{"id":290,"date":"2017-05-17T22:32:14","date_gmt":"2017-05-17T14:32:14","guid":{"rendered":"https:\/\/ayonel.malash.net\/?p=290"},"modified":"2017-06-04T22:45:39","modified_gmt":"2017-06-04T14:45:39","slug":"coroutine_spider","status":"publish","type":"post","link":"https:\/\/ayonel.malash.net\/index.php\/2017\/05\/17\/coroutine_spider\/","title":{"rendered":"\u57fa\u4e8e\u534f\u7a0b\u3001\u5f02\u6b65IO\u7684python\u722c\u866b"},"content":{"rendered":"<p>\u534f\u7a0b\uff0c\u53c8\u79f0\u5fae\u7ebf\u7a0b\uff0c\u7ea4\u7a0b\u3002\u82f1\u6587\u540dCoroutine<\/p>\n<p>\u6211\u4eec\u53ef\u4ee5\u5c06\u534f\u7a0b\u7406\u89e3\u4e3a\u4e00\u4e2a\u5b50\u7a0b\u5e8f\/\u51fd\u6570\u7684\u7279\u4f8b\u3002\u4e0e\u5b50\u7a0b\u5e8f\/\u51fd\u6570\u4e0d\u540c\u7684\u662f\uff0c\u5b50\u7a0b\u5e8f\u8c03\u7528\u603b\u662f\u4e00\u4e2a\u5165\u53e3\uff0c\u4e00\u6b21\u8fd4\u56de\uff0c\u8c03\u7528\u987a\u5e8f\u662f\u660e\u786e\u7684\u3002\u800c\u534f\u7a0b\u7684\u8c03\u7528\u548c\u5b50\u7a0b\u5e8f\u4e0d\u540c\u3002\u534f\u7a0b\u770b\u4e0a\u53bb\u4e5f\u662f\u5b50\u7a0b\u5e8f\uff0c\u4f46\u6267\u884c\u8fc7\u7a0b\u4e2d\uff0c\u5728\u5b50\u7a0b\u5e8f\u5185\u90e8\u53ef\u4e2d\u65ad\uff0c\u7136\u540e\u8f6c\u800c\u6267\u884c\u522b\u7684\u5b50\u7a0b\u5e8f\uff0c\u5728\u9002\u5f53\u7684\u65f6\u5019\u518d\u8fd4\u56de\u6765\u63a5\u7740\u6267\u884c\u3002<\/p>\n<p>\u5b50\u7a0b\u5e8f\u4e0e\u4e3b\u7a0b\u5e8f\u662f\u8c03\u7528\u4e0e\u88ab\u8c03\u7528\u5173\u7cfb\uff0c\u800c\u534f\u7a0b\u4e4b\u95f4\u662f\u5e73\u7b49\u7684\u5173\u7cfb\uff0c\u5148\u6267\u884c\u4e00\u4e2a\u534f\u7a0bA\uff0c\u5728\u9002\u5f53\u7684\u65f6\u5019\u53bb\u6267\u884c\u53e6\u4e00\u4e2a\u534f\u7a0bB\uff0c\u5728\u9002\u5f53\u7684\u65f6\u5019\u53c8\u8fd4\u56de\u534f\u7a0bA\u7ee7\u7eed\u6267\u884c\u3002\u534f\u7a0b\u5728\u5355\u7ebf\u7a0b\u4e2d\u5b9e\u73b0\u4e86\u7c7b\u4f3c\u591a\u7ebf\u7a0b\u7684\u6548\u679c\uff0c\u4f46\u56e0\u4e3a\u534f\u7a0b\u59cb\u7ec8\u5c5e\u4e8e\u4e00\u4e2a\u7ebf\u7a0b\uff0c\u4e0d\u540c\u534f\u7a0b\u7684\u6267\u884c\u53ea\u662f\u4e00\u4e2a\u7ebf\u7a0b\u5728\u6267\u884c\u4e0d\u540c\u7684\u201c\u51fd\u6570\u201d\u800c\u5df2\uff0c\u56e0\u6b64\u5b83\u7701\u53bb\u4e86\u7ebf\u7a0b\u5207\u6362\u5e26\u6765\u7684\u5f00\u9500\uff0c\u5177\u6709\u5f88\u9ad8\u7684\u5e76\u53d1\u548c\u6027\u80fd\u3002<\/p>\n<p>\u4f46\u534f\u7a0b\u662f\u4e00\u4e2a\u7ebf\u7a0b\u6267\u884c\uff0c\u5982\u4f55\u5229\u7528\u591a\u6838CPU\u5462\uff0c\u7b54\u6848\u5c31\u662f\u534f\u7a0b+\u8fdb\u7a0b\uff0c\u6bcf\u4e2a\u6838\u7ef4\u6301\u4e00\u4e2a\u8fdb\u7a0b\uff0c\u5728\u8be5\u8fdb\u7a0b\u4e2d\u6709\u4e00\u4e2a\u7ebf\u7a0b\u6765\u6267\u884c\u534f\u7a0b\uff0c\u8fd9\u6837\u5c31\u80fd\u5145\u5206\u5229\u7528\u591a\u6838\u4ee5\u53ca\u534f\u7a0b\u7684\u9ad8\u6548\u7387\uff0c\u83b7\u5f97\u6781\u5927\u5730\u6027\u80fd\u3002<\/p>\n<p>\u5728Python\u4e2d\uff0c\u7531\u4e8eGIL\uff08Global Interpreter Lock\uff09\u7684\u5b58\u5728\uff0c\u5bfc\u81f4\u5728python\u4e2d\u7684\u591a\u7ebf\u7a0b\u5176\u5b9e\u662f\u4f2a\u591a\u7ebf\u7a0b\uff0c\u540c\u4e00\u65f6\u523b\u53ea\u6709\u4e00\u4e2a\u7ebf\u7a0b\u6b63\u5728\u6267\u884c\u3002\u56e0\u6b64\u5728python\u4e2d\u591a\u7ebf\u7a0b\u5f80\u5f80\uff08\u5bf9\u4e8eCPU\u5bc6\u96c6\u578b\uff09\u8fd8\u6ca1\u6709\u5355\u7ebf\u7a0b\u9ad8\u6548\uff0c\uff08\u5f53\u7136\u53ef\u4ee5\u7528multiprocessing\u6a21\u5757\uff0c\u5229\u7528\u591a\u8fdb\u7a0b\u5b9e\u73b0\u591a\u6838CPU\u5e76\u884c\uff09\uff0c\u56e0\u6b64python\u7684\u591a\u7ebf\u7a0b\u5bf9\u4e8eCPU\u5bc6\u96c6\u578b\u5de5\u4f5c\u5176\u5b9e\u662f\u4e2a\u9e21\u808b\u3002\u591a\u8fdb\u7a0b+\u534f\u7a0b\u624d\u662fpython\u6027\u80fd\u7684\u5927\u6740\u5668\u3002\u5728IO\u5bc6\u96c6\u578b\u5de5\u4f5c\u4e2d\uff0cpython\u7684\u591a\u7ebf\u7a0b\u80fd\u53d1\u6325\u5f97\u597d\u4e00\u4e9b\uff0c\u4f46\u8fd8\u662f\u6ca1\u6709\u534f\u7a0b\u9ad8\u6548\u3002<\/p>\n<p>\u56de\u5230\u672c\u6587\u5b9e\u73b0\u7684\u76ee\u6807\uff1a\u505a\u4e00\u4e2a\u722c\u866b\u3002\u722c\u866b\u5c5e\u4e8eIO\u5bc6\u96c6\u578b\uff0c\u90a3\u4e48\u5982\u679c\u6211\u4eec\u4e0d\u5229\u7528\u4efb\u4f55\u591a\u7ebf\u7a0b\u6216\u8005\u534f\u7a0b\u6280\u672f\uff0c\u4e5f\u5c31\u662f\u4f7f\u7528\u540c\u6b65\u6765\u5b9e\u73b0\u722c\u866b\uff0c\u90a3\u4e48\u5bf9\u4e8e\u6bcf\u4e00\u6b21\u7f51\u7edc\u8c03\u7528\uff0cCPU\u90fd\u4f1a\u963b\u585e\uff0c\u76f4\u5230\u7f51\u7edc\u8c03\u7528response\u7684\u5230\u6765\u3002\u8fd9\u5c31\u4f7fCPU\u7684\u5927\u90e8\u5206\u65f6\u95f4\u963b\u585e\u5728\u7b49\u5f85\u7f51\u7edcIO\u4e0a\uff0c\u6548\u7387\u53ca\u5176\u4f4e\u3002\u800c\u5229\u7528\u534f\u7a0b\u7684\u8bdd\uff0c\u6bcf\u5f53\u4e00\u4e2a\u534f\u7a0b\u8fdb\u884c\u7f51\u7edc\u8c03\u7528\u65f6\uff0cCPU\u4e0d\u7528\u963b\u585e\u7b49\u5f85\u800c\u662f\u76f4\u63a5\u6267\u884c\u4e0b\u4e00\u4e2a\u534f\u7a0b\uff0c\u5f53\u7f51\u7edc\u8c03\u7528\u8fd4\u56de\u540e\uff0c\u5c06\u6ce8\u518c\u5728\u4e8b\u4ef6\u5faa\u73af\u4e2d\uff0c\u5728\u672a\u6765\u7684\u67d0\u4e2a\u65f6\u523b\u63a5\u7740\u6267\u884c\u3002\u8fd9\u5c31\u662f\u5f02\u6b65IO\uff0c\u80fd\u6781\u5927\u5730\u63d0\u9ad8\u6027\u80fd\u3002<\/p>\n<p><strong>Scrapy<\/strong>\u6846\u67b6\u4f7f\u7528\u591a\u7ebf\u7a0b\u6765\u5b9e\u73b0\u722c\u866b\u8fd9\u79cdIO\u5bc6\u96c6\u578b\u7684\u5de5\u4f5c\uff0c\u4e5f\u80fd\u53d6\u5f97\u4e0d\u9519\u7684\u6027\u80fd\u3002\u4f46\u6211\u4eec\u4eca\u5929\u4e0d\u6253\u7b97\u5229\u7528\u7ebf\u7a0b\u6c60\u6765\u5b9e\u73b0\u9ad8\u6548 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0 \u00a0\u722c\u866b\uff0c\u800c\u662f\u4f7f\u7528\u534f\u7a0b\u6765\u5b9e\u73b0\u3002Python 3.5\u4ee5\u540e\u5df2\u7ecf\u76f4\u63a5\u652f\u6301async, await\u5173\u952e\u5b57\uff0c\u4f7f\u5f97\u534f\u7a0b\u7684\u5b9e\u73b0\u53d8\u5f97\u5f88\u7b80\u5355\u3002<\/p>\n<p>\u56de\u60f3\u4e00\u4e0b\u5982\u679c\u6211\u4eec\u4e0d\u4f7f\u7528\u534f\u7a0b+\u5f02\u6b65IO\uff0c\u6211\u4eec\u5c06\u8fd9\u4e48\u5b9e\u73b0,\u4ee3\u7801\u57fa\u4e8epython3.5\uff1a<\/p>\n<div class=\"codecolorer-container python railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;\"><div class=\"python codecolorer\"><span class=\"kw1\">from<\/span> <span class=\"kw3\">urllib<\/span> <span class=\"kw1\">import<\/span> request<br \/>\n<span class=\"kw1\">from<\/span> <span class=\"kw3\">urllib<\/span>.<span class=\"me1\">error<\/span> <span class=\"kw1\">import<\/span> HTTPError<br \/>\n<span class=\"kw1\">import<\/span> json<br \/>\n<br \/>\n<span class=\"kw1\">def<\/span> crawl<span class=\"br0\">&#40;<\/span>url<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; <span class=\"kw1\">try<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; res <span class=\"sy0\">=<\/span> request.<span class=\"me1\">urlopen<\/span><span class=\"br0\">&#40;<\/span>url<span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">except<\/span> HTTPError:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">return<\/span> <span class=\"kw2\">None<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">return<\/span> res.<span class=\"me1\">read<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\">#\u8fd4\u56de\u5b57\u8282\u6d41<\/span><br \/>\n<span class=\"kw1\">if<\/span> name <span class=\"sy0\">==<\/span> <span class=\"st0\">'main'<\/span>:<br \/>\n&nbsp; &nbsp; url <span class=\"sy0\">=<\/span> <span class=\"st0\">'https:\/\/api.github.com\/users\/ayonel\/followers?per_page=99&amp;amp;page=1'<\/span><br \/>\n&nbsp; &nbsp; res_data <span class=\"sy0\">=<\/span> crawl<span class=\"br0\">&#40;<\/span>url<span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; json_data <span class=\"sy0\">=<\/span> json.<span class=\"me1\">loads<\/span><span class=\"br0\">&#40;<\/span>res_data.<span class=\"me1\">decode<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u5b57\u8282\u6d41\u89e3\u7801\uff0c\u5e76\u8f6c\u4e3ajson<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">print<\/span><span class=\"br0\">&#40;<\/span>json_data<span class=\"br0\">&#41;<\/span><\/div><\/div>\n<p>\u4e0a\u9762\u8fd9\u6bb5\u4ee3\u7801\uff0c\u5229\u7528python3\u5185\u7f6e\u7684urllib\u6a21\u5757\uff0c\u722c\u53d6github API, \u8fd4\u56de\u7684\u662f<a href=\"https:\/\/github.com\/ayonel\">\u7b14\u8005\u7684github<\/a>\u7684\u7c89\u4e1d\uff08\u867d\u7136\u6ca1\u51e0\u4e2a&#8230;\uff09\u3002<\/p>\n<p>\u5728\u4e0a\u9762\u4ee3\u7801\u4e2d\uff0c\u7a0b\u5e8f\u5c06\u963b\u585e\u5728\u8fd9\u4e00\u884c\uff0c\u76f4\u5230\u7f51\u7edc\u8c03\u7528\u8fd4\u56de\u7ed3\u679c\u3002<\/p>\n<div class=\"codecolorer-container text railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;\"><div class=\"text codecolorer\">&nbsp;res = request.urlopen(url)<\/div><\/div>\n<p>\u6211\u4eec\u7684\u534f\u7a0b+\u5f02\u6b65IO\u722c\u866b\uff0c\u5c31\u662f\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u5f53\u53d1\u51fa\u7f51\u7edc\u8bf7\u6c42\uff0c\u7a0b\u5e8f\u4e0d\u7528\u963b\u585e\uff0cCPU\u76f4\u63a5\u6267\u884c\u4e0b\u4e00\u4e2a\u534f\u7a0b\u3002<br \/>\n\u5728urllib\u4e2d\u7684request\u662f\u57fa\u4e8e\u540c\u6b65\u5b9e\u73b0\u7684\uff0c\u6211\u4eec\u9700\u8981<a href=\"http:\/\/aiohttp.readthedocs.io\/en\/stable\/\">aiohttp<\/a>\u8fd9\u4e2a\u6a21\u5757\uff0c\u7528\u6765\u53d1\u51fa\u5f02\u6b65\u7684\u7f51\u7edc\u8bf7\u6c42\u3002\u53e6\u5916\uff0c\u6211\u8fd8\u5c06\u722c\u53d6\u5230\u7684\u7ed3\u679c\uff0c\u5b58\u5165\u4e86MongoDB\uff0c\u4f46\u662fpython\u4e2d\u6700\u5e38\u7528\u7684\u64cd\u4f5cMongoDB\u7684\u9a71\u52a8pymongo\u4e5f\u4e0d\u662f\u57fa\u4e8e\u5f02\u6b65\u5b9e\u73b0\u7684\uff0c\u8fd8\u597d\u6709<a href=\"http:\/\/motor.readthedocs.io\/en\/stable\/\">motor<\/a>,\u4e00\u4e2a\u57fa\u4e8e\u5f02\u6b65IO\u7684python MongoDB\u9a71\u52a8\u3002<\/p>\n<p>\u8fd8\u662f\u539f\u6765\u7684\u9700\u6c42\uff0c\u6211\u4eec\u9700\u8981\u722c\u53d6github\u4e0a\u4e00\u4e9b\u7528\u6237\u7684\u7c89\u4e1d\u3002\u722c\u53d6\u94fe\u63a5\u4e3a\uff1a<\/p>\n<div class=\"codecolorer-container text railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;\"><div class=\"text codecolorer\">https:\/\/api.github.com\/users\/{user}\/followers?per_page=99&amp;page={page}<\/div><\/div>\n<p>\u4e0a\u8ff0\u8fd9\u4e2aURL\u8fd4\u56de\u4e00\u4e2a\u7528\u6237\u7684\u7c89\u4e1d\uff0c\u5e76\u4e14\u6bcf\u9875\u6700\u591a\u8fd4\u56de99\u4e2a\uff0c\u5982\u679c\u8d85\u8fc799\u4e2a\uff0c\u5219\u9700\u8981\u5bf9<strong>page<\/strong>+1<\/p>\n<p>\u5148\u5b9a\u4e49\u4e24\u4e2a\u534f\u7a0b\u51fd\u6570\uff0c fetch \u4ee5\u53ca do_insert\uff0c\u5206\u522b\u7528\u4e8e\u5f02\u6b65\u722c\u53d6\u7f51\u9875\uff0c\u4ee5\u53ca\u5f02\u6b65\u63d2\u5165MongoDB\u3002<\/p>\n<div class=\"codecolorer-container python railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;\"><div class=\"python codecolorer\">async <span class=\"kw1\">def<\/span> fetch<span class=\"br0\">&#40;<\/span>session<span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> page<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; url <span class=\"sy0\">=<\/span> <span class=\"st0\">'https:\/\/api.github.com\/users\/'<\/span> + <span class=\"kw3\">user<\/span> + <span class=\"st0\">'\/followers?per_page=99&amp;amp;page='<\/span> + <span class=\"kw2\">str<\/span><span class=\"br0\">&#40;<\/span>page<span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">with<\/span> async_timeout.<span class=\"me1\">timeout<\/span><span class=\"br0\">&#40;<\/span><span class=\"nu0\">20<\/span><span class=\"br0\">&#41;<\/span>: &nbsp;<span class=\"co1\"># \u9ed8\u8ba4\u8d85\u65f6\u65f6\u95f420s<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; async <span class=\"kw1\">with<\/span> session.<span class=\"me1\">get<\/span><span class=\"br0\">&#40;<\/span>url<span class=\"sy0\">,<\/span> headers<span class=\"sy0\">=<\/span><span class=\"br0\">&#123;<\/span><span class=\"br0\">&#125;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"kw1\">as<\/span> response:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> response.<span class=\"me1\">status<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">200<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">return<\/span> <span class=\"kw2\">True<\/span><span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> await response.<span class=\"me1\">read<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> &nbsp;<span class=\"co1\"># True\u4ee3\u8868\u722c\u53d6\u6210\u529f<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">else<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">return<\/span> <span class=\"kw2\">False<\/span><span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> await response.<span class=\"me1\">read<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> &nbsp; <span class=\"co1\"># False\u4ee3\u8868\u722c\u53d6\u5931\u8d25<\/span><\/div><\/div>\n<p>\u8fd8\u6709\u63d2\u5165\u6570\u636e\u5e93\u51fd\u6570\uff1a<\/p>\n<div class=\"codecolorer-container python railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;\"><div class=\"python codecolorer\">async <span class=\"kw1\">def<\/span> do_insert<span class=\"br0\">&#40;<\/span>arg<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; await collection.<span class=\"me1\">insert_one<\/span><span class=\"br0\">&#40;<\/span>arg<span class=\"br0\">&#41;<\/span> &nbsp;<span class=\"co1\"># collection\u662f\u5168\u5c40\u53d8\u91cf\uff0c\u4ee3\u8868\u4f60\u8981\u63d2\u5165\u7684MongoDB\u7684collection<\/span><\/div><\/div>\n<p>\u4e0a\u9762\u8fd9\u4e24\u4e2a\u534f\u7a0b\u51fd\u6570\uff0c\u662f\u6211\u4eec\u5f02\u6b65IO\u8c03\u7528\u7684\u5173\u952e\u51fd\u6570\uff0c\u4e5f\u662f\u6211\u4eec\u722c\u866b\u6027\u80fd\u9ad8\u6548\u7684\u5173\u952e\u6240\u5728\u3002<br \/>\n\u6709\u4e86\u534f\u7a0b\u51fd\u6570\uff0c\u6211\u4eec\u5c31\u9700\u8981\u5b9a\u4e49\u4e00\u4e2a\u4e3b\u51fd\u6570\u6765\u6267\u884c\uff0c\u6211\u4eec\u7684\u4e3b\u51fd\u6570\u4e5f\u662f\u534f\u7a0b\u51fd\u6570\uff0c\u53e6\u5916\u8fd8\u4f20\u5165\u4e86\u4f60\u8981\u722c\u53d6\u7684\u7528\u6237\u96c6<\/p>\n<div class=\"codecolorer-container python railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;height:100%;\"><div class=\"python codecolorer\">async <span class=\"kw1\">def<\/span> main<span class=\"br0\">&#40;<\/span>loop<span class=\"sy0\">,<\/span> peopleSet<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; async <span class=\"kw1\">with<\/span> aiohttp.<span class=\"me1\">ClientSession<\/span><span class=\"br0\">&#40;<\/span>loop<span class=\"sy0\">=<\/span>loop<span class=\"br0\">&#41;<\/span> <span class=\"kw1\">as<\/span> session:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">for<\/span> people <span class=\"kw1\">in<\/span> peopleSet:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; page <span class=\"sy0\">=<\/span> <span class=\"nu0\">1<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">while<\/span> <span class=\"kw2\">True<\/span>: &nbsp;<span class=\"co1\"># \u56e0\u4e3a\u6709\u4e9b\u4eba\u4e0d\u6b62\u670999\u4e2a\u7c89\u4e1d\uff0c\u6240\u4ee5\u9047\u5230\u4e00\u9875\u8fd4\u56de99\u4e2a\u7c89\u4e1d\u7684\uff0c\u4e0d\u80fd\u76f4\u63a5\u4e0b\u4e00\u4e2a\u4eba\uff0c\u8fd8\u9700\u8981\u5c06page+1\uff0c\u53bb\u722c\u53d6\u8be5\u4eba\u7684\u5176\u4ed6\u7c89\u4e1d<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; is_ok<span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> data <span class=\"sy0\">=<\/span> await fetch<span class=\"br0\">&#40;<\/span>session<span class=\"sy0\">,<\/span> people<span class=\"sy0\">,<\/span> page<span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">print<\/span><span class=\"br0\">&#40;<\/span><span class=\"kw3\">user<\/span><span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> is_ok: &nbsp;<span class=\"co1\">#\u5982\u679c\u7f51\u7edc\u8fd4\u56de\u6b63\u5e38\uff0cstatus==200<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> data<span class=\"br0\">&#91;<\/span><span class=\"nu0\">0<\/span><span class=\"br0\">&#93;<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">31<\/span> <span class=\"kw1\">and<\/span> data<span class=\"br0\">&#91;<\/span><span class=\"nu0\">1<\/span><span class=\"br0\">&#93;<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">139<\/span>: &nbsp;<span class=\"co1\"># \u8fd9\u513f\u662f\u4e2a\u5751\uff0c\u5224\u65ad\u662f\u4e0d\u662fgzip\u538b\u7f29\u8fc7\u7684\u5b57\u8282\u6d41\u3002\u539f\u56e0\u89c1\u4e0b\u6587\u89e3\u91ca<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">print<\/span><span class=\"br0\">&#40;<\/span><span class=\"st0\">'gzip data returned!'<\/span><span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; data <span class=\"sy0\">=<\/span> <span class=\"kw3\">zlib<\/span>.<span class=\"me1\">decompress<\/span><span class=\"br0\">&#40;<\/span>data<span class=\"sy0\">,<\/span> <span class=\"kw3\">zlib<\/span>.<span class=\"me1\">MAX_WBITS<\/span> | <span class=\"nu0\">16<\/span><span class=\"br0\">&#41;<\/span> &nbsp;<span class=\"co1\"># \u89e3gzip\u5b57\u8282\u6d41<\/span><br \/>\n<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; follower_list <span class=\"sy0\">=<\/span> <span class=\"br0\">&#91;<\/span><span class=\"br0\">&#93;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">for<\/span> follower <span class=\"kw1\">in<\/span> json.<span class=\"me1\">loads<\/span><span class=\"br0\">&#40;<\/span>data.<span class=\"me1\">decode<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span><span class=\"br0\">&#41;<\/span>: <span class=\"co1\"># \u5c06\u5b57\u8282\u6d41\u89e3\u7801\u4e3astr\uff0c\u5e76\u8f6c\u4e3ajson<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; follower_list.<span class=\"me1\">append<\/span><span class=\"br0\">&#40;<\/span>follower<span class=\"br0\">&#91;<\/span><span class=\"st0\">'login'<\/span><span class=\"br0\">&#93;<\/span><span class=\"br0\">&#41;<\/span><br \/>\n<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; await do_insert<span class=\"br0\">&#40;<\/span><span class=\"br0\">&#123;<\/span><span class=\"st0\">'user'<\/span>: <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> <span class=\"st0\">'follower'<\/span>: follower_list<span class=\"br0\">&#125;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u5f02\u6b65\u8c03\u7528\u63d2\u5165\u6570\u636e\u5e93<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> <span class=\"kw2\">len<\/span><span class=\"br0\">&#40;<\/span>follower_list<span class=\"br0\">&#41;<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">99<\/span>: <span class=\"co1\"># \u5982\u679c\u8fd4\u56de99\u4e2a\u7c89\u4e1d\uff0c\u9700\u8981page+1<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; page +<span class=\"sy0\">=<\/span> <span class=\"nu0\">1<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">else<\/span>: <span class=\"co1\"># \u5426\u5219\uff0c\u76f4\u63a5break,\u722c\u53d6\u4e0b\u4e00\u4e2a\u4eba<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">break<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">else<\/span>: <span class=\"co1\"># \u7f51\u7edc\u8c03\u7528\u5931\u8d25\uff0c\u76f4\u63a5break\uff0c\u722c\u53d6\u4e0b\u4e00\u4e2a\u4eba<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">break<\/span><\/div><\/div>\n<p>\u89e3\u91ca\u4e00\u4e0b\u4e0a\u9762\u4e3a\u4ec0\u4e48\u8981\u5224\u65ad\u5b57\u8282\u6d41\u662f\u5426\u662fgzip\u538b\u7f29\u8fc7\u7684\u3002Github API \u6709\u4e2a\u5751\uff0c\u5b83\u6709\u65f6\u4f1a\u5c06\u54cd\u5e94\u5185\u5bb9\u538b\u7f29\u4e3agzip\u8fd4\u56de\uff0c\u6211\u4eec\u7528\u6d4f\u89c8\u5668\u67e5\u770b\u65f6\u6ca1\u95ee\u9898\uff0c\u56e0\u4e3a\u6d4f\u89c8\u5668\u4f1a\u81ea\u52a8\u5224\u65ad\u662f\u5426\u662fgzip\u683c\u5f0f\u7684\u5b57\u8282\u6d41\uff0c\u5982\u679c\u662f\u5c06\u4f1a\u81ea\u52a8\u89e3\u538b\u3002\u800caiohttp\u8fd4\u56de\u7684response.read()\u662f\u539f\u59cb\u7684\u5b57\u8282\u6d41\uff0c\u4f60\u4e0d\u77e5\u9053\u5b83\u6709\u6ca1\u6709\u7ecf\u8fc7gzip\u538b\u7f29\u3002\u6309\u5e38\u7406\u6765\u8bf4\uff0c\u5982\u679c\u4f60\u5728\u4f60\u7684\u8bf7\u6c42\u5934\u4e2d\u4e0d\u8981\u8bbe\u7f6eAccept-Encoding\u5b57\u6bb5\uff0c\u670d\u52a1\u5668\u5e94\u8be5\u8ba4\u4e3a\u8be5\u5ba2\u6237\u7aef\u4e0d\u63a5\u53d7\u4efb\u4f55\u538b\u7f29\u8fc7\u7684\u5185\u5bb9\uff0c\u5e94\u8be5\u8fd4\u56de\u672a\u538b\u7f29\u7684\u5b57\u8282\u6d41\u3002\u4f46\u6211\u5f3a\u5236\u6307\u5b9a\u8bf7\u6c42\u5934\uff0c\u4e0d\u8bbe\u7f6eAccept-Encoding\u5b57\u6bb5\uff0cGithub API\u8fd8\u662f\u7384\u5e7b\u5730\u968f\u673a\u8fd4\u56degzip\u5b57\u8282\u6d41\u3002\u5e76\u4e14\u5b83\u7684response\u7684headers\u4e2d\u6c38\u8fdc\u663e\u793a\u5176Content-Encoding = gzip\uff0c\u8fd9\u513f\u5e94\u8be5\u662f\u4e2abug\u5427\u3002\u6240\u4ee5\u6211\u4e0d\u5f97\u4e0d\u81ea\u884c\u5224\u65ad\u662f\u5426\u662fgzip\u683c\u5f0f\u7684\uff0c\u5224\u65ad\u65b9\u6cd5\u5f88\u7b80\u5355\uff0c\u5229\u7528\u5b57\u8282\u6d41\u7684\u524d\u4e24\u4e2a\u5b57\u8282\uff1a<br \/>\n\u524d\u4e24\u4e2a\u5b57\u8282\u7528\u4e8e\u6807\u8bc6gzip\u6587\u4ef6\uff0c\u5176\u4e2d\u7b2c\u4e00\u4e2a\u5b57\u8282ID1 = 31\uff080x1f\uff0c\\037\uff09\uff0c\u7b2c\u4e8c\u4e2a\u5b57\u8282ID2 = 139\uff080x8b\uff0c\\213\uff09\uff0c\u5982\u679c\u5224\u65ad\u8be5\u5b57\u8282\u6d41\u4ee5\u8fd9\u4e24\u4e2a\u5b57\u8282\u5f00\u5934\uff0c\u90a3\u4e48\u53ef\u4ee5\u521d\u6b65\u8ba4\u4e3a\u8fd9\u662fgzip\u5b57\u8282\u6d41\u3002<\/p>\n<p>\u6211\u4eec\u8fd8\u9700\u8981\u5f00\u542f\u4e8b\u4ef6\u5faa\u73af\uff0c\u624d\u80fd\u8fbe\u5230\u5f02\u6b65IO\u7684\u6548\u679c\uff0c\u5b8c\u6574\u7a0b\u5e8f\u89c1\u4e0b\u6587\uff1a<\/p>\n<div class=\"codecolorer-container python railscasts\" style=\"overflow:auto;white-space:nowrap;width:100%;height:100%;\"><div class=\"python codecolorer\"><span class=\"st0\">'''<br \/>\nAuthor: ayonel<br \/>\nDate:<br \/>\nBlog: https:\/\/ayonel.malash.net<br \/>\nGitHub: https:\/\/github.com\/ayonel<br \/>\nE-mail: ayonel@qq.com<br \/>\n\u63d0\u53d6\u51fa\u6240\u6709pull\u4e2d\u7684\u4eba\u5458\uff0c\u722c\u53d6\u5176\u5173\u6ce8\u5173\u7cfb\u3002<br \/>\n'''<\/span><br \/>\n<span class=\"kw1\">import<\/span> <span class=\"kw3\">itertools<\/span><br \/>\n<span class=\"kw1\">import<\/span> json<br \/>\n<span class=\"kw1\">import<\/span> aiohttp<br \/>\n<span class=\"kw1\">import<\/span> asyncio<br \/>\n<span class=\"kw1\">import<\/span> <span class=\"kw3\">time<\/span><br \/>\n<span class=\"kw1\">from<\/span> motor.<span class=\"me1\">motor_asyncio<\/span> <span class=\"kw1\">import<\/span> AsyncIOMotorClient<br \/>\n<span class=\"kw1\">import<\/span> <span class=\"kw3\">zlib<\/span><br \/>\n<span class=\"kw1\">import<\/span> async_timeout<br \/>\n<br \/>\nasync_client <span class=\"sy0\">=<\/span> AsyncIOMotorClient<span class=\"br0\">&#40;<\/span><span class=\"st0\">'localhost'<\/span><span class=\"sy0\">,<\/span> <span class=\"st0\">'27017'<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u5efa\u7acbmotor\u7684client<\/span><br \/>\ndb <span class=\"sy0\">=<\/span> async_client<span class=\"br0\">&#91;<\/span><span class=\"st0\">'follow'<\/span><span class=\"br0\">&#93;<\/span> <span class=\"co1\"># \u6307\u5b9a\u8981\u63d2\u5165\u7684\u6570\u636e\u5e93<\/span><br \/>\ncollection <span class=\"sy0\">=<\/span> db<span class=\"br0\">&#91;<\/span><span class=\"st0\">'asyncfollow'<\/span><span class=\"br0\">&#93;<\/span> <span class=\"co1\"># \u6307\u5b9a\u8981\u63d2\u5165\u7684collection<\/span><br \/>\n<br \/>\n<span class=\"co1\">#\u5f02\u6b65\u63d2\u5165\u51fd\u6570<\/span><br \/>\n<br \/>\nasync <span class=\"kw1\">def<\/span> do_insert<span class=\"br0\">&#40;<\/span>arg<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; await collection.<span class=\"me1\">insert_one<\/span><span class=\"br0\">&#40;<\/span>arg<span class=\"br0\">&#41;<\/span><br \/>\n<br \/>\n<span class=\"co1\">#\u5f02\u6b65\u722c\u53d6\u51fd\u6570<\/span><br \/>\n<br \/>\nasync <span class=\"kw1\">def<\/span> fetch<span class=\"br0\">&#40;<\/span>session<span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> page<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; url <span class=\"sy0\">=<\/span> <span class=\"st0\">'https:\/\/api.github.com\/users\/'<\/span> + <span class=\"kw3\">user<\/span> + <span class=\"st0\">'\/follower?per_page=99&amp;amp;page='<\/span> + <span class=\"kw2\">str<\/span><span class=\"br0\">&#40;<\/span>page<span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">with<\/span> async_timeout.<span class=\"me1\">timeout<\/span><span class=\"br0\">&#40;<\/span><span class=\"nu0\">20<\/span><span class=\"br0\">&#41;<\/span>: &nbsp;<span class=\"co1\"># \u9ed8\u8ba4\u8d85\u65f6\u65f6\u95f420s<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; async <span class=\"kw1\">with<\/span> session.<span class=\"me1\">get<\/span><span class=\"br0\">&#40;<\/span>url<span class=\"sy0\">,<\/span> headers<span class=\"sy0\">=<\/span><span class=\"br0\">&#123;<\/span><span class=\"br0\">&#125;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"kw1\">as<\/span> response:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> response.<span class=\"me1\">status<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">200<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">return<\/span> <span class=\"kw2\">True<\/span><span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> await response.<span class=\"me1\">read<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> &nbsp;<span class=\"co1\"># True\u4ee3\u8868\u722c\u53d6\u6210\u529f<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">else<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">return<\/span> <span class=\"kw2\">False<\/span><span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> await response.<span class=\"me1\">read<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> &nbsp; <span class=\"co1\"># False\u4ee3\u8868\u722c\u53d6\u5931\u8d25<\/span><br \/>\n<br \/>\n<span class=\"co1\">#\u4e3b\u51fd\u6570<\/span><br \/>\n<br \/>\nasync <span class=\"kw1\">def<\/span> main<span class=\"br0\">&#40;<\/span>loop<span class=\"sy0\">,<\/span> peopleSet<span class=\"br0\">&#41;<\/span>:<br \/>\n&nbsp; &nbsp; async <span class=\"kw1\">with<\/span> aiohttp.<span class=\"me1\">ClientSession<\/span><span class=\"br0\">&#40;<\/span>loop<span class=\"sy0\">=<\/span>loop<span class=\"br0\">&#41;<\/span> <span class=\"kw1\">as<\/span> session:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">for<\/span> people <span class=\"kw1\">in<\/span> peopleSet:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; page <span class=\"sy0\">=<\/span> <span class=\"nu0\">1<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">while<\/span> <span class=\"kw2\">True<\/span>: &nbsp;<span class=\"co1\"># \u56e0\u4e3a\u6709\u4e9b\u4eba\u4e0d\u6b62\u670999\u4e2a\u7c89\u4e1d\uff0c\u6240\u4ee5\u9047\u5230\u4e00\u9875\u8fd4\u56de99\u4e2a\u7c89\u4e1d\u7684\uff0c\u4e0d\u80fd\u76f4\u63a5\u4e0b\u4e00\u4e2a\u4eba\uff0c\u8fd8\u9700\u8981\u5c06page+1\uff0c\u53bb\u722c\u53d6\u8be5\u4eba\u7684\u5176\u4ed6\u7c89\u4e1d<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; is_ok<span class=\"sy0\">,<\/span> <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> data <span class=\"sy0\">=<\/span> await fetch<span class=\"br0\">&#40;<\/span>session<span class=\"sy0\">,<\/span> people<span class=\"sy0\">,<\/span> page<span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">print<\/span><span class=\"br0\">&#40;<\/span><span class=\"kw3\">user<\/span><span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> is_ok: &nbsp;<span class=\"co1\">#\u5982\u679c\u7f51\u7edc\u8fd4\u56de\u6b63\u5e38\uff0cstatus==200<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> data<span class=\"br0\">&#91;<\/span><span class=\"nu0\">0<\/span><span class=\"br0\">&#93;<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">31<\/span> <span class=\"kw1\">and<\/span> data<span class=\"br0\">&#91;<\/span><span class=\"nu0\">1<\/span><span class=\"br0\">&#93;<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">139<\/span>: &nbsp;<span class=\"co1\"># \u8fd9\u513f\u662f\u4e2a\u5751\uff0c\u5224\u65ad\u662f\u4e0d\u662fgzip\u538b\u7f29\u8fc7\u7684\u5b57\u8282\u6d41\u3002\u539f\u56e0\u89c1\u4e0b\u6587\u89e3\u91ca<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">print<\/span><span class=\"br0\">&#40;<\/span><span class=\"st0\">'gzip data returned!'<\/span><span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; data <span class=\"sy0\">=<\/span> <span class=\"kw3\">zlib<\/span>.<span class=\"me1\">decompress<\/span><span class=\"br0\">&#40;<\/span>data<span class=\"sy0\">,<\/span> <span class=\"kw3\">zlib<\/span>.<span class=\"me1\">MAX_WBITS<\/span> | <span class=\"nu0\">16<\/span><span class=\"br0\">&#41;<\/span> &nbsp;<span class=\"co1\"># \u89e3gzip\u5b57\u8282\u6d41<\/span><br \/>\n<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; follower_list <span class=\"sy0\">=<\/span> <span class=\"br0\">&#91;<\/span><span class=\"br0\">&#93;<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">for<\/span> follower <span class=\"kw1\">in<\/span> json.<span class=\"me1\">loads<\/span><span class=\"br0\">&#40;<\/span>data.<span class=\"me1\">decode<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span><span class=\"br0\">&#41;<\/span>: <span class=\"co1\"># \u5c06\u5b57\u8282\u6d41\u89e3\u7801\u4e3astr\uff0c\u5e76\u8f6c\u4e3ajson<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; follower_list.<span class=\"me1\">append<\/span><span class=\"br0\">&#40;<\/span>follower<span class=\"br0\">&#91;<\/span><span class=\"st0\">'login'<\/span><span class=\"br0\">&#93;<\/span><span class=\"br0\">&#41;<\/span><br \/>\n<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; await do_insert<span class=\"br0\">&#40;<\/span><span class=\"br0\">&#123;<\/span><span class=\"st0\">'user'<\/span>: <span class=\"kw3\">user<\/span><span class=\"sy0\">,<\/span> <span class=\"st0\">'follower'<\/span>: follower_list<span class=\"br0\">&#125;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u5f02\u6b65\u8c03\u7528\u63d2\u5165\u6570\u636e\u5e93<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">if<\/span> <span class=\"kw2\">len<\/span><span class=\"br0\">&#40;<\/span>follower_list<span class=\"br0\">&#41;<\/span> <span class=\"sy0\">==<\/span> <span class=\"nu0\">99<\/span>: <span class=\"co1\"># \u5982\u679c\u8fd4\u56de99\u4e2a\u7c89\u4e1d\uff0c\u9700\u8981page+1<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; page +<span class=\"sy0\">=<\/span> <span class=\"nu0\">1<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">else<\/span>: <span class=\"co1\"># \u5426\u5219\uff0c\u76f4\u63a5break,\u722c\u53d6\u4e0b\u4e00\u4e2a\u4eba<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">break<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">else<\/span>: <span class=\"co1\"># \u7f51\u7edc\u8c03\u7528\u5931\u8d25\uff0c\u76f4\u63a5break\uff0c\u722c\u53d6\u4e0b\u4e00\u4e2a\u4eba<\/span><br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">break<\/span><br \/>\n<br \/>\n<br \/>\n<span class=\"kw1\">if<\/span> name <span class=\"sy0\">==<\/span> <span class=\"st0\">'main'<\/span>: <span class=\"co1\"># \u7a0b\u5e8f\u5165\u53e3<\/span><br \/>\n&nbsp; &nbsp; start <span class=\"sy0\">=<\/span> <span class=\"kw3\">time<\/span>.<span class=\"kw3\">time<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u6807\u8bb0\u5f00\u59cb\u65f6\u95f4<\/span><br \/>\n&nbsp; &nbsp; peopleSet <span class=\"sy0\">=<\/span> <span class=\"kw2\">set<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u521d\u59cb\u5316\u9700\u8981\u722c\u53d6\u7684\u7528\u6237\u96c6<\/span><br \/>\n&nbsp; &nbsp; peopleSet.<span class=\"me1\">add<\/span><span class=\"br0\">&#40;<\/span><span class=\"st0\">'ayonel'<\/span><span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; peopleSet.<span class=\"me1\">add<\/span><span class=\"br0\">&#40;<\/span><span class=\"st0\">'malash'<\/span><span class=\"br0\">&#41;<\/span><br \/>\n&nbsp; &nbsp; <span class=\"co1\"># \u4e0a\u9762\u6211\u53ea\u6dfb\u52a0\u4e862\u4e2a\u4eba\uff0c\u5b9e\u9645\u6211\u7684peopleSet\u4e2d\u67092\u4e07\u591a\u4eba<\/span><br \/>\n&nbsp; &nbsp; loop <span class=\"sy0\">=<\/span> asyncio.<span class=\"me1\">get_event_loop<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u5f00\u542f\u4e8b\u4ef6\u5faa\u73af<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">try<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; loop.<span class=\"me1\">run_until_complete<\/span><span class=\"br0\">&#40;<\/span>main<span class=\"br0\">&#40;<\/span>loop<span class=\"sy0\">,<\/span> peopleSet<span class=\"br0\">&#41;<\/span><span class=\"br0\">&#41;<\/span> <span class=\"co1\"># \u5f00\u59cb\u6267\u884cmain<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">except<\/span> <span class=\"kw2\">Exception<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">pass<\/span><br \/>\n&nbsp; &nbsp; <span class=\"kw1\">finally<\/span>:<br \/>\n&nbsp; &nbsp; &nbsp; &nbsp; <span class=\"kw1\">print<\/span><span class=\"br0\">&#40;<\/span><span class=\"st0\">'\u603b\u8017\u65f6\uff1a'<\/span> + <span class=\"kw2\">str<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#40;<\/span><span class=\"kw3\">time<\/span>.<span class=\"kw3\">time<\/span><span class=\"br0\">&#40;<\/span><span class=\"br0\">&#41;<\/span>-start<span class=\"br0\">&#41;<\/span>\/<span class=\"nu0\">60<\/span><span class=\"br0\">&#41;<\/span><span class=\"br0\">&#41;<\/span><\/div><\/div>\n<p>\u6211\u53e6\u5916\u8fd8\u662f\u5b9e\u73b0\u4e86\u540c\u6b65\u7684urllib.request\u4f5c\u4e3a\u5bf9\u6bd4\u6d4b\u8bd5\uff0c\u5b9e\u9a8c\u663e\u793a\uff0c\u5728\u6211\u7684\u5f02\u6b65\u722c\u866b\u722c\u53d6\u4e869000+\u4eba\u7684\u65f6\u95f4\u91cc\uff0c\u540c\u6b65\u722c\u866b\u722c\u53d6\u4e86300\u4eba\u4e0d\u5230\u3002\u6027\u80fd\u5dee\u8ddd\u662f\u5de8\u5927\u6ef4&#8230;<\/p>\n<p>\u4e0a\u9762\u5b8c\u6574\u4ee3\u7801\u7ed9\u51fa\u7684\u722c\u866b\u8fd8\u80fd\u4e0d\u80fd\u63d0\u9ad8\u901f\u5ea6\u5462\uff1f\u7b54\u6848\u662f\u53ef\u4ee5\u7684\uff01\u4e0a\u8ff0\u4ee3\u7801\u4e2d\u5176\u5b9e\u628a\u6574\u4e2a\u722c\u53d6\u4efb\u52a1\u5c01\u88c5\u6210\u4e86\u4e00\u4e2a\u5927\u534f\u7a0b\uff0c\u8fd9\u4e2a\u5927\u534f\u7a0b\u7531\u8bb8\u591a\u4e2a\u7f51\u7edc\u8c03\u7528\u5c0f\u534f\u7a0b\u4ee5\u53ca\u6570\u636e\u5e93\u63d2\u5165\u5c0f\u534f\u7a0b\u6784\u6210\u3002\u540c\u65f6\u6211\u4eec\u7684\u6240\u6709aiohttp\u7684\u8bf7\u6c42\u590d\u7528\u4e86\u540c\u4e00\u4e2aaiohttp.ClientSession(),\u8fd9\u6837\u505a\u7684\u597d\u5904\u662f\u6211\u4eec\u7684\u7a0b\u5e8f\u8fd0\u884c\u671f\u95f4\u53ea\u6709\u4e00\u4e2aClientSession\u5bf9\u8c61\uff0c\u5341\u5206\u8282\u7ea6\u5185\u5b58\u8d44\u6e90\uff0c\u5982\u679c\u6211\u4eec\u5bf9\u6bcf\u4e2a\u8bf7\u6c42\u65b0\u5f00\u4e00\u4e2aClientSession\u7684\u8bdd\uff0c\u8bf7\u6c42\u4e00\u591a\uff0c\u5185\u5b58\u76f4\u63a5\u5c31\u7206\u6389\u4e86\u3002\u6211\u5b9e\u9645\u4e86\u6d4b\u8bd520000\u4e2a\u8bf7\u6c42\uff0c\u5f88\u5feb\u5185\u5b58\u5c31\u4f1a\u5403\u523010G\uff0c\u6240\u4ee5\u8bf4\u5bf9\u4e8eClientSession\u6211\u4eec\u9700\u8981\u590d\u7528\uff0c\u90a3\u662f\u4e0d\u662f\u6240\u6709\u8bf7\u6c42\u90fd\u590d\u7528\u4e00\u4e2a\u5462\uff0c\u5c31\u50cf\u4e0a\u9762\u5b8c\u6574\u4ee3\u7801\u4e2d\u4e00\u6837\u3002\u5f53\u7136\u4e0d\u662f\uff0c\u6211\u4eec\u53ef\u4ee5\u81ea\u5df1\u7ec4\u7ec7\uff0c\u6bd4\u5982500\u4e2a\u8bf7\u6c42\u590d\u7528\u4e00\u4e2aClientSession\u5bf9\u8c61\uff0c\u6216\u8005200\u4e2a\u8bf7\u6c42\u590d\u7528\u4e00\u4e2aClientSession\u5bf9\u8c61\uff0c\u5728\u5b9e\u9645\u6d4b\u8bd5\u4e2d\uff0c\u722c\u53d6\u6548\u7387\u4f1a\u8fc5\u901f\u63d0\u5347\uff0c\u8fdc\u8fdc\u9ad8\u4e8e\u6240\u6709\u8bf7\u6c42\u590d\u7528\u540c\u4e00\u4e2aClientSession\u5bf9\u8c61\u7684\u60c5\u51b5\u3002<\/p>\n<p>aiohttp\u4e2d\u8fd8\u6709connector\uff08\u8fde\u63a5\u6c60\uff09\uff0c\u76f8\u4fe1\u5229\u7528connector\u80af\u5b9a\u8fd8\u80fd\u66f4\u8fdb\u4e00\u6b65\u63d0\u9ad8\u722c\u53d6\u6548\u7387\u3002<\/p>\n<p>\u6700\u540e\u603b\u7ed3\uff0c\u534f\u7a0b+\u5f02\u6b65IO\u662f\u63d0\u9ad8\u5e76\u53d1\u7684\u5927\u6740\u5668\uff0cpython\u4e00\u76f4\u88ab\u8bdf\u75c5\u7684\u6027\u80fd\u95ee\u9898\uff0c\u53ef\u4ee5\u4ece\u8fd9\u513f\u627e\u56de\u70b9\u81ea\u4fe1\uff0c\u4f46\u662f\u7f3a\u70b9\u4e5f\u6bd4\u8f83\u660e\u663e\uff0c\u53ea\u9002\u5408\u4e8eIO\u5bc6\u96c6\u578b\u7684\u5de5\u4f5c\uff0c\u53e6\u5916\u5f02\u6b65\u4ee3\u7801\u786e\u5b9e\u4e0d\u5982\u540c\u6b65\u4ee3\u7801\u597d\u7406\u89e3\uff0c\u867d\u71363.5\u5df2\u7ecf\u5b9e\u73b0\u4e86async await\u5173\u952e\u5b57\uff0c\u4f46\u8fd8\u662f\u9700\u8981\u591acoding\u624d\u80fd\u52a0\u6df1\u7406\u89e3\u3002 \u542c\u8bf4tornado\u662f\u4e2a\u4e0d\u9519\u7684\u4e1c\u4e1c\uff0c\u6709\u65f6\u95f4\u53ef\u4ee5\u770b\u770b\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u534f\u7a0b\uff0c\u53c8\u79f0\u5fae\u7ebf\u7a0b\uff0c\u7ea4\u7a0b\u3002\u82f1\u6587\u540dCoroutine \u6211\u4eec\u53ef\u4ee5\u5c06\u534f\u7a0b\u7406\u89e3\u4e3a\u4e00\u4e2a\u5b50\u7a0b\u5e8f\/\u51fd\u6570\u7684\u7279\u4f8b\u3002\u4e0e\u5b50\u7a0b\u5e8f\/\u51fd\u6570\u4e0d [&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],"tags":[],"class_list":["post-290","post","type-post","status-publish","format-standard","hentry","category-python"],"_links":{"self":[{"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/posts\/290","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/comments?post=290"}],"version-history":[{"count":18,"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/posts\/290\/revisions"}],"predecessor-version":[{"id":319,"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/posts\/290\/revisions\/319"}],"wp:attachment":[{"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/media?parent=290"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/categories?post=290"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ayonel.malash.net\/index.php\/wp-json\/wp\/v2\/tags?post=290"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}