{"id":20997,"date":"2023-06-04T10:35:12","date_gmt":"2023-06-04T01:35:12","guid":{"rendered":"http:\/\/www.code-magagine.com\/?p=20997"},"modified":"2023-07-17T11:50:24","modified_gmt":"2023-07-17T02:50:24","slug":"%e3%80%90python%e3%80%91scrapy%e3%81%a7spider%e3%82%92%e4%bd%9c%e6%88%90%e3%81%99%e3%82%8b%e6%b5%81%e3%82%8c","status":"publish","type":"post","link":"http:\/\/www.code-magagine.com\/?p=20997","title":{"rendered":"\u3010Python\u3011Scrapy\u3067spider\u3092\u4f5c\u6210\u3059\u308b\u6d41\u308c"},"content":{"rendered":"<h2>\u30b9\u30d1\u30a4\u30c0\u30fc\u306e\u4f5c\u6210<\/h2>\n<pre class=\"lang:default decode:true\">cd spiders\nscrapy genspider [-t \u30c6\u30f3\u30d7\u30ec\u30fc\u30c8] \u30b9\u30d1\u30a4\u30c0\u30fc\u540d URL(\u6700\u521d\u306ehttps:\/\/\u3068\u6700\u5f8c\u306e\/\u306f\u4e0d\u8981)\n<\/pre>\n<p>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u5185\u306espiders\u30d5\u30a9\u30eb\u30c0\u306b\u79fb\u52d5\u3057\u3066\u4e0a\u8a18\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3057\u307e\u3059\u3002<\/p>\n<h3>-t \u30c6\u30f3\u30d7\u30ec\u30fc\u30c8<\/h3>\n<p>\u30c7\u30d5\u30a9\u30eb\u30c8\u306f\u300cbasic\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u300d\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n<h4>\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u306e\u78ba\u8a8d<\/h4>\n<pre class=\"lang:default decode:true\">scrapy genspider -l\n\nAvailable templates:\n  basic\n  crawl\n  csvfeed\n  xmlfeed<\/pre>\n<p>\u9078\u3079\u308b\u30c6\u30f3\u30d7\u30ec\u30fc\u30c8\u306f\u4e0a\u8a18\u30b3\u30de\u30f3\u30c9\u3067\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002<\/p>\n<h3>\u751f\u6210\u3055\u308c\u308b\u30b9\u30d1\u30a4\u30c0\u30fcclass<\/h3>\n<pre class=\"lang:default decode:true\">import scrapy\n\n\nclass XXXSpider(scrapy.Spider):\n    name = \"\u30b9\u30d1\u30a4\u30c0\u30fc\u540d\"\n    allowed_domains = [\"xxx\"]\n    start_urls = [\"https:\/\/xxx\"]\n\n    def parse(self, response):\n        pass\n<\/pre>\n<h4>scrapy.Spider<\/h4>\n<p>\u7d99\u627f\u3057\u3066\u3044\u308b\u30af\u30e9\u30b9\u3067\u3059\u3002\u3053\u308c\u3092\u7d99\u627f\u3057\u3066\u3044\u308b\u306e\u3067\u307b\u3093\u306e\u6570\u884c\u3067\u3082\u591a\u304f\u306e\u3053\u3068\u3092\u884c\u3046\u3053\u3068\u304c\u3067\u304d\u307e\u3059\u3002<\/p>\n<h4>allowed_domains<\/h4>\n<p>spider\u304c\u30a2\u30af\u30bb\u30b9\u3059\u308b\u30c9\u30e1\u30a4\u30f3\u540d\u3067\u3059\u3002\u6307\u5b9a\u3055\u308c\u305f\u30c9\u30e1\u30a4\u30f3\u4ee5\u5916\u306b\u30b9\u30af\u30ec\u30a4\u30d4\u30f3\u30b0\u3059\u308b\u3053\u3068\u3092\u9632\u6b62\u3067\u304d\u307e\u3059\u3002\u8a2d\u5b9a\u3057\u306a\u304f\u3066\u3082\u52d5\u304d\u307e\u3059\u304c\u3001\u601d\u308f\u306c\u30b5\u30a4\u30c8\u306b\u30a2\u30af\u30bb\u30b9\u3057\u3066\u3057\u307e\u308f\u306a\u3044\u3088\u3046\u306b\u8a2d\u5b9a\u3057\u305f\u307b\u3046\u304c\u7121\u96e3\u3067\u3059\u3002<\/p>\n<h4>start_urls<\/h4>\n<p>\u3053\u3053\u3067\u8a2d\u5b9a\u3057\u305fURL\u306b\u5bfe\u3057\u3066\u30ea\u30af\u30a8\u30b9\u30c8\u3092\u307e\u305a\u884c\u3044\u307e\u3059\u3002\u914d\u5217\u306a\u306e\u3067\u8907\u6570\u8a2d\u5b9a\u3082\u53ef\u80fd\u3067\u3059\u3002<\/p>\n<h4>parse\u30e1\u30bd\u30c3\u30c9<\/h4>\n<p>Web\u30b5\u30a4\u30c8\u304b\u3089\u306e\u30ec\u30b9\u30dd\u30f3\u30b9\u3092\u3053\u3053\u3067\u30ad\u30e3\u30c3\u30c1\u3057\u307e\u3059\u3002\u3053\u3053\u306bXPath\u3084CSS\u30bb\u30ec\u30af\u30bf\u306a\u3069\u3092\u4f7f\u3063\u305f\u60c5\u5831\u62bd\u51fa\u51e6\u7406\u306a\u3069\u3092\u8a18\u8ff0\u3057\u3066\u3044\u304d\u307e\u3059\u3002<\/p>\n<h2>\u30b5\u30f3\u30d7\u30eb<\/h2>\n<p>Scrapy\u3067\u306f\u307b\u3093\u306e\u6570\u884c\u306e\u30b3\u30fc\u30c9\u3092\u8a18\u8ff0\u3059\u308b\u3060\u3051\u3067\u57fa\u672c\u7684\u306a\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306f\u7d42\u308f\u308a\u307e\u3059\u3002<\/p>\n<pre class=\"lang:default decode:true\">import scrapy\n\n\nclass QiitaTrend1dSpider(scrapy.Spider):\n    name = \"spider\u540d\"\n    allowed_domains = [\"xxx.com\"]\n    start_urls = [\"https:\/\/xxx.com\"]\n\n    def parse(self, response):\n        \u5909\u65701 = response.xpath('\u5909\u65701\u3092\u53d6\u5f97\u3059\u308bXpath').get()\n        \u5909\u65702 = response.xpath('\u5909\u65702\u3092\u53d6\u5f97\u3059\u308bXpath').getall()\n\n        yield {\n            '\u30ad\u30fc1':\u5909\u65701,\n            '\u30ad\u30fc2': \u5909\u65702,\n        }\n<\/pre>\n<h3>response<\/h3>\n<p>\u30c7\u30fc\u30bf\u578b\u306f\u300cscrapy.http.response.html.HtmlResponse\u300d\u3068\u3044\u3046class\u306b\u306a\u308a\u307e\u3059\u3002<\/p>\n<p>\u516c\u5f0f\u30b5\u30a4\u30c8\u306b\u8a73\u3057\u3044\u4f7f\u3044\u65b9\u306f\u8f09\u3063\u3066\u3044\u307e\u3059\u3002\uff08xpath\u3084css\u30e1\u30bd\u30c3\u30c9\u306b\u3064\u3044\u3066\u3082\u3053\u306e\u30da\u30fc\u30b8\u306b\u8a18\u8f09\u304c\u3042\u308a\u307e\u3059\u3002\uff09<\/p>\n<p>https:\/\/doc-ja-scrapy.readthedocs.io\/ja\/latest\/topics\/request-response.html<\/p>\n<h3>yield \u623b\u308a\u5024<\/h3>\n<p>\u95a2\u6570\u306e\u5b9f\u884c\u3092\u4e00\u6642\u7684\u306b\u505c\u6b62\u3057\u3066\u623b\u308a\u5024\u3092\u8fd4\u3057\u307e\u3059\u3002response\u7d50\u679c\u306b\u5bfe\u3057\u3066\u8f9e\u66f8\u578b\u3092\u623b\u308a\u5024\u3068\u3057\u3066\u8a2d\u5b9a\u3057\u3066\u3042\u3052\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u753b\u9762\u3084\u30b3\u30f3\u30bd\u30fc\u30eb\u306b\u53d6\u5f97\u7d50\u679c\u304c\u51fa\u529b\u3055\u308c\u307e\u3059\u3002\u4e00\u65e6\u505c\u6b62\u3059\u308b\u3060\u3051\u306a\u306e\u3067\u305d\u306e\u5f8c\u51e6\u7406\u306f\u7d99\u7d9a\u3057\u3066\u5b9f\u884c\u3055\u308c\u307e\u3059\u3002<\/p>\n<h2>spider\u306e\u5b9f\u884c<\/h2>\n<p>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30d5\u30a9\u30eb\u30c0\u76f4\u4e0b\u3067\u3001\u4ee5\u4e0b\u306e\u30b3\u30de\u30f3\u30c9\u3092\u5b9f\u884c\u3057\u307e\u3059\u3002<\/p>\n<pre class=\"lang:default decode:true\">scrapy crawl \u30b9\u30d1\u30a4\u30c0\u30fc\u540d\uff08spider\u30af\u30e9\u30b9\u306e\u4e2d\u306ename\u3067\u6307\u5b9a\u3057\u305f\u5024\uff09<\/pre>\n<h3>json\u306b\u51fa\u529b\u3057\u305f\u3044\u5834\u5408<\/h3>\n<p>o\u30aa\u30d7\u30b7\u30e7\u30f3\u3092\u4f7f\u3044\u307e\u3059\u3002<\/p>\n<pre class=\"lang:default decode:true\">scrapy crawl spider\u540d -o xxx.json<\/pre>\n<h2>\u5165\u308c\u5b50(Selector\u306b\u5bfe\u3057\u3066XPath\u3092\u6307\u5b9a)\uff1a\u76f8\u5bfeXPath<\/h2>\n<pre class=\"lang:default decode:true\">parent = response.xpath('\/\/div[contains(@class,\"parent\")]')\nchild = parent.xpath('.\/\/div[contains(@class,\"pName\")]\/p')<\/pre>\n<p>\u89aa\u8981\u7d20\u306eSelector\u306b\u5bfe\u3057\u3066xpath\u3092\u5b9f\u884c\u3067\u304d\u307e\u3059\u3002\u305d\u306e\u969b\u306fresponse\u306bXPath\u3092\u6307\u5b9a\u3059\u308b\u306e\u3068\u7570\u306a\u308a\u3001\u30c9\u30c3\u30c8\u3092\u5148\u982d\u306b\u3064\u3051\u308b\u5fc5\u8981\u304c\u3042\u308b\u306e\u3067\u6ce8\u610f\u3067\u3059\u3002<\/p>\n<p>\u3053\u308c\u3092\u76f8\u5bfeXPath\u3068\u547c\u3073\u307e\u3059\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u30b9\u30d1\u30a4\u30c0\u30fc\u306e\u4f5c\u6210 cd spiders scrapy genspider [-t \u30c6\u30f3\u30d7\u30ec\u30fc\u30c8] \u30b9\u30d1\u30a4\u30c0\u30fc\u540d URL(\u6700\u521d\u306ehttps:\/\/\u3068\u6700\u5f8c\u306e\/\u306f\u4e0d\u8981) \u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u5185\u306espiders\u30d5\u30a9\u30eb\u30c0\u306b\u79fb\u52d5\u3057\u3066\u4e0a\u8a18\u30b3\u30de\u30f3 [&hellip;]","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[47],"tags":[],"_links":{"self":[{"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=\/wp\/v2\/posts\/20997"}],"collection":[{"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=20997"}],"version-history":[{"count":12,"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=\/wp\/v2\/posts\/20997\/revisions"}],"predecessor-version":[{"id":21978,"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=\/wp\/v2\/posts\/20997\/revisions\/21978"}],"wp:attachment":[{"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=20997"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=20997"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.code-magagine.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=20997"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}