{"id":5038,"date":"2019-05-07T13:53:59","date_gmt":"2020-04-22T06:37:52","guid":{"rendered":"https:\/\/vip.fxxkpython.com\/?p=5038"},"modified":"2021-08-31T03:25:00","modified_gmt":"2021-08-30T19:25:00","slug":"3e9ab96b3f","status":"publish","type":"post","link":"https:\/\/vip.fxxkpython.com\/?p=5038","title":{"rendered":"python\u722c\u866b29 | \u4f7f\u7528scrapy\u722c\u53d6\u7cd7\u4e8b\u767e\u79d1\u7684\u4f8b\u5b50\uff0c\u544a\u8bc9\u4f60\u5b83\u6709\u591a\u5389\u5bb3\uff01"},"content":{"rendered":"
\n

\u662f\u65f6\u5019\u7ed9\u4f60\u8bf4\u8bf4<\/p>\n

\n

\u722c\u866b\u6846\u67b6\u4e86<\/span><\/p>\n

\n

\u4f7f\u7528\u6846\u67b6\u6765\u722c\u53d6\u6570\u636e<\/p>\n

\n

\u4f1a\u8282\u7701\u6211\u4eec\u66f4\u591a\u65f6\u95f4<\/p>\n

\n

\u5f88\u5feb\u5c31\u80fd\u6293\u53d6\u5230\u6211\u4eec\u60f3\u8981\u6293\u53d6\u7684\u5185\u5bb9<\/p>\n

\n

\u6846\u67b6\u96c6\u5408\u4e86\u8bb8\u591a\u64cd\u4f5c<\/p>\n

\n

\u6bd4\u5982\u8bf7\u6c42\uff0c\u6570\u636e\u89e3\u6790\uff0c\u5b58\u50a8\u7b49\u7b49<\/p>\n

\n

\u90fd\u53ef\u4ee5\u7531\u6846\u67b6\u5b8c\u6210<\/p>\n

\n

\"python\u722c\u866b29<\/p>\n

\n

\u6709\u4e9b\u5c0f\u4f19\u4f34\u5c31\u8981\u95ee\u4e86<\/p>\n

\n

\u4f60\u4ed6\u5988\u7684<\/p>\n

\n

\u4e3a\u4ec0\u4e48\u4e0d\u65e9\u70b9\u8bf4\u5462\uff1f<\/p>\n

\n

\"python\u722c\u866b29<\/p>\n

\n

\u662f\u8fd9\u6837\u7684<\/p>\n

\n

\u5f53\u4f60\u4e0d\u77e5\u9053 1+1 \u662f\u4ec0\u4e48\u7684\u65f6\u5019<\/p>\n

\n

\u4f60\u53bb\u4f7f\u7528\u8ba1\u7b97\u5668\u6765\u8ba1\u7b97<\/p>\n

\n

\u4e5f\u662f\u6ca1\u7528\u7684<\/p>\n

\n

\u5bf9\u5427<\/p>\n

\n

\u6240\u4ee5\u6846\u67b6\u7684\u4f7f\u7528<\/p>\n

\n

\u5728\u73b0\u5728\u8fd9\u4e2a\u65f6\u5019\uff08\u722c\u866b28\u7bc7\u4e4b\u540e\uff09\u8bb2<\/p>\n

\n

\u5c31\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u65f6\u673a<\/p>\n

\n

\"python\u722c\u866b29<\/p>\n

\n

\u4eca\u5929<\/p>\n

\n

\u5c0f\u5e05b\u5c31\u8ddf\u4f60\u8bf4\u8bf4<\/p>\n

\n

scrapy\u8fd9\u4e2a\u6846\u67b6<\/p>\n

\n

\u5230\u5e95\u6709\u591a\u725bb<\/p>\n

\n

\u90a3\u4e48<\/p>\n

\u63a5\u4e0b\u6765\u5c31\u662f<\/p>\n

\n

\u5b66\u4e60 python \u7684\u6b63\u786e\u59ff\u52bf<\/span><\/p>\n

\n

\"python\u722c\u866b29<\/p>\n

\n

\u8981\u4f7f\u7528 scrapy<\/p>\n

\n

\u9996\u5148\u5f53\u7136\u4f60\u5f97\u9700\u8981\u6709\u554a<\/p>\n

\n

\u4f60\u53ef\u4ee5\u4f7f\u7528\u00a0conda \u5b89\u88c5<\/p>\n

\n

\n
conda<\/span> install -c conda-forge scrapy<\/span><\/code><\/pre>\n<\/section>\n
\n
\u4f60\u4e5f\u53ef\u4ee5\u4f7f\u7528 PyPI \u5b89\u88c5<\/span><\/p>\n
\n
\n
pip<\/span> install Scrapy<\/span><\/code><\/pre>\n<\/section>\n
\n
\n
scrapy\u4f9d\u8d56\u4e00\u4e9b\u76f8\u5173\u7684\u5e93<\/span><\/p>\n
\u00a0<\/span><\/p>\n
\n
lxml\n<\/span><\/code>parsel\n<\/span><\/code>w3lib\n<\/span><\/code>twisted\n<\/span><\/code>cryptography\u00a0and\u00a0pyOpenSSL<\/span><\/code><\/pre>\n<\/section>\n
\n
\n
\u5982\u679c\u4f60\u5728\u4f7f\u7528 scrapy \u7684\u65f6\u5019\u53d1\u73b0\u76f8\u5173\u5e93\u7f3a\u5931<\/p>\n
\n
\u628a\u88e4\u5b50\u7a7f\u4e0a\u5c31\u662f\u4e86<\/p>\n
\n
\u54e6\u4e0d\u662f<\/p>\n
\n
\u628a\u4f60\u7f3a\u5931\u7684\u5e93\u5b89\u88c5\u4e0a\u5c31\u5b8c\u4e8b\u4e86<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u597d\u4e86<\/p>\n
\n
\u73b0\u5728\u5047\u8bbe\u4f60\u5df2\u7ecf\u5b89\u88c5\u597d\u4e86 scrapy \u8fd9\u4e2a\u6846\u67b6<\/p>\n
\n
\u90a3\u4e48\u63a5\u4e0b\u6765<\/p>\n
\n
\u5c0f\u5e05b\u4f1a\u5e26\u4f60\u4f7f\u7528\u5b83\u6765\u722c\u53d6\u4e00\u4e0b \u7cd7\u4e8b\u767e\u79d1<\/span> \u7684\u6bb5\u5b50<\/p>\n
\n
\u4e3b\u8981\u8ba9\u4f60\u77e5\u9053 scrapy \u7684\u4f7f\u7528\u4ee5\u53ca\u4f53\u9a8c\u5b83\u7684\u725b\u903c\u4e4b\u5904<\/p>\n
\n
\u5e9f\u8bdd\u4e0d\u591a\u8bf4<\/p>\n
\n
\u5728\u4f60\u60f3\u8981\u5b58\u653e\u7684\u722c\u866b\u6587\u4ef6\u76ee\u5f55\u4e0b<\/p>\n
\n
\u4f7f\u7528\u547d\u4ee4\u6765\u521b\u5efa\u4e00\u4e2a scrapy \u722c\u866b\u9879\u76ee<\/p>\n
\n
\u6bd4\u5982\u5728\u8fd9\u91cc<\/p>\n
\n
\u6211\u4eec\u8981\u521b\u5efa\u4e00\u4e2a qiushibaike \u7684\u722c\u866b\u9879\u76ee<\/p>\n
\n
\u5c31\u53ef\u4ee5\u8fd9\u6837<\/p>\n
\n
\n
\u00a0scrapy<\/span>\u00a0startproject\u00a0qiushibaike<\/span><\/code><\/pre>\n<\/section>\n
\n
\u8fd9\u65f6\u5019\u4f60\u5c31\u4f1a\u53d1\u73b0<\/p>\n
\n
scrapy\u5e2e\u4f60\u81ea\u52a8\u751f\u6210\u4e86\u9879\u76ee\u6587\u4ef6<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\n
\u5728\u8fd9\u91cc\u9762\u6709\u4e00\u4e9b\u914d\u7f6e\u6587\u4ef6\u548c\u9884\u5b9a\u4e49\u7684\u8bbe\u7f6e\u6587\u4ef6<\/p>\n
\n
\u800c\u6211\u4eec\u7684\u722c\u866b\u4ee3\u7801<\/p>\n
\n
\u53ef\u4ee5\u5728 spiders \u76ee\u5f55\u4e0b\u521b\u5efa<\/p>\n
\n
\u5728\u8fd9\u91cc\u6211\u4eec\u5c31\u521b\u5efa\u4e00\u4e2a qiushibaike_spider \u5427<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u8981\u4f7f\u7528 scrapy \u722c\u866b<\/p>\n
\n
\u6211\u4eec\u5c31\u9700\u8981\u7ee7\u627f\u00a0\u00a0scrapy.Spider \u8fd9\u4e2a\u7c7b<\/span><\/p>\n
\u00a0<\/span><\/p>\n
\u8fd9\u6837\u6211\u4eec\u624d\u80fd\u4f7f\u7528\u5b83\u5b9a\u4e49\u7684\u4e00\u4e9b\u65b9\u6cd5<\/span><\/p>\n
\n
\n
class<\/span> QiushiSpider<\/span>(scrapy.Spider)<\/span>:<\/span><\/span><\/code><\/pre>\n<\/section>\n
\n
\n
\u63a5\u7740\u6211\u4eec\u8981\u5b9a\u4e49\u4e00\u4e2a\u722c\u866b\u7684\u540d\u79f0<\/p>\n
\n
\u8fd9\u91cc\u5b9a\u4e49\u4e00\u4e2a\u552f\u4e00\u7684\u540d\u79f0<\/p>\n
\u7528\u6765\u6807\u8bc6\u7cd7\u4e8b\u7684\u722c\u866b<\/p>\n
\u5728\u9879\u76ee\u4e2d\u4e0d\u80fd\u548c\u522b\u7684\u722c\u866b\u540d\u79f0\u4e00\u6837<\/p>\n
\u7b49\u4f1a\u4f1a\u7528\u5230\u8fd9\u4e2a\u540d\u79f0<\/p>\n
\n
\n
\u00a0\u00a0name<\/span>\u00a0=\u00a0\"qiushibaike\"<\/span><\/span><\/code><\/pre>\n<\/section>\n
\n
\u63a5\u7740\u6211\u4eec\u5c31\u53ef\u4ee5\u6765\u5b9a\u4e49\u6211\u4eec\u7684\u8bf7\u6c42\u4e86<\/p>\n
\n
\u6bd4\u5982\u6211\u4eec\u8981\u722c\u7cd7\u4e8b\u767e\u79d1\u7684\u6bb5\u5b50\u7684\u7b2c\u4e00\u548c\u7b2c\u4e8c\u9875<\/p>\n
\n
\u6240\u4ee5\u6211\u4eec\u53ef\u4ee5\u8fd9\u6837\u5b9a\u4e49\u8bf7\u6c42\u94fe\u63a5<\/p>\n
\n
\n
    def<\/span> start_requests<\/span>(self<\/span>)<\/span><\/span>:\n<\/span><\/code>        urls = [\n<\/span><\/code>\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0'https:\/\/www.qiushibaike.com\/text\/page\/1\/'<\/span>,\n<\/span><\/code>            'https:\/\/www.qiushibaike.com\/text\/page\/2\/'<\/span>,\n<\/span><\/code>        ]\n<\/span><\/code>        for<\/span> url in<\/span> urls:\n<\/span><\/span><\/code>            yield<\/span> scrapy.Request(url=url, callback=self<\/span>.parse)<\/span><\/code><\/pre>\n<\/section>\n
\n
\u6211\u4eec\u5728\u8fd9\u4e2a\u65b9\u6cd5 start_requests \u9700\u8981\u8fd4\u56de\u4e00\u4e2a yield \u751f\u6210\u7684\u8fed\u4ee3<\/p>\n
\n
\u800c\u5176\u4e2d\u7684\u53c2\u6570\u00a0callba<\/span>ck=<\/span>self<\/span>.parse <\/span>\u5c31\u662f\u8981\u8ba9\u5b83\u53bb\u56de\u8c03\u6211\u4eec\u7684\u6570\u636e\u89e3\u6790\u65b9\u6cd5<\/p>\n
\n
\u56de\u8c03\u65b9\u6cd5\u662f\u8fd9\u6837\u7684<\/p>\n
\n
\n
    def<\/span> parse<\/span>(self, response)<\/span>:\n<\/span><\/span><\/code>        page = response.url.split(\"\/\"<\/span>)[-2<\/span>]\n<\/span><\/code>        filename = 'qiushi-%s.html'<\/span> % page\n<\/span><\/code>        with<\/span> open(filename, 'wb'<\/span>) as<\/span> f:\n<\/span><\/code>            f.write(response.body)\n<\/span><\/code>        self.log('Saved file %s'<\/span> % filename)<\/span><\/code><\/pre>\n<\/section>\n
\n
\u4e3b\u8981\u662f\u628a\u6211\u4eec\u6293\u53d6\u4e0b\u6765\u7684 html \u5b58\u5165\u5230\u672c\u5730\u6587\u4ef6<\/p>\n
\n
\u6211\u4eec\u6765\u4f7f\u7528 scrapy \u8fd0\u884c\u4e00\u4e0b\u8fd9\u4e2a\u722c\u866b<\/p>\n
\n
\u4f7f\u7528\u5982\u4e0b\u547d\u4ee4\u5373\u53ef<\/p>\n
\n
\n
 cd<\/span> qiushibaike\/\n<\/span><\/code>scrapy crawl qiushibaike<\/span><\/code><\/pre>\n<\/section>\n
\n
scrapy crawl qiushibaike <\/span>\u4e2d\u7684 qiushibaike \u5c31\u662f\u6211\u4eec\u521a\u521a\u5b9a\u4e49\u7684\u540d\u79f0<\/p>\n
\n
\u4e0d\u8fc7\u8fd9\u4e2a\u65f6\u5019\u8fd0\u884c\u540e\u4f60\u4f1a\u53d1\u73b0\u62a5\u9519\u4e86<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u8fd9\u662f\u56e0\u4e3a\u4f60\u61c2\u5f97<\/p>\n
\n
\u7cd7\u4e8b\u505a\u4e86\u53cd\u722c<\/p>\n
\n
\u6211\u4eec\u5b9a\u4e49\u4e00\u4e2a header \u5427<\/p>\n
\n
\n
 haders = {\n<\/span><\/code>        'User-Agent'<\/span>: 'Mozilla\/5.0 (X11; Linux x86_64) AppleWebKit\/537.36 (KHTML, like Gecko) Ubuntu Chromium\/73.0.3683.86 Chrome\/73.0.3683.86 Safari\/537.36'\n<\/span><\/span><\/code>    }\n<\/span><\/code>\n<\/span><\/code>    def<\/span> start_requests<\/span>(self<\/span>)<\/span><\/span>:\n<\/span><\/code>        urls = [\n<\/span><\/code>            'https:\/\/www.qiushibaike.com\/text\/page\/12\/'<\/span>,\n<\/span><\/code>            'https:\/\/www.qiushibaike.com\/text\/page\/2\/'<\/span>,\n<\/span><\/code>        ]\n<\/span><\/code>        for<\/span> url in<\/span> urls:\n<\/span><\/span><\/code>            yield<\/span> scrapy.Request(url=url, callback=self<\/span>.parse, headers=self<\/span>.haders)<\/span><\/code><\/pre>\n<\/section>\n
\n
\u518d\u6b21\u8fd0\u884c\u547d\u4ee4<\/p>\n
\n
scrapy crawl qiushibaike<\/span><\/p>\n
\u00a0<\/span><\/p>\n
\u8fd9\u6b21\u53ef\u4ee5\u53d1\u73b0<\/p>\n
\n
\u6e90\u4ee3\u7801\u88ab\u6211\u4eec\u722c\u53d6\u4e0b\u6765\u4e86<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u662f\u4e0d\u662f\u5f88\u65b9\u4fbf\u54a7<\/p>\n
\n
\u63a5\u4e0b\u6765\u6211\u4eec\u518d\u6765\u89e3\u6790\u5173\u952e\u6570\u636e<\/p>\n
\n
\u6bd4\u5982\u6211\u4eec\u53ea\u9700\u8981\u6bb5\u5b50\u7684\u4f5c\u8005\u548c\u6bb5\u5b50\u7684\u5185\u5bb9<\/p>\n
\n
scrapy \u4e5f\u5185\u7f6e\u4e86 css\u3001xpath \u9009\u62e9\u5668\u7684\u89e3\u6790\u4e86<\/p>\n
\n
\u800c\u4e14<\/p>\n
\n
scrapy \u8fd8\u5185\u7f6e\u4e86\u5f88\u591a\u597d\u7528\u7684\u547d\u4ee4<\/p>\n
\n
\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528 scrapy shell \u6765\u8bf7\u6c42\u6211\u4eec\u7684\u7f51\u9875<\/p>\n
\n
\n
scrapy<\/span>\u00a0shell\u00a0\/home\/wistbean\/PycharmProjects\/spider\/qiushibaike\/qiushi-1<\/span>.html<\/span><\/code><\/pre>\n<\/section>\n
\n
shell \u540e\u9762\u53ef\u4ee5\u662f\u4f60\u722c\u4e0b\u6765\u7684 HTML \u6587\u4ef6<\/p>\n
\n
\u4e5f\u53ef\u4ee5\u662f\u4f60\u4e00\u4e2a\u94fe\u63a5<\/p>\n
\n
\u8fdb\u53bb\u4e4b\u540e\u662f\u8fd9\u6837\u7684<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u6211\u4eec\u53ef\u4ee5\u5728\u8fd9\u91cc\u9762\u505a\u4e00\u4e9b\u547d\u4ee4\u64cd\u4f5c\u4e86<\/p>\n
\n
\u6bd4\u5982\u6211\u4eec\u5728\u8fd9\u91cc\u5750\u4e00\u4e0b\u89e3\u6790\u64cd\u4f5c<\/p>\n
\n
\u6253\u5f00\u6211\u4eec\u521a\u521a\u8981\u722c\u7684\u7cd7\u4e8b\u767e\u79d1\u7684\u94fe\u63a5<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\n
\u53ef\u4ee5\u770b\u5230<\/p>\n
\n
\u6bcf\u4e2a\u6bb5\u5b50\u90fd\u88ab\u5305\u542b\u5728\u4e00\u4e2a id \u4e3a content-left \u7684 div \u91cc\u9762<\/p>\n
\n
\u6211\u4eec\u4f7f\u7528\u5982\u4e0b\u547d\u4ee4\u83b7\u53d6<\/p>\n
\n
\n
>><\/span>>\u00a0content_left_div\u00a0=\u00a0response.xpath('\/\/*[@id=\"content-left\"]'<\/span>)<\/span><\/code><\/pre>\n<\/section>\n
\n
\u63a5\u7740\u6211\u4eec\u83b7\u53d6\u5b83\u4e0b\u9762\u7684\u6240\u6709 div<\/p>\n
\n
\n
>><\/span>>\u00a0content_list_div\u00a0=\u00a0content_left_div.xpath('.\/div'<\/span>)<\/span><\/code><\/pre>\n<\/section>\n
\n
\u6211\u4eec\u8bd5\u7740\u83b7\u53d6\u8fd9\u4e2a\u9875\u9762\u7684\u6240\u6709\u4f5c\u8005\u540d\u79f0\u548c\u5185\u5bb9<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\u4f5c\u8005\u540d\u79f0\u4f4d\u4e8e a \u6807\u7b7e\u4e0b\u7684 h2<\/span><\/p>\n
\n
\n
\"python\u722c\u866b29<\/p>\n
\u5185\u5bb9\u4f4d\u4e8ediv\u4e0b\u7684span<\/p>\n
\n
\u6211\u4eec\u8fd8\u662f\u4e00\u6837<\/p>\n
\n
\u901a\u8fc7 xpath \u83b7\u53d6<\/p>\n
\n
\u6211\u4eec\u5148\u6765\u83b7\u53d6\u4e00\u4e2a\u6761\u76ee\u770b\u770b<\/p>\n
\n
\n
content_div<\/span>\u00a0=\u00a0content_list_div[0<\/span>]<\/span><\/code><\/pre>\n<\/section>\n
\n
\u83b7\u53d6\u4f5c\u8005\u540d\u79f0<\/p>\n
\n
\n
>><\/span>> author = content_div.xpath('.\/div\/a[2]\/h2\/text()'<\/span>).get()\n<\/span><\/code>>><\/span>> print(author)\n<\/span><\/code>\n<\/span><\/code>\u8857\u89d2*\n<\/span><\/code>\n<\/span><\/code><\/pre>\n<\/section>\n
\n
\u83b7\u53d6\u6bb5\u5b50\u5185\u5bb9<\/p>\n
\n
\n
>><\/span>> content = content_div.xpath('.\/a\/div\/span\/text()'<\/span>).getall()\n<\/span><\/code>>><\/span>> print(content)\n<\/span><\/code>['nnn\u521a\u4e0a\u5c0f\u5b66\u4e00\u5e74\u7ea7\u65f6\uff0c\u4e00\u6b21\u809a\u5b50\u6709\u70b9\u4e0d\u8212\u670d\u62c9\u809a\u5b50\uff0c\u8dd1\u5230\u5395\u6240\u540e\u8fd0\u52a8\u88e4\u4e0a\u9762\u7684\u7ef3\u5b50\u7adf\u7136\u6253\u4e86\u6b7b\u7ed3\uff0c\u5728\u5395\u6240\u91cc\u9762\u5982\u65e0\u5934\u82cd\u8747\u4e00\u6837\u4e71\u8f6c\u3002'<\/span>, '\u8fd9\u65f6\u770b\u5230\u8001\u5e08\u5728\u65c1\u8fb9\u4e0a\u8e72\u5751\uff0c\u4e5f\u4e0d\u987e\u96be\u4e3a\u60c5\u4e86'<\/span>\u6b64\u65f6\u8001\u5e08\u8e72\u5728\u8e72\u5751\u8eb2\u95ea\u4e0d\u53ca\uff0c\u6d51\u8eab\u4e0a\u4e0b\u661f\u661f\u70b9\u70b9\uff0c\u5c4e\u55b7\u4e86\u6ee1\u8138\u5982\u540c\u957f\u6ee1\u9ebb\u5b50\u822c\uff01', '<\/span>\u53c8\u662f\u5f00\u5fc3\u7684\u4e00\u5929\uff0c\u6ca1\u6709\u62c9\u88e4\u5b50\uff01nn']\n<\/span><\/span><\/code>>>>\u00a0<\/span><\/code><\/pre>\n<\/section>\n
\n
\n
\u8fd9\u6837<\/p>\n
\n
\u6211\u4eec\u5c31\u901a\u8fc7\u547d\u4ee4\u884c\u7684\u65b9\u5f0f\u53ef\u4ee5\u77e5\u9053\u5982\u4f55\u83b7\u53d6\u6211\u4eec\u60f3\u8981\u7684\u6570\u636e\u4e86<\/p>\n
\n
\u56de\u5230\u4ee3\u7801\u6765<\/p>\n
\n
\n
\u6211\u4eec\u628a parse \u65b9\u6cd5\u6539\u6210\u8fd9\u6837<\/p>\n
\n
\n
 def<\/span> parse<\/span>(self<\/span>, response)<\/span><\/span>:\n<\/span><\/code>\n<\/span><\/code>        content_left_div = response.xpath('\/\/*[@id=\"content-left\"]'<\/span>)\n<\/span><\/code>        content_list_div = content_left_div.xpath('.\/div'<\/span>)\n<\/span><\/code>\n<\/span><\/code>        for<\/span> content_div in<\/span> content_list_div:\n<\/span><\/span><\/code>            yield<\/span> {\n<\/span><\/code>                'author'<\/span>: content_div.xpath('.\/div\/a[2]\/h2\/text()'<\/span>).get(),\n<\/span><\/code>                'content'<\/span>: content_div.xpath('.\/a\/div\/span\/text()'<\/span>).getall(),\n<\/span><\/code>            }<\/span><\/code><\/pre>\n<\/section>\n
\n
\u7136\u540e\u518d\u4f7f\u7528\u547d\u4ee4\u884c\u8fd0\u884c<\/p>\n
\n
\n
scrapy<\/span>\u00a0crawl\u00a0qiushibaike<\/span><\/code><\/pre>\n<\/section>\n
\n
\n
\u53ef\u4ee5\u770b\u5230\u6211\u4eec\u8981\u7684\u4fe1\u606f\u88ab\u6253\u5370\u51fa\u6765\u4e86<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\n
\u90a3\u4e48<\/p>\n
\n
\u8981\u5c06\u722c\u4e0b\u6765\u7684\u6570\u636e\u5b58\u50a8\u4e3a json \u6587\u4ef6\u600e\u4e48\u529e\u5462<\/p>\n
\n
\u4e00\u4e2a\u547d\u4ee4\u5c31\u641e\u5b9a\u4e86<\/p>\n
\n
\n
scrapy<\/span>\u00a0crawl<\/span>\u00a0qiushibaike<\/span>\u00a0-o<\/span>\u00a0qiushibaike<\/span>.json<\/span><\/span><\/code><\/pre>\n<\/section>\n
\n
\u8fd0\u884c\u4e4b\u540e\u4f60\u4f1a\u770b\u5230\u4f60\u7684\u9879\u76ee\u4e0b\u591a\u4e86\u4e00\u4e2a json \u6587\u4ef6<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u4e0d\u8fc7\u4e2d\u6587\u4e71\u7801\u4e86<\/p>\n
\n
\u5728 settings.py \u4e2d\u52a0\u4e00\u53e5<\/p>\n
\n
\n
FEED_EXPORT_ENCODING<\/span>\u00a0=\u00a0'utf-8'<\/span><\/span><\/code><\/pre>\n<\/section>\n
\n
\u6211\u4eec\u5728\u8fd0\u884c\u4e00\u4e0b<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\n
\u4e2d\u6587\u56de\u6765\u4e86<\/p>\n
\n
\"python\u722c\u866b29<\/p>\n
\n
\u4ec0\u4e48\uff1f<\/p>\n
\n
\u4f60\u60f3\u5b9e\u73b0\u7ffb\u9875\u6293\u53d6\u6240\u6709\u5185\u5bb9\uff1f<\/p>\n
\u8fd8\u60f3\u4fdd\u5b58\u5230\u6570\u636e\u5e93\u91cc\uff1f<\/p>\n
\n
\u597d\u5427<\/p>\n
\n
\u7bc7\u5e45\u6709\u9650<\/p>\n
\n
\u4eca\u5929\u5c31\u5230\u8fd9\u91cc<\/p>\n
\n
\u4e14\u542c\u5e05b\u4e0b\u56de\u8bb2\u89e3<\/p>\n
\n
peace<\/span><\/p>\n
\u00a0<\/span><\/p>\n
\"python\u722c\u866b29<\/span><\/a><\/p>\n
\u539f\u6587\u59cb\u53d1\u4e8e\u5fae\u4fe1\u516c\u4f17\u53f7\uff08\u5b66\u4e60python\u7684\u6b63\u786e\u59ff\u52bf\uff09\uff1apython\u722c\u866b29 | \u4f7f\u7528scrapy\u722c\u53d6\u7cd7\u4e8b\u767e\u79d1\u7684\u4f8b\u5b50\uff0c\u544a\u8bc9\u4f60\u5b83\u6709\u591a\u5389\u5bb3\uff01<\/a><\/p><\/blockquote>\n<\/div>\n","protected":false},"excerpt":{"rendered":"
\u662f\u65f6\u5019\u7ed9\u4f60\u8bf4\u8bf4 \u722c\u866b\u6846\u67b6\u4e86 \u4f7f\u7528\u6846\u67b6\u6765\u722c\u53d6\u6570\u636e \u4f1a\u8282\u7701\u6211\u4eec\u66f4\u591a\u65f6\u95f4 \u5f88\u5feb\u5c31\u80fd\u6293\u53d6\u5230\u6211\u4eec\u60f3\u8981\u6293\u53d6\u7684\u5185\u5bb9 \u6846\u67b6\u96c6\u5408\u4e86\u8bb8\u591a\u64cd\u4f5c \u6bd4\u5982\u8bf7\u6c42\uff0c\u6570\u636e\u89e3\u6790\uff0c\u5b58\u50a8\u7b49\u7b49 \u90fd\u53ef\u4ee5\u7531\u6846\u67b6\u5b8c\u6210 \u6709\u4e9b\u5c0f\u4f19\u4f34\u5c31\u8981\u95ee\u4e86 \u4f60\u4ed6\u5988\u7684 \u4e3a\u4ec0\u4e48\u4e0d\u65e9\u70b9\u8bf4\u5462\uff1f \u662f\u8fd9\u6837\u7684 \u5f53\u4f60\u4e0d\u77e5\u9053 1+1 …<\/p>\n","protected":false},"author":1,"featured_media":5039,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[303],"tags":[401],"_links":{"self":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts\/5038"}],"collection":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5038"}],"version-history":[{"count":2,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts\/5038\/revisions"}],"predecessor-version":[{"id":6642,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/posts\/5038\/revisions\/6642"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=\/wp\/v2\/media\/5039"}],"wp:attachment":[{"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5038"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5038"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vip.fxxkpython.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5038"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}