a3\u6837\u4f7f\u7528\u952e\u503c\u5bf9\uff0c\u4f46\u8fd8\u662f\u7d22\u5f15\u7528\u5f97\u591a\u3002\u540c\u6837\uff0c\u503c\u7684\u7c7b\u578b\u53ef\u4ee5\u662f\u4efb\u610f\u7c7b\u578b\u3002<\/li>\n<\/ul>\n<p><strong>\u6240\u4ee5\uff0c\u4e00\u4e2a JSON \u5bf9\u8c61\u53ef\u4ee5\u5199\u4e3a\u5982\u4e0b\u5f62\u5f0f\uff1a<\/strong><\/p>\n<pre><code class=\"language-json line-numbers\">[{\n\"name\": \"Bob\", \n\"gender\": \"male\", \n\"birthday\": \"1992-10-18\" \n}, { \n\"name\": \"Selina\", \n\"gender\": \"female\", \n\"birthday\": \"1995-10-18\" \n}]\n<\/code><\/pre>\n<p>\u7531\u4e2d\u62ec\u53f7\u5305\u56f4\u7684\u5c31\u76f8\u5f53\u4e8e\u5217\u8868\u7c7b\u578b\uff0c\u5217\u8868\u4e2d\u7684\u6bcf\u4e2a\u5143\u7d20\u53ef\u4ee5\u662f\u4efb\u610f\u7c7b\u578b\uff0c\u8fd9\u4e2a\u793a\u4f8b\u4e2d\u5b83\u662f\u5b57\u5178\u7c7b\u578b\uff0c\u7531\u5927\u62ec\u53f7\u5305\u56f4\u3002<\/p>\n<p>JSON \u53ef\u4ee5\u7531\u4ee5\u4e0a\u4e24\u79cd\u5f62\u5f0f\u81ea\u7531\u7ec4\u5408\u800c\u6210\uff0c\u53ef\u4ee5\u65e0\u9650\u6b21\u5d4c\u5957\uff0c\u7ed3\u6784\u6e05\u6670\uff0c\u662f\u6570\u636e\u4ea4\u6362\u7684\u6781\u4f73\u65b9\u5f0f\u3002<\/p>\n<h3>2.json\u6a21\u5757\u65b9\u6cd5<\/h3>\n<table>\n<thead>\n<tr>\n<th>\u65b9\u6cd5<\/th>\n<th>\u4f5c\u7528<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>json.dumps()<\/td>\n<td>\u628apython\u5bf9\u8c61\u8f6c\u6362\u6210json\u5bf9\u8c61\u7684\u4e00\u4e2a\u8fc7\u7a0b\uff0c\u751f\u6210\u7684\u662f\u5b57\u7b26\u4e32\u3002<\/td>\n<\/tr>\n<tr>\n<td>json.dump()<\/td>\n<td>\u7528\u4e8e\u5c06dict\u7c7b\u578b\u7684\u6570\u636e\u8f6c\u6210str\uff0c\u5e76\u5199\u5165\u5230json\u6587\u4ef6\u4e2d<\/td>\n<\/tr>\n<tr>\n<td>json.loads()<\/td>\n<td>\u5c06json\u5b57\u7b26\u4e32\u89e3\u7801\u6210python\u5bf9\u8c61<\/td>\n<\/tr>\n<tr>\n<td>json.load()<\/td>\n<td>\u7528\u4e8e\u4ecejson\u6587\u4ef6\u4e2d\u8bfb\u53d6\u6570\u636e\u3002<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h3>3.json\u6a21\u5757\u5b9e\u9645\u64cd\u4f5c<\/h3>\n<p><strong>\u6848\u5217\uff1a<\/strong><\/p>\n<p>\u200b   \u83b7\u53d6\u52304399\u6700\u65b0\u5c0f\u6e38\u620f<\/p>\n<p>\u200b   \u7f51\u5740\uff1ahttps:\/\/www.4399.com\/flash\/<\/p>\n<pre><code class=\"language-python line-numbers\">import json\nimport requests\nfrom lxml import etree\n\n\nurl = 'https:\/\/www.4399.com\/flash\/'\n\nresponse = requests.get(url)\nhtml = etree.HTML(response.content.decode('gbk'))\na_list = html.xpath('\/\/ul[@class=\"n-game cf\"]\/li\/a')\ndata_list = []\nfor a in a_list:\n    item = {}\n    item['href'] = a.xpath('.\/@href')[0]\n    item['title'] = a.xpath('.\/b\/text()')[0]\n    data_list.append(item)\n\nwith open('data.json', 'w', encoding='utf-8')as file:\n    file.write(json.dumps(data_list))\n<\/code><\/pre>\n<p>\u53ef\u4ee5\u770b\u5230\uff0c\u4e2d\u6587\u5b57\u7b26\u90fd\u53d8\u6210\u4e86 Unicode \u5b57\u7b26\uff0c\u8fd9\u5e76\u4e0d\u662f\u6211\u4eec\u60f3\u8981\u7684\u7ed3\u679c\u3002<\/p>\n<p>\u4e3a\u4e86\u8f93\u51fa\u4e2d\u6587\uff0c\u8fd8\u9700\u8981\u6307\u5b9a\u53c2\u6570 ensure_ascii \u4e3a False\uff0c\u53e6\u5916\u8fd8\u8981\u89c4\u5b9a\u6587\u4ef6\u8f93\u51fa\u7684\u7f16\u7801\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">file.write(json.dumps(data_list, indent=2, ensure_ascii=False))\n<\/code><\/pre>\n<h2>\u4e09\u3001\u8868\u683c\u6587\u4ef6\u6570\u636e\u5b58\u50a8<\/h2>\n<p>\u200b   CSV\uff0c\u5168\u79f0\u4e3a Comma-Separated Values\uff0c\u4e2d\u6587\u53ef\u4ee5\u53eb\u4f5c\u9017\u53f7\u5206\u9694\u503c\u6216\u5b57\u7b26\u5206\u9694\u503c\uff0c\u5176\u6587\u4ef6\u4ee5\u7eaf\u6587\u672c\u5f62\u5f0f\u5b58\u50a8\u8868\u683c\u6570\u636e\u3002\u8be5\u6587\u4ef6\u662f\u4e00\u4e2a\u5b57\u7b26\u5e8f\u5217\uff0c\u53ef\u4ee5\u7531\u4efb\u610f\u6570\u76ee\u7684\u8bb0\u5f55\u7ec4\u6210\uff0c\u8bb0\u5f55\u95f4\u4ee5\u67d0\u79cd\u6362\u884c\u7b26\u5206\u9694\u3002\u6bcf\u6761\u8bb0\u5f55\u7531\u5b57\u6bb5\u7ec4\u6210\uff0c\u5b57\u6bb5\u95f4\u7684\u5206\u9694\u7b26\u662f\u5176\u4ed6\u5b57\u7b26\u6216\u5b57\u7b26\u4e32\uff0c\u6700\u5e38\u89c1\u7684\u662f\u9017\u53f7\u6216\u5236\u8868\u7b26\u3002\u4e0d\u8fc7\u6240\u6709\u8bb0\u5f55\u90fd\u6709\u5b8c\u5168\u76f8\u540c\u7684\u5b57\u6bb5\u5e8f\u5217\uff0c\u76f8\u5f53\u4e8e\u4e00\u4e2a\u7ed3\u6784\u5316\u8868\u7684\u7eaf\u6587\u672c\u5f62\u5f0f\u3002\u5b83\u6bd4 Excel \u6587\u4ef6\u66f4\u52a0\u7b80\u6d01\uff0cXLS \u6587\u672c\u662f\u7535\u5b50\u8868\u683c\uff0c\u5b83\u5305\u542b\u4e86\u6587\u672c\u3001\u6570\u503c\u3001\u516c\u5f0f\u548c\u683c\u5f0f\u7b49\u5185\u5bb9\uff0c\u800c CSV \u4e2d\u4e0d\u5305\u542b\u8fd9\u4e9b\u5185\u5bb9\uff0c\u5c31\u662f\u7279\u5b9a\u5b57\u7b26\u5206\u9694\u7684\u7eaf\u6587\u672c\uff0c\u7ed3\u6784\u7b80\u5355\u6e05\u6670\u3002\u6240\u4ee5\uff0c\u6709\u65f6\u5019\u7528 CSV \u6765\u4fdd\u5b58\u6570\u636e\u662f\u6bd4\u8f83\u65b9\u4fbf\u7684\u3002\u672c\u8282\u4e2d\uff0c\u6211\u4eec\u6765\u8bb2\u89e3Python \u8bfb\u53d6\u548c\u5199\u5165 CSV \u6587\u4ef6\u7684\u8fc7\u7a0b\u3002<\/p>\n<h3>1.\u5199\u5165<\/h3>\n<p>\u8fd9\u91cc\u5148\u770b\u4e00\u4e2a\u6700\u7b80\u5355\u7684\u4f8b\u5b50\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">import csv \nwith open('data.csv', 'w') as csvfile: \n    writer = csv.writer(csvfile) \n    writer.writerow(['id', 'name', 'age']) \n    writer.writerow(['10001', 'Mike', 20]) \n    writer.writerow(['10002', 'Bob', 22]) \n    writer.writerow(['10003', 'Jordan', 21])\n<\/code><\/pre>\n<p>\u9996\u5148\uff0c\u6253\u5f00 data.csv \u6587\u4ef6\uff0c\u7136\u540e\u6307\u5b9a\u6253\u5f00\u7684\u6a21\u5f0f\u4e3a w\uff08\u5373\u5199\u5165\uff09\uff0c\u83b7\u5f97\u6587\u4ef6\u53e5\u67c4\uff0c\u968f\u540e\u8c03\u7528 csv \u5e93\u7684writer \u65b9\u6cd5\u521d\u59cb\u5316\u5199\u5165\u5bf9\u8c61\uff0c\u4f20\u5165\u8be5\u53e5\u67c4\uff0c\u7136\u540e\u8c03\u7528 writerow \u65b9\u6cd5\u4f20\u5165\u6bcf\u884c\u7684\u6570\u636e\u5373\u53ef\u5b8c\u6210\u5199\u5165\u3002<\/p>\n<p>\u5982\u679c\u60f3\u4fee\u6539\u5217\u4e0e\u5217\u4e4b\u95f4\u7684\u5206\u9694\u7b26\uff0c\u53ef\u4ee5\u4f20\u5165 delimiter \u53c2\u6570\uff0c\u5176\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">import csv \nwith open('data.csv', 'w') as csvfile: \n    writer = csv.writer(csvfile, delimiter=' ') \n    writer.writerow(['id', 'name', 'age']) \n    writer.writerow(['10001', 'Mike', 20]) \n    writer.writerow(['10002', 'Bob', 22]) \n    writer.writerow(['10003', 'Jordan', 21])\n<\/code><\/pre>\n<h3>2.\u591a\u884c\u5199\u5165<\/h3>\n<p>\u8c03\u7528 writerows \u65b9\u6cd5\u540c\u65f6\u5199\u5165\u591a\u884c\uff0c\u6b64\u65f6\u53c2\u6570\u5c31\u9700\u8981\u4e3a\u4e8c\u7ef4\u5217\u8868\uff0c\u4f8b\u5982\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">import csv \nwith open('data.csv', 'w') as csvfile: \n    writer = csv.writer(csvfile) \n    writer.writerow(['id', 'name', 'age']) \n    writer.writerows([['10001', 'Mike', 20], ['10002', 'Bob', 22], ['10003', 'Jordan', 21]])\n<\/code><\/pre>\n<h3>3.\u5b57\u5178\u5199\u5165<\/h3>\n<p>\u7528\u5b57\u5178\u6765\u8868\u793a\u3002\u5728 csv \u5e93\u4e2d\u4e5f\u63d0\u4f9b\u4e86\u5b57\u5178\u7684\u5199\u5165\u65b9\u5f0f\uff0c\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">import csv \nwith open('data.csv', 'w') as csvfile: \n    fieldnames = ['id', 'name', 'age'] \n    writer = csv.DictWriter(csvfile, fieldnames=fieldnames) \n    writer.writeheader() \n    writer.writerow({'id': '10001', 'name': 'Mike', 'age': 20}) \n    writer.writerow({'id': '10002', 'name': 'Bob', 'age': 22}) \n    writer.writerow({'id': '10003', 'name': 'Jordan', 'age': 21})\n<\/code><\/pre>\n<h3>4.\u722c\u866b\u91c7\u96c6\u5165\u5e93<\/h3>\n<p><strong>\u6848\u5217\uff1a<\/strong><\/p>\n<p>\u200b   \u91c7\u96c6B\u7ad9\u4e0a\u89c6\u9891\u6570\u636e\u4fe1\u606f<\/p>\n<p>\u200b   \u7f51\u5740\uff1ahttps:\/\/search.bilibili.com\/video?keyword=%E7%BE%8E%E5%A5%B3&amp;from_source=webtop_search&amp;spm_id_from=333.1007&amp;search_source=5<\/p>\n<pre><code class=\"language-python line-numbers\">import csv\nimport requests\n\nwith open('b\u7ad9.csv', 'a', encoding='utf-8', newline='')as f:\n    fieldnames = ['author', 'arcurl', 'tag']\n    writer = csv.DictWriter(f, fieldnames=fieldnames)\n    writer.writeheader()\n    for i in range(1, 5):\n        url = f'https:\/\/api.bilibili.com\/x\/web-interface\/wbi\/search\/type?__refresh__=true&amp;_extra=&amp;context=&amp;page={i}&amp;page_size=42&amp;from_source=&amp;from_spmid=333.337&amp;platform=pc&amp;highlight=1&amp;single_column=0&amp;keyword=%E5%8A%A8%E6%BC%AB&amp;qv_id=fIPKpNTneO0oVdF05oqicBkdGC7Bbhpc&amp;ad_resource=5654&amp;source_tag=3&amp;gaia_vtoken=&amp;category_id=&amp;search_type=video&amp;dynamic_offset=36&amp;w_rid=0a5ef9656b684bc8036d1993840ec427&amp;wts=1679638956'\n        headers = {\n            'origin': 'https:\/\/search.bilibili.com',\n            'cookie': \"\",\n            'user-agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/111.0.0.0 Safari\/537.36'\n        }\n\n        response = requests.get(url, headers=headers)\n        print(response.json())\n\n        for res in response.json()['data']['result']:\n            item = {}\n            item['author'] = res['author']\n            item['arcurl'] = res['arcurl']\n            item['tag'] = res['tag']\n            writer.writerow(item)\n<\/code><\/pre>\n<h2>\u56db\u3001MySQL\u5b58\u50a8<\/h2>\n<p>\u5173\u7cfb\u578b\u6570\u636e\u5e93\u662f\u57fa\u4e8e\u5173\u7cfb\u6a21\u578b\u7684\u6570\u636e\u5e93\uff0c\u800c\u5173\u7cfb\u6a21\u578b\u662f\u901a\u8fc7\u4e8c\u7ef4\u8868\u6765\u4fdd\u5b58\u7684\uff0c\u6240\u4ee5\u5b83\u7684\u5b58\u50a8\u65b9\u5f0f\u5c31\u662f\u884c<\/p>\n<p>\u5217\u7ec4\u6210\u7684\u8868\uff0c\u6bcf\u4e00\u5217\u662f\u4e00\u4e2a\u5b57\u6bb5\uff0c\u6bcf\u4e00\u884c\u662f\u4e00\u6761\u8bb0\u5f55\u3002\u8868\u53ef\u4ee5\u770b\u4f5c\u67d0\u4e2a\u5b9e\u4f53\u7684\u96c6\u5408\uff0c\u800c\u5b9e\u4f53\u4e4b\u95f4\u5b58\u5728\u8054<\/p>\n<p>\u7cfb\uff0c\u8fd9\u5c31\u9700\u8981\u8868\u4e0e\u8868\u4e4b\u95f4\u7684\u5173\u8054\u5173\u7cfb\u6765\u4f53\u73b0\uff0c\u5982\u4e3b\u952e\u5916\u952e\u7684\u5173\u8054\u5173\u7cfb\u3002\u591a\u4e2a\u8868\u7ec4\u6210\u4e00\u4e2a\u6570\u636e\u5e93\uff0c\u4e5f\u5c31\u662f<\/p>\n<p>\u5173\u7cfb\u578b\u6570\u636e\u5e93\u3002<\/p>\n<p>\u5173\u7cfb\u578b\u6570\u636e\u5e93\u6709\u591a\u79cd\uff0c\u5982 SQLite\u3001MySQL\u3001Oracle\u3001SQL Server\u3001DB2 \u7b49\u3002<\/p>\n<h3>1.\u51c6\u5907\u5de5\u4f5c<\/h3>\n<p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u8bf7\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u597d\u4e86 MySQL \u6570\u636e\u5e93\u5e76\u4fdd\u8bc1\u5b83\u80fd\u6b63\u5e38\u8fd0\u884c\uff0c\u800c\u4e14\u9700\u8981\u5b89\u88c5\u597d PyMySQL\u5e93\u3002\u5b89\u88c5\u5305\u81ea\u884c\u89e3\u51b3<\/p>\n<p>\u4e0b\u8f7d\u5730\u5740;https:\/\/dev.mysql.com\/downloads\/mysql\/<\/p>\n<p>\u5b89\u88c5\u5305\uff1ahttps:\/\/downloads.mysql.com\/archives\/get\/p\/23\/file\/mysql-5.7.9-winx64.zip<\/p>\n<p>\u53c2\u8003\u5730\u5740\uff1ahttps:\/\/blog.csdn.net\/ychgyyn\/article\/details\/84404217<\/p>\n<h3>2.\u8fde\u63a5\u6570\u636e\u5e93<\/h3>\n<p>\u8fd9\u91cc\uff0c\u9996\u5148\u5c1d\u8bd5\u8fde\u63a5\u4e00\u4e0b\u6570\u636e\u5e93\u3002\u5047\u8bbe\u5f53\u524d\u7684 MySQL \u8fd0\u884c\u5728\u672c\u5730\uff0c\u7528\u6237\u540d\u4e3a root\uff0c\u5bc6\u7801\u4e3a root\uff0c\u8fd0\u884c\u7aef\u53e3\u4e3a 3306\u3002\u8fd9\u91cc\u5229\u7528 PyMySQL \u5148\u8fde\u63a5 MySQL\uff0c\u7136\u540e\u521b\u5efa\u4e00\u4e2a\u65b0\u7684\u6570\u636e\u5e93\uff0c\u540d\u5b57\u53eb\u4f5c spiders\uff0c<\/p>\n<p>\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">import pymysql\n\n\ndef db_connect():\n    # \u6253\u5f00\u6570\u636e\u5e93\u8fde\u63a5\n    db = pymysql.connect(host=\"localhost\", user=\"root\", password=\"root\")\n    # \u4f7f\u7528cursor()\u65b9\u6cd5\u521b\u5efa\u4e00\u4e2a\u6e38\u6807\u5bf9\u8c61cursor\n    cursor = db.cursor()\n    # \u4f7f\u7528execute()\u65b9\u6cd5\u6267\u884cSQL\u67e5\u8be2\n    cursor.execute(\"SELECT VERSION()\")\n    # \u4f7f\u7528 fetchone() \u65b9\u6cd5\u83b7\u53d6\u5355\u6761\u6570\u636e\n    data = cursor.fetchone()\n    # data\u8fd4\u56de\u503c\u4e3a\u4e00\u4e2a\u5143\u7ec4\n    print(data)\n    # \u521b\u5efa\u6570\u636e\u5e93\n    cursor.execute(\"CREATE DATABASE spiders DEFAULT CHARACTER SET utf8\")\n    # \u5173\u95ed\u6570\u636e\u5e93\u8fde\u63a5\n    db.close()\n\ndef main():\n    db_connect()\n\nif __name__ == \"__main__\":\n    main()\n<\/code><\/pre>\n<h3>3.\u521b\u5efa\u6570\u636e\u8868<\/h3>\n<pre><code class=\"language-python line-numbers\">import pymysql\n\n\ndef create_table():\n    db = pymysql.connect(host=\"localhost\", user=\"root\", password=\"root\", db=\"spiders\")\n    # \u4f7f\u7528 cursor() \u65b9\u6cd5\u521b\u5efa\u4e00\u4e2a\u6e38\u6807\u5bf9\u8c61cursor\n    cursor = db.cursor()\n    # \u4f7f\u7528\u9884\u5904\u7406\u8bed\u53e5\u521b\u5efa\u8868\n    sql = '''\n    CREATE TABLE IF NOT EXISTS students (\n        id VARCHAR(255) NOT NULL, \n        name VARCHAR(255) NOT NULL, \n        age INT NOT NULL, \n        PRIMARY KEY (id))\n    '''\n    try:\n        cursor.execute(sql)\n        print(\"CREATE TABLE SUCCESS.\")\n    except Exception as ex:\n        print(f\"CREATE TABLE FAILED,CASE:{ex}\")\n    finally:\n        # \u5173\u95ed\u6570\u636e\u5e93\u8fde\u63a5\n        db.close()\n\ndef main():\n    create_table()\n\n\nif __name__ == \"__main__\":\n    main()\n<\/code><\/pre>\n<h3>4.\u63d2\u5165\u6570\u636e<\/h3>\n<pre><code class=\"language-python line-numbers\">import pymysql\n\nid = '00001'\nuser = '\u67cf\u6c4c'\nage = 18\n\ndef insert_record():\n    db = pymysql.connect(host='localhost', user='root', password='root', db='spiders')\n    # \u83b7\u53d6\u6e38\u6807\n    cursor = db.cursor()\n    # SQL \u63d2\u5165\u8bed\u53e5\n    sql = 'INSERT INTO students(id, name, age) values(%s, %s, %s)'\n    # \u6267\u884c SQL \u8bed\u53e5\n    try:\n        cursor.execute(sql,  (id, user, age))\n        # \u63d0\u4ea4\u5230\u6570\u636e\u5e93\u6267\u884c\n        db.commit()\n        print('\u6570\u636e\u63d2\u5165\u6210\u529f...')\n    except Exception as e:\n        print(f'\u6570\u636e\u63d2\u5165\u5931\u8d25: {e}')\n        # \u5982\u679c\u53d1\u751f\u9519\u8bef\u5c31\u56de\u6eda\n        db.rollback()\n    finally:\n        # \u5173\u95ed\u6570\u636e\u5e93\u8fde\u63a5\n        db.close()\n\n\nif __name__ == '__main__':\n    insert_record()\n<\/code><\/pre>\n<h3>5.\u722c\u866b\u6570\u636e\u91c7\u96c6\u5165\u5e93<\/h3>\n<p>\u200b   \u8981\u6c42\uff1a\u83b7\u53d6\u5230\u963f\u91cc\u62db\u8058\u7684\u6570\u636e\u4fe1\u606f<\/p>\n<p>\u200b   \u7f51\u5740\uff1ahttps:\/\/talent.alibaba.com\/off-campus\/position-list?lang=zh<\/p>\n<pre><code class=\"language-python line-numbers\">import requests\nimport pymysql\n\n\nclass Baidu(object):\n    def __init__(self):\n        self.db = pymysql.connect(host=\"localhost\", user=\"root\", password=\"root\", db=\"spiders\")\n        self.cursor = self.db.cursor()\n        self.url = 'https:\/\/talent.alibaba.com\/position\/search'\n        self.headers = {\n            'cookie': 'XSRF-TOKEN=09d5fe8f-08a2-4d3c-a43f-93d8b696fb32; SESSION=QjM2QUVFNUM3QTM1MzFGMzI2MzhDMUQ1MTkyNkFCQUU=; l=fBrMihtqNPyVb32pBO5Courza779zCRXCsPzaNbMiIEGa1zCCdxCJN5sdROwAdtjgT52SQxr24w81dFpyvzLRAkDBeYQsiooVC96-eM3N7AN.; isg=BOHhya8gIa2r9Y3Z8AhN8hvB8K37jlWAJhO6skOyCejQqgx8sdrWUPerDN4sYu24; tfstk=cmGNBF1gICdaEC3v2WVqYrPt1fU1a40io6z7Innsc3K6Wdeu4s4NDyqpwyzf8i2G.',\n            'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/105.0.0.0 Safari\/537.36'\n        }\n        self.params = {\n            \"_csrf\": \"09d5fe8f-08a2-4d3c-a43f-93d8b696fb32\"\n        }\n\n\n    def get_data(self, page):  # \u83b7\u53d6\u5730\u5740\u548cUser-Agent\n        data = {\n            \"channel\": \"group_official_site\",\n            \"language\": \"zh\",\n            \"batchId\": \"\",\n            \"categories\": \"\",\n            \"deptCodes\": [],\n            \"key\": \"\",\n            \"pageIndex\": page,\n            \"pageSize\": 10,\n            \"regions\": \"\",\n            \"subCategories\": \"\"\n        }\n        response = requests.post(url=self.url, params=self.params, headers=self.headers, json=data)\n        return response.json()\n\n    def parse_data(self, response):\n        # print(response)\n        data_list = response[\"content\"]['datas']\n        for node in data_list:\n            workLocations = ','.join(node['workLocations'])\n\n            name = node['name']\n            requirement = node['requirement']\n            self.save_data(workLocations, name, requirement)\n\n    def create_table(self):\n        # \u4f7f\u7528\u9884\u5904\u7406\u8bed\u53e5\u521b\u5efa\u8868\n        sql = '''\n                CREATE TABLE IF NOT EXISTS ali(\n                    id int primary key auto_increment not null,\n                    workLocations VARCHAR(255) NOT NULL, \n                    name VARCHAR(255) NOT NULL, \n                    requirement TEXT)\n        '''\n        try:\n            self.cursor.execute(sql)\n            print(\"CREATE TABLE SUCCESS.\")\n        except Exception as ex:\n            print(f\"CREATE TABLE FAILED,CASE:{ex}\")\n\n    def save_data(self, workLocations, name, requirement):\n        # SQL \u63d2\u5165\u8bed\u53e5\n        sql = 'INSERT INTO ali(id, workLocations, name, requirement) values(%s, %s, %s, %s)'\n        # \u6267\u884c SQL \u8bed\u53e5\n        try:\n            self.cursor.execute(sql, (0, workLocations, name, requirement))\n            # \u63d0\u4ea4\u5230\u6570\u636e\u5e93\u6267\u884c\n            self.db.commit()\n            print('\u6570\u636e\u63d2\u5165\u6210\u529f...')\n        except Exception as e:\n            print(f'\u6570\u636e\u63d2\u5165\u5931\u8d25: {e}')\n            # \u5982\u679c\u53d1\u751f\u9519\u8bef\u5c31\u56de\u6eda\n            self.db.rollback()\n\n    def run(self):\n        self.create_table()\n        for i in range(1, 10):\n            response = self.get_data(i)\n            self.parse_data(response)\n\n        # \u5173\u95ed\u6570\u636e\u5e93\u8fde\u63a5\n        self.db.close()\n\n\nif __name__ == '__main__':\n    baidu = Baidu()\n    baidu.run()\n<\/code><\/pre>\n<h2>\u4e94\u3001MongoDB\u5b58\u50a8<\/h2>\n<h3>1.MongoDB\u7b80\u4ecb<\/h3>\n<p>\u200b   MongoDB \u662f\u7531 C++ \u8bed\u8a00\u7f16\u5199\u7684\u975e\u5173\u7cfb\u578b\u6570\u636e\u5e93\uff0c\u662f\u4e00\u4e2a\u57fa\u4e8e\u5206\u5e03\u5f0f\u6587\u4ef6\u5b58\u50a8\u7684\u5f00\u6e90\u6570\u636e\u5e93\u7cfb\u7edf\uff0c\u5176\u5185\u5bb9\u5b58\u50a8\u5f62\u5f0f\u7c7b\u4f3cJSON \u5bf9\u8c61\uff0c\u5b83\u7684\u5b57\u6bb5\u503c\u53ef\u4ee5\u5305\u542b\u5176\u4ed6\u6587\u6863\u3001\u6570\u7ec4\u53ca\u6587\u6863\u6570\u7ec4\uff0c\u975e\u5e38\u7075\u6d3b\u3002\u5728\u8fd9\u4e00\u8282\u4e2d\uff0c\u6211\u4eec\u5c31\u6765\u770b\u770b Python 3 \u4e0b MongoDB \u7684\u5b58\u50a8\u64cd\u4f5c\u3002<\/p>\n<p>\u5e38\u7528\u547d\u4ee4:<\/p>\n<ol>\n<li>\u67e5\u8be2\u6570\u636e\u5e93:  show dbs<\/p>\n<\/li>\n<li>\n<p>\u4f7f\u7528\u6570\u636e\u5e93:  use \u5e93\u540d<\/p>\n<\/li>\n<li>\n<p>\u67e5\u770b\u96c6\u5408:  show tables\/show collections<\/p>\n<\/li>\n<li>\n<p>\u67e5\u8be2\u8868\u6570\u636e:  db.\u96c6\u5408\u540d.find()<\/p>\n<\/li>\n<li>\n<p>\u5220\u9664\u8868:  db.\u96c6\u5408\u540d.drop()<\/p>\n<\/li>\n<\/ol>\n<h3>2. \u8fde\u63a5 MongoDB<\/h3>\n<p>\u200b   \u8fde\u63a5 MongoDB \u65f6\uff0c\u6211\u4eec\u9700\u8981\u4f7f\u7528 PyMongo \u5e93\u91cc\u9762\u7684 MongoClient\u3002\u4e00\u822c\u6765\u8bf4\uff0c\u4f20\u5165 MongoDB \u7684 IP\u53ca\u7aef\u53e3\u5373\u53ef\uff0c\u5176\u4e2d\u7b2c\u4e00\u4e2a\u53c2\u6570\u4e3a\u5730\u5740 host\uff0c\u7b2c\u4e8c\u4e2a\u53c2\u6570\u4e3a\u7aef\u53e3 port\uff08\u5982\u679c\u4e0d\u7ed9\u5b83\u4f20\u9012\u53c2\u6570\uff0c\u9ed8\u8ba4\u662f27017\uff09<\/p>\n<pre><code class=\"language-python line-numbers\">import pymongo # \u5982\u679c\u662f\u4e91\u670d\u52a1\u7684\u6570\u636e\u5e93 \u7528\u516c\u7f51IP\u8fde\u63a5\nclient = pymongo.MongoClient(host='localhost', port=27017)\n<\/code><\/pre>\n<h3>3. \u6307\u5b9a\u6570\u636e\u5e93\u548c\u8868<\/h3>\n<pre><code class=\"language-python line-numbers\">import pymongo # \u5982\u679c\u662f\u4e91\u670d\u52a1\u7684\u6570\u636e\u5e93 \u7528\u516c\u7f51IP\u8fde\u63a5\nclient = pymongo.MongoClient(host='localhost', port=27017)\ncollection = client['students']\n<\/code><\/pre>\n<h3>4.\u63d2\u5165\u6570\u636e<\/h3>\n<p>\u63d2\u5165\u6570\u636e\u3002\u5bf9\u4e8e students \u8fd9\u4e2a\u96c6\u5408\uff0c\u65b0\u5efa\u4e00\u6761\u5b66\u751f\u6570\u636e\uff0c\u8fd9\u6761\u6570\u636e\u4ee5\u5b57\u5178\u5f62\u5f0f\u8868\u793a\uff1a<\/p>\n<pre><code class=\"language-python line-numbers\">import pymongo # \u5982\u679c\u662f\u4e91\u670d\u52a1\u7684\u6570\u636e\u5e93 \u7528\u516c\u7f51IP\u8fde\u63a5\nclient = pymongo.MongoClient(host='127.0.0.1', port=27017)\ncollection = client['students']['stu']\n\n# \u63d2\u5165\u5355\u6761\u6570\u636e\nstudent = {'id': '20170101', 'name': 'Jordan', 'age': 20, 'gender': 'male' }\nresult = collection.insert_one(student)\nprint(result)\n\n# \u63d2\u5165\u591a\u6761\u6570\u636e\nstudent1 = { 'id': '20170101', 'name': 'Jordan', 'age': 20, 'gender': 'male' }\nstudent2 = { 'id': '20170202', 'name': 'Mike', 'age': 21, 'gender': 'male' }\ncollection.insert_many([student1, student2])\n<\/code><\/pre>\n<h3>5.\u722c\u866b\u6570\u636e\u91c7\u96c6\u5165\u5e93<\/h3>\n<p>\u8981\u6c42\uff1a\u83b7\u53d6\u5230\u7231\u5947\u827a\u89c6\u9891\u7535\u89c6\u5267\u6570\u636e\u4fe1\u606f,\u6807\u9898,\u64ad\u653e\u5730\u5740,\u7b80\u4ecb<\/p>\n<p>\u7f51\u5740\uff1ahttps:\/\/list.iqiyi.com\/www\/2\/15&#8212;&#8212;&#8212;&#8212;-11-1-1-iqiyi&#8211;.html?s_source=PCW_SC<\/p>\n<pre><code class=\"language-python line-numbers\">import requests\nimport pymongo\n\n\nclass Aqiyi(object):\n    def __init__(self):\n        self.client = pymongo.MongoClient(host='127.0.0.1', port=27017)\n        self.collection = self.client['spider']['aqy']\n        self.headers = {\n            'referer': 'https:\/\/list.iqiyi.com\/www\/2\/15-------------11-1-1-iqiyi--.html?s_source=PCW_SC',\n            'user-agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/105.0.0.0 Safari\/537.36',\n            'x-requested-with': 'XMLHttpRequest'\n        }\n        self.url = 'https:\/\/pcw-api.iqiyi.com\/search\/recommend\/list'\n\n\n    def get_data(self, params):\n        response = requests.get(self.url, headers=self.headers, params=params)\n        return response.json()\n\n    def parse_data(self, data):\n        categoryVideos = data['data']['list']\n        for video in categoryVideos:\n            item = {}\n            item['title'] = video['title']\n            item['playUrl'] = video['playUrl']\n            item['description'] = video['description']\n            print(item)\n            self.save_data(item)\n\n    def save_data(self, item):\n        self.collection.insert_one(item)\n\n\n    def main(self):\n        for page in range(1, 2):\n            params = {\n                'channel_id': '2',\n                'data_type': '1',\n                'mode': '11',\n                'page_id': page,\n                'ret_num': '48',\n                'session': 'fc7d98794f15b224b169d328bf8f9f13',\n                'three_category_id': '15;must',\n            }\n            data = self.get_data(params)\n            self.parse_data(data)\n\n\n\nif __name__ == '__main__':\n    yk = Aqiyi()\n    yk.main()\n<\/code><\/pre>\n<h2>\u516d\u3001\u6570\u636e\u53bb\u91cd<\/h2>\n<h3>1.\u722c\u866b\u53bb\u91cd\u7684\u5e94\u7528\u573a\u666f<\/h3>\n<ol>\n<li>\u9632\u6b62\u53d1\u51fa\u91cd\u590d\u7684\u8bf7\u6c42<\/li>\n<li>\u9632\u6b62\u5b58\u50a8\u91cd\u590d\u7684\u6570\u636e<\/li>\n<\/ol>\n<h3>2.\u722c\u866b\u6570\u636e\u53bb\u91cd\u5b9e\u73b0\u7684\u57fa\u672c\u539f\u7406<\/h3>\n<p>\u200b   \u6839\u636e\u7ed9\u5b9a\u7684\u5224\u65ad\u4f9d\u636e\u548c\u7ed9\u5b9a\u7684\u53bb\u91cd\u5bb9\u5668\uff0c\u5c06\u539f\u59cb\u6570\u636e\u9010\u4e00\u8fdb\u884c\u5224\u65ad\uff0c\u5224\u65ad\u53bb\u91cd\u5bb9\u5668\u4e2d\u662f\u5426\u6709\u8be5\u6570\u636e\uff0c\u5982\u679c\u6ca1\u6709\u90a3\u5c31\u628a\u8be5\u6570\u636e\u5bf9\u5e94\u7684\u5224\u65ad\u4f9d\u636e\u6dfb\u52a0\u53bb\u91cd\u5bb9\u5668\u4e2d\uff0c\u540c\u65f6\u6807\u8bb0\u8be5\u6570\u636e\u662f\u4e0d\u91cd\u590d\u6570\u636e\uff0c\u5982\u679c\u6709\u5c31\u4e0d\u6dfb\u52a0\uff0c\u540c\u65f6\u6807\u8bb0\u8be5\u6570\u636e\u662f\u91cd\u590d\u6570\u636e\u3002<\/p>\n<h3>3.\u4e34\u65f6\u53bb\u91cd\u5bb9\u5668\u548c\u6301\u4e45\u5316\u53bb\u91cd\u5bb9\u5668<\/h3>\n<ol>\n<li>\u4e34\u65f6\u53bb\u91cd\u5bb9\u5668\n<p>\u6307\u5982\u5229\u7528list\u3001set\u7b49\u7f16\u7a0b\u8bed\u8a00\u7684\u6570\u636e\u7ed3\u6784\u5b58\u50a8\u53bb\u91cd\u6570\u636e\uff0c\u4e00\u65e6\u7a0b\u5e8f\u5173\u95ed\u6216\u91cd\u542f\u540e\uff0c\u53bb\u91cd\u5bb9\u5668\u4e2d\u7684\u6570\u636e\u5c31\u88ab\u56de\u6536\u4e86\u3002<\/p>\n<p>\u4f18\u70b9\uff1a\u4f7f\u7528\u4e0e\u5b9e\u73b0\u7b80\u5355\u65b9\u4fbf\uff1b<\/p>\n<p>\u7f3a\u70b9\uff1a\u4f46\u65e0\u6cd5\u5171\u4eab\u3001\u65e0\u6cd5\u6301\u4e45\u5316<\/p>\n<\/li>\n<li>\n<p>\u6301\u4e45\u5316\u53bb\u91cd\u5bb9\u5668<\/p>\n<p>\u6307\u5982\u5229\u7528 redis\u3001mysql \u7b49\u6570\u636e\u5e93\u5b58\u50a8\u53bb\u91cd\u6570\u636e\u3002<\/p>\n<p>\u4f18\u70b9\uff1a\u6301\u4e45\u5316\u3001\u5171\u4eab\uff1b<\/p>\n<p>\u7f3a\u70b9\uff1a\u4f46\u4f7f\u7528\u4e0e\u5b9e\u73b0\u76f8\u5bf9\u590d\u6742<\/p>\n<\/li>\n<\/ol>\n<h3>4.\u5e38\u7528\u51e0\u79cd\u7279\u6b8a\u7684\u539f\u59cb\u6570\u636e\u7279\u5f81\u503c\u8ba1\u7b97<\/h3>\n<ol>\n<li>\u4fe1\u606f\u6458\u8981 hash \u7b97\u6cd5\uff08\u6307\u7eb9)<\/li>\n<li>SimHash \u7b97\u6cd5 &#8211; \u6a21\u7cca\u6587\u672c<\/li>\n<li>\u5e03\u9686\u8fc7\u6ee4\u5668\u65b9\u5f0f &#8211; \u4e0a\u4ebf\u7ea7\u522b\u7684\u6570\u636e\u53bb\u91cd<\/li>\n<\/ol>\n<h3>5.Redis\u547d\u4ee4\u590d\u4e60<\/h3>\n<ol>\n<li>\u8fdb\u5165\u6570\u636e\u5e93:  redis-cli<\/li>\n<li>\u5207\u6362\u6570\u636e\u5e93:  select \u4e0b\u6807<\/li>\n<li>\u67e5\u770b\u6240\u6709\u952e:  keys *<\/li>\n<li>\u63d2\u5165\u96c6\u5408\u6570\u636e:  sadd \u952e \u503c<\/li>\n<li>\u67e5\u8be2\u96c6\u5408\u6570\u636e:  SMEMBERS \u952e<\/li>\n<li>\u5220\u9664\u952e: del \u952e<\/li>\n<\/ol>\n<h3>5.\u4ee3\u7801\u5b9e\u6218<\/h3>\n<p>\u83b7\u53d6\u8292\u679ctv\u7684\u6570\u636e\u4fe1\u606f,\u83b7\u53d6\u7b80\u4ecb,\u6f14\u5458,\u6807\u9898<\/p>\n<p>\u7f51\u5740:https:\/\/www.mgtv.com\/lib\/2?lastp=list_index&amp;lastp=ch_tv&amp;kind=19&amp;area=10&amp;year=all&amp;sort=c2&amp;chargeInfo=a1&amp;fpa=2912&amp;fpos=<\/p>\n<pre><code class=\"language-python line-numbers\">import hashlib\n\nimport redis\nimport requests\nimport pymongo\n\n\nclass Mgtv(object):\n    def __init__(self):\n        self.client = pymongo.MongoClient(host='127.0.0.1', port=27017)\n        self.collection = self.client['spider']['mgtv']\n        self.red = redis.Redis()\n        self.headers = {\n            'referer': 'https:\/\/www.mgtv.com\/',\n            'user-agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/105.0.0.0 Safari\/537.36',\n            'x-requested-with': 'XMLHttpRequest'\n        }\n        self.url = 'https:\/\/pianku.api.mgtv.com\/rider\/list\/pcweb\/v3'\n\n    def get_md5(self, val):\n        \"\"\"\u628a\u76ee\u6807\u6570\u636e\u8fdb\u884c\u54c8\u5e0c\uff0c\u7528\u54c8\u5e0c\u503c\u53bb\u91cd\u66f4\u5feb\"\"\"\n        md5 = hashlib.md5()\n        md5.update(str(val).encode('utf-8'))\n        # print(md5.hexdigest())\n        return md5.hexdigest()\n\n    def get_data(self, params):\n        response = requests.get(self.url, headers=self.headers, params=params)\n        return response.json()\n\n    def parse_data(self, data):\n        categoryVideos = data['data']['hitDocs']\n        for video in categoryVideos:\n            item = {}\n            item['story'] = video['story']\n            item['subtitle'] = video['subtitle']\n            item['title'] = video['title']\n            print(item)\n            self.save_data(item)\n\n    def save_data(self, item):\n        value = self.get_md5(item)\n        res = self.red.sadd('mg:filter', value)\n        if res:\n            self.collection.insert_one(item)\n            print('\u63d2\u5165\u6210\u529f!!!!')\n        else:\n            print('\u6570\u636e\u91cd\u590d!!!!')\n\n    def main(self):\n        for page in range(1, 2):\n            params = {\n                \"allowedRC\": \"1\",\n                \"platform\": \"pcweb\",\n                \"channelId\": \"2\",\n                \"pn\": page,\n                \"pc\": \"80\",\n                \"hudong\": \"1\",\n                \"_support\": \"10000000\",\n                \"kind\": \"19\",\n                \"area\": \"10\",\n                \"year\": \"all\",\n                \"chargeInfo\": \"a1\",\n                \"sort\": \"c2\"\n            }\n            data = self.get_data(params)\n            self.parse_data(data)\n\n\nif __name__ == '__main__':\n    mg = Mgtv()\n    mg.main()\n\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>\u6570\u636e\u5b58\u50a8 \u5b66\u4e60\u76ee\u6807 \u638c\u63e1\u6587\u672c\u6570\u636e\u5b58\u50a8\u65b9\u5f0f \u638c\u63e1 json\u6570\u636e&hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5,11],"tags":[4,14],"class_list":["post-97","post","type-post","status-publish","format-standard","hentry","category-python","category-11","tag-python","tag-14"],"_links":{"self":[{"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/posts\/97","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/comments?post=97"}],"version-history":[{"count":0,"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/posts\/97\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/media?parent=97"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/categories?post=97"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.luips.com\/index.php\/wp-json\/wp\/v2\/tags?post=97"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}