{"id":1147,"date":"2018-08-02T21:28:45","date_gmt":"2018-08-02T13:28:45","guid":{"rendered":"http:\/\/www.sniper97.cn\/?p=1147"},"modified":"2018-08-02T21:28:45","modified_gmt":"2018-08-02T13:28:45","slug":"%e7%ac%ac%e5%8d%81%e4%b8%83%e8%8a%82%ef%bc%9ascrapy%e6%a1%86%e6%9e%b6","status":"publish","type":"post","link":"http:\/\/www.sniper97.cn\/index.php\/note\/carwler\/1147\/","title":{"rendered":"\u7b2c\u5341\u4e03\u8282\uff1aScrapy\u6846\u67b6"},"content":{"rendered":"

\u672c\u9875\u4ee3\u7801\u53ef\u4ee5\u5728\u8fd9\u91cc<\/a>\u4e0b\u8f7d\u3002
\n\u5982\u679c\u65e0\u6cd5\u542f\u52a8Scrapy\u79fb\u6b65\u8fd9\u91cc<\/a>\u3002<\/p>\n

PySpider\u548cScrapy\u7684\u533a\u522b\uff1a<\/h4>\n

\u524d\u8005\u63d0\u4f9b\u4e86WebUI\uff0c\u4ee3\u7801\u7684\u7f16\u5199\u3001\u8c03\u8bd5\u90fd\u662f\u5728WebUI\u4e2d\u7ee7\u7eed\uff0c\u800c\u540e\u8005\u7684\u539f\u751f\u4e0d\u5177\u5907\u8fd9\u4e2a\u529f\u80fd\uff0c\u91c7\u7528\u4ee3\u7801\u548c\u547d\u4ee4\u884c\u64cd\u4f5c\uff0c\u4f46\u53ef\u4ee5\u901a\u8fc7\u5bf9\u63a5Portia\u5b9e\u73b0\u53ef\u89c6\u5316\u914d\u7f6e\u3002
\n\u524d\u8005\u8c03\u8bd5\u975e\u5e38\u65b9\u4fbf\uff0cWebUI\u64cd\u4f5c\u4fbf\u6377\u76f4\u89c2\u3002\u540e\u8005\u5219\u662f\u4f7f\u7528parse\u547d\u4ee4\u8fdb\u884c\u8c03\u8bd5\u3002
\n\u524d\u8005\u652f\u6301PhantomJS\u6765\u8fdb\u884cJS\u6e32\u67d3\uff0c\u800c\u540e\u8005\u53ef\u4ee5\u5bf9\u63a5Scrapy-Splash\u7ec4\u4ef6\uff0c\u8fd9\u4e2a\u9700\u8981\u683c\u5916\u914d\u7f6e\u3002
\n\u524d\u8005\u5185\u7f6epyquery\u4f5c\u4e3a\u9009\u62e9\u5668\uff0c\u800c\u540e\u8005\u5bf9\u63a5XPath\u548cCSS\u9009\u62e9\u5668\u3002
\n\u524d\u8005\u53ef\u6269\u5c55\u7a0b\u5ea6\u4e0d\u8db3\uff0c\u53ef\u914d\u7f6e\u5316\u7a0b\u5ea6\u4e0d\u9ad8\u3002\u540e\u8005\u53ef\u4ee5\u901a\u8fc7\u5bf9\u63a5Middleware\u3001Pipeline\u3001Extension \u7b49\u7ec4\u4ef6\u5b9e\u73b0\u975e\u5e38\u5f3a\u5927\u7684\u529f\u80fd\uff0c\u4e14\u6a21\u5757\u4e4b\u95f4\u8026\u5408\u7a0b\u5ea6\u4f4e\uff0c\u53ef\u6269\u5c55\u7a0b\u5ea6\u6781\u9ad8\u3002
\n <\/p>\n

Scrapy\u57fa\u672c\u4ecb\u7ecd\uff1a<\/h4>\n

Scrapy\u662f\u4e00\u4e2a\u57fa\u4e8eTwisted\u7684\u5f02\u6b65\u5904\u7406\u6846\u67b6\uff0c\u662f\u7eafPython\u5b9e\u73b0\u7684\u722c\u866b\u6846\u67b6\uff0c\u5176\u67b6\u6784\u6e05\u6670\uff0c\u7c73\u5757\u4e4b\u95f4\u7684\u8026\u5408\u7a0b\u5ea6\u6781\u4f4e\uff0c\u53ef\u6269\u5c55\u6027\u6781\u5f3a\uff0c\u53ef\u4ee5\u7075\u6d3b\u5b8c\u6210\u5404\u79cd\u9700\u6c42\u3002
\n\u5b83\u53ef\u4ee5\u5206\u4e3a\u4ee5\u4e0b\u51e0\u90e8\u5206\uff1a
\nEngine\uff1a\u5f15\u64ce\uff0c\u5904\u7406\u6574\u4e2a\u7cfb\u7edf\u7684\u6570\u636e\u6d41\u5904\u7406\u3001\u51fa\u53d1\u4e8b\u7269\uff0c\u662f\u6574\u4e2a\u6846\u67b6\u7684\u6838\u5fc3\u3002
\nItem\uff1a\u9879\u76ee\uff0c\u5b83\u5b9a\u4e49\u4e86\u722c\u53d6\u7ed3\u679c\u7684\u6570\u636e\u7ed3\u6784\uff0c\u722c\u53d6\u7684\u6570\u636e\u4f1a\u88ab\u8d4b\u503c\u6210\u8be5Item\u5bf9\u8c61\u3002
\nScheduler\uff1a\u8c03\u5ea6\u5668\uff0c\u63a5\u53d7\u5f15\u64ce\u53d1\u8fc7\u6765\u7684\u8bf7\u6c42\u5e76\u5c06\u5176\u52a0\u5165\u961f\u5217\u4e2d\uff0c\u5728\u5f15\u64ce\u518d\u6b21\u8bf7\u6c42\u7684\u65f6\u5019\u5c06\u8bf7\u6c42\u63d0\u4f9b\u7ed9\u5f15\u64ce\u3002
\nDownloader\uff1a\u4e0b\u8f7d\u5668\uff0c\u4e0b\u8f7d\u7f51\u9875\u5185\u5bb9\uff0c\u5e76\u5c06\u5185\u5bb9\u8fd4\u56de\u7ed9\u8718\u86db\u3002
\nSpider\uff1a\u8718\u86db\uff0c\u5176\u5185\u5b9a\u4e49\u4e86\u722c\u53d6\u7684\u903b\u8f91\u548c\u7f51\u9875\u7684\u89e3\u6790\u89c4\u5219\uff0c\u4ed6\u4e3b\u8981\u8d1f\u8d23\u89e3\u6790\u54cd\u5e94\u5e76\u751f\u6210\u63d0\u53d6\u7ed3\u679c\u548c\u65b0\u7684\u8bf7\u6c42\u3002
\nItem Pipeline\uff1a\u9879\u76ee\u7ba1\u9053\uff0c\u8d1f\u8d23\u5904\u7406\u7531\u8718\u86db\u4ece\u7f51\u9875\u4e2d\u62bd\u53d6\u7684\u9879\u76ee\uff0c\u5b83\u4e3b\u8981\u4efb\u52a1\u662f\u6e05\u6d17\u3001\u9a8c\u8bc1\u548c\u5b58\u50a8\u3002
\nDownloader Middlewares\uff1a\u4e0b\u8f7d\u5668\u4e2d\u95f4\u4ef6\uff0c\u4f4d\u4e8e\u5f15\u64ce\u548c\u4e0b\u8f7d\u5668\u4e4b\u95f4\u7684\u94a9\u5b50\u6846\u67b6\uff0c\u4e3b\u8981\u5904\u7406\u5f15\u64ce\u548c\u4e0b\u8f7d\u5668\u4e4b\u95f4\u7684\u8bf7\u6c42\u548c\u76f8\u5e94\u3002
\nSpider Middlewares\uff1a\u8718\u86db\u4e2d\u95f4\u4ef6\uff0c\u4f4d\u4e8e\u5f15\u64ce\u548c\u8718\u86db\u4e4b\u95f4\u7684\u94a9\u5b50\u67b6\u6784\uff0c\u4e3b\u8981\u5904\u7406\u8718\u86db\u8f93\u5165\u7684\u54cd\u5e94\u548c\u8f93\u51fa\u7684\u7ed3\u679c\u53ca\u65b0\u7684\u8bf7\u6c42\u3002
\n <\/p>\n

\u521b\u5efaScrapy\uff1a<\/h4>\n

\u6211\u4eec\u4ee5\u722c\u53d6http:\/\/quotes.toscrape.com\/<\/a> \u4e3a\u4f8b
\n\u5728\u547d\u4ee4\u884c\u4e2d\u8f93\u5165scrapy startproject tutorial
\n\u5176\u4e2dscrapy startproject\u662f\u56fa\u5b9a\u542f\u52a8\u547d\u4ee4 tutorial\u662f\u5de5\u7a0b\u540d\u3002
\n\u521b\u5efa\u5b8c\u6210\u4e4b\u540e\u5f53\u524d\u76ee\u5f55\u4e0b\u4f1a\u591a\u4e00\u4e2atutorial\u6587\u4ef6\u5939\u3002
\n\"\"
\n\u7136\u540e\u8fdb\u5165tutorial\u76ee\u5f55\u4e0b\uff0c\u547d\u4ee4\u884c\u8f93\u5165\uff1a
\nscrapy genspider quotes quotes.toscrape.com
\ngenspider\u547d\u4ee4\u4e2d\u7b2c\u4e00\u4e2a\u53c2\u6570\u662f\u6587\u4ef6\u540d\uff0c\u7b2c\u4e8c\u4e2a\u53c2\u6570\u662fURL
\n\u521b\u5efaSpider\u7684\u5b50\u7c7b\uff0c\u7528\u6765\u6293\u53d6\u7f51\u9875\u4e2d\u7684\u5185\u5bb9\u3002
\n\"\"
\n\u8fd0\u884c\u7ed3\u675f\u4e4b\u540e\u6211\u4eec\u770b\u5230spiders\u6587\u4ef6\u4e0b\u591a\u4e86\u4e00\u4e2aquotes.py
\n\u5176\u4e2d\u4ee3\u7801\uff1a<\/p>\n

# -*- coding: utf-8 -*-\nimport scrapy\nclass QuotesSpider(scrapy.Spider):\n    name = 'quotes'\n    allowed_domains = ['quotes.toscrape.com']\n    start_urls = ['http:\/\/quotes.toscrape.com\/']\n    def parse(self, response):\n        pass\n<\/pre>\n
\u8fd9\u91cc\u6709\u4e09\u4e2a\u5c5e\u6027\uff1aname\u3001allowed_domains \u548cstart_urls\uff0c\u8fd8\u6709\u4e00\u4e2a\u65b9\u6cd5parse\u3002
\nname\uff1a\u6ca1\u4e00\u4e2a\u9879\u76ee\u552f\u4e00\u7684\u540d\u5b57\uff0c\u7528\u6765\u533a\u5206\u4e0d\u540c\u7684Spider
\nallowed_domains\uff1a\u5141\u8bb8\u722c\u53d6\u7684\u57df\u540d\uff0c\u5982\u679c\u521d\u59cb\u6216\u540e\u7eed\u7684\u8bf7\u6c42\u94fe\u63a5\u4e0d\u662f\u8fd9\u4e2a\u57df\u540d\u4e0b\u7684\uff0c\u5219\u8bf7\u6c42\u94fe\u63a5\u4f1a\u88ab\u8fc7\u6ee4\u6389\u3002
\nstart_urls\uff1a\u5b83\u5305\u542b\u4e86Spider\u5728\u542f\u52a8\u65f6\u722c\u53d6\u7684url\u5217\u8868\uff0c\u521d\u59cb\u8bf7\u6c42\u662f\u7531\u5b83\u6765\u5b9a\u4e49\u7684\u3002
\nparse\uff1a\u4ed6\u662fSpider\u7684\u4e00\u4e2a\u65b9\u6cd5\u3002\u9ed8\u8ba4\u60c5\u51b5\u4e0b\uff0c\u88ab\u8c03\u7528start_urls\u91cc\u9762\u7684\u94fe\u63a5\u6784\u6210\u7684\u8bf7\u6c42\u5b8c\u6210\u4e0b\u8f7d\u6267\u884c\u540e\uff0c\u8fd4\u56de\u54cd\u5e94\u5c31\u4f1a\u4f5c\u4e3a\u552f\u4e00\u7684\u53c2\u6570\u4f20\u9012\u7ed9\u8fd9\u4e2a\u51fd\u6570\u3002\u8be5\u65b9\u6cd5\u8d1f\u8d23\u89e3\u6790\u8fd4\u56de\u7684\u54cd\u5e94\u3001\u63d0\u53d6\u6570\u636e\u6216\u8fdb\u4e00\u6b65\u751f\u6210\u8981\u5904\u7406\u7684\u8bf7\u6c42\u3002
\n <\/p>\n
\u521b\u5efaitem\uff1a<\/h4>\n
\u4fdd\u5b58\u722c\u53bb\u6570\u636e\u7684\u5bb9\u5668\uff0c\u4f7f\u7528\u65b9\u6cd5\u548c\u5b57\u5178\u7c7b\u4f3c\uff0c\u4f46\u662f\u591a\u4e86\u4fdd\u62a4\u673a\u5236\uff0c\u53ef\u4ee5\u907f\u514d\u62fc\u5199\u9519\u8bef\u6216\u8005\u5b9a\u4e49\u5b57\u6bb5\u9519\u8bef\u3002
\nitems.py<\/p>\n
# -*- coding: utf-8 -*-\n# Define here the models for your scraped items\n#\n# See documentation in:\n# https:\/\/doc.scrapy.org\/en\/latest\/topics\/items.html\nimport scrapy\nclass TutorialItem(scrapy.Item):\n    # define the fields for your item here like:\n    # name = scrapy.Field()\n    text = scrapy.Field()\n    author = scrapy.Field()\n    tags = scrapy.Field()\n<\/pre>\n
quotes.py \u4e0b parse() \u65b9\u6cd5
\n\u7136\u540e\u6211\u4eec\u66f4\u6539quotes.py\uff0c\u6ce8\u610f\u8fd9\u91cc\u4e0b\u4e00\u9875\u662f\u76f8\u5bf9\u94fe\u63a5\uff0c\u9700\u8981\u4f7f\u7528reljoin\u8f6c\u6362\u6210\u7edd\u5bf9\u94fe\u63a5\u3002
\n\"\"
\n\u7136\u540e\u5904\u7406\u4fe1\u606f\u8fc7\u6ee4\uff1a<\/p>\n
# -*- coding: utf-8 -*-\nimport scrapy\nfrom tutorial.items import TutorialItem\nclass QuotesSpider(scrapy.Spider):\n    name = 'quotes'\n    allowed_domains = ['quotes.toscrape.com']\n    start_urls = ['http:\/\/quotes.toscrape.com\/']\n    def parse(self, response):\n        quotes = response.css('.quote')\n        for quote in quotes:\n            item = TutorialItem()\n            item['text'] = quote.css('.text::text').extract_first()\n            item['author'] = quote.css('.author::text').extract_first()\n            item['tags'] = quote.css('.tags .tag::text').extract()\n            yield item\n        # \u83b7\u53d6\u4e0b\u4e00\u9875\u94fe\u63a5\n        next = response.css('.pager .next a::attr(\"href\")').extract_first()\n        # \u5904\u7406\u7edd\u5bf9\u94fe\u63a5\n        url = response.urljoin(next)\n        yield scrapy.Request(url=url, callback=self.parse)\n<\/pre>\n
 
\n\u7136\u540e\u5728\u547d\u4ee4\u884c\u8f93\u5165\uff1a scrapy crawl quotes
\n\u8f93\u51fa\u722c\u53d6\u7ed3\u679c\uff1a
\n\"\"<\/p>\n
\u8f93\u51fa\u5230\u6587\u4ef6\uff1a<\/h4>\n
\u547d\u4ee4\u884c\u8f93\u5165\uff1a
\nscrapy crawl quotes -o quotes.json
\n\u8fd9\u91cc\u662f\u8f93\u51fa\u4e00\u4e2ajson\u6587\u4ef6\uff0c\u540c\u6837\u8fd8\u53ef\u4ee5\u8f93\u51fa.csv\u3001.xml\u7b49\u8bb8\u591a\u683c\u5f0f\u3002<\/p>\n
\u8f93\u51fa\u5230\u6570\u636e\u5e93\uff1a<\/h4>\n
\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Item Pipeline\u628a\u6570\u636e\u4fdd\u5b58\u5230\u6570\u636e\u5e93\u3002
\n\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Item Pipeline\u6765\u505a\u4ee5\u4e0b\u64cd\u4f5c\uff1a
\n\u6e05\u7406HTML\u6570\u636e\u3002
\n\u9a8c\u8bc1\u722c\u53d6\u6570\u636e\uff0c\u68c0\u67e5\u722c\u53d6\u6587\u5b57\u3002
\n\u67e5\u91cd\u5e76\u4e22\u5f03\u91cd\u590d\u5185\u5bb9\u3002
\n\u5c06\u722c\u53d6\u7ed3\u679c\u4fdd\u5b58\u5230\u6570\u636e\u5e93\u4e2d\u3002
\n\u8981\u5b9e\u73b0Item Pipeline\uff0c\u53ea\u9700\u8981\u5b9a\u4e49\u4e00\u4e2a\u7c7b\u5e76\u5b9e\u73b0process_item\uff08\uff09\u65b9\u6cd5\u5373\u53ef\u3002
\n\u4fee\u6539\u9879\u76ee\u4e2d\u7684pipelines.py\u6587\u4ef6\uff1a<\/p>\n
# -*- coding: utf-8 -*-\n# Define your item pipelines here\n#\n# Don't forget to add your pipeline to the ITEM_PIPELINES setting\n# See: https:\/\/doc.scrapy.org\/en\/latest\/topics\/item-pipeline.html\nfrom scrapy.exceptions import DropItem\nimport pymongo\nclass TutorialPipeline(object):\n    def __init__(self):\n        self.limit = 50\n    def process_item(self, item, spider):\n        if item['text']:\n            if len(item['text']) > self.limit:\n                # rstrip \u5220\u9664\u7ed3\u5c3e\u7a7a\u683c\n                item['text'] = item['text'][0:self.limit].rstrip() + '...'\n            return item\n        else:\n            return DropItem('Missing Text')\nclass MongoPipeline(object):\n    def __init__(self, mongo_uri, mongo_db):\n        self.mongo_uri = mongo_uri\n        self.mongo_db = mongo_db\n    @classmethod\n    def from_crawler(cls, crawler):\n        return cls(\n            mongo_uri=crawler.settings.get('MONGO_URI'),\n            mongo_db=crawler.settings.get('MONGO_DB')\n        )\n    def open_spider(self, spider):\n        self.client = pymongo.MongoClient(self.mongo_uri)\n        self.db = self.client[self.mongo_db]\n    def process_item(self, item, spider):\n        name = item.__class__,__name__\n        self.db[name].insert(dict(item))\n        return item\n    def close_spider(self,spider):\n        self.client.close()\n<\/pre>\n
\u8fd9\u91cc\u6211\u4eec\u5728\u6784\u9020\u65b9\u6cd5\u4e2d\u5b9a\u4e49\u4e86\u9650\u5236\u957f\u5ea650\uff0c\u5b9e\u73b0\u4e86process_item\uff08\uff09\uff0c\u5176\u53c2\u6570\u662fitem\u548cspider\uff0c\u9996\u5148\u8be5\u65b9\u6cd5\u5224\u65aditem\u7684text\u5c5e\u6027\u662f\u5426\u5b58\u5728\uff0c\u5982\u679c\u4e0d\u5b58\u5728\u629b\u51fa\u5f02\u5e38\uff0c\u5982\u679c\u5b58\u5728\uff0c\u5728\u5224\u65ad\u957f\u5ea6\u662f\u5426\u5927\u4e8e50\uff0c\u5982\u679c\u5927\u4e8e\uff0c\u90a3\u5c31\u9636\u6bb5\u7136\u540e\u62fc\u63a5\u7701\u7565\u53f7\uff0c\u518d\u5c06item\u8fd4\u56de\u3002
\n\u7136\u540e\u5b9a\u4e49\u4e86\u4e00\u4e2a\u7c7bMongoPipeline\u6765\u4fdd\u5b58\u8fdb\u6570\u636e\u5e93\uff1a
\nfrom_crawler\uff08\uff09\uff1b\u4e00\u4e2a\u7c7b\u65b9\u6cd5\uff0c\u7528@classmethod\u6807\u8bc6\uff0c\u662f\u4e00\u79cd\u4f9d\u8d56\u6ce8\u5165\u7684\u65b9\u5f0f\uff0c\u4ed6\u7684\u53c2\u6570\u5c31\u662fcrawler\uff0c\u901a\u8fc7crawler\u6211\u4eec\u53ef\u4ee5\u62ff\u5230\u5168\u5c40\u914d\u7f6e\u7684\u6bcf\u4e2a\u914d\u7f6e\u4fe1\u606f\u3002\u5728\u5168\u5c40\u914d\u7f6esettings.py\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u5b9a\u4e49MONGO_URI \u548c MONGO_DB \u6765\u6307\u5b9aMongoDB \u8fde\u63a5\u9700\u8981\u7684\u5730\u5740\u548c\u6570\u636e\u5e93\u540d\u3002\u5373\u8fd9\u4e2a\u65b9\u6cd5\u5c31\u662f\u7528\u6765\u83b7\u53d6settings.py\u4e2d\u7684\u914d\u7f6e\u7684\u3002
\nopen_spider\uff08\uff09\uff1b\u5f53Spider\u5f00\u542f\u65f6\uff0c\u8fd9\u4e2a\u65b9\u6cd5\u88ab\u8c03\u7528\uff0c\u4e3b\u8981\u8fdb\u884c\u4e00\u4e9b\u521d\u59cb\u5316\u64cd\u4f5c\u3002
\nclose_spider\uff08\uff09\uff1b\u5f53Spider\u5173\u95ed\u65f6\uff0c\u8fd9\u4e2a\u65b9\u6cd5\u88ab\u8c03\u7528\uff0c\u4e3b\u8981\u8fdb\u884c\u5173\u95ed\u6570\u636e\u5e93\u64cd\u4f5c\u3002
\nprocess_item\uff08\uff09\uff1b\u6267\u884c\u6570\u636e\u63d2\u5165\u64cd\u4f5c\u3002
\n\u7136\u540e\u5728settings.py\u4e2d\u6dfb\u52a0\u914d\u7f6e\u4fe1\u606f\uff1a<\/p>\n
ITEM_PIPELINES = {\n    'tutorial.pipelines.TutorialPipeline': 300,\n    'tutorial.pipelines.MongoPipeline': 400\n}\nMONGO_URI = 'localhost'\nMONGO_DB = 'Test'\n<\/pre>\n
\u6700\u540e\u91cd\u65b0\u8fd0\u884c\u722c\u866b\uff0c\u6570\u636e\u5e93\u8f93\u51fa\u5982\u4e0b\uff1a
\n\"\"
\n <\/p>\n
Selector \u7684\u7528\u6cd5\uff1a<\/h4>\n
selector\u662fScrapy\u63d0\u4f9b\u7684\u81ea\u5df1\u7684\u6570\u636e\u63d0\u53d6\u65b9\u6cd5\uff0c\u5b83\u662f\u57fa\u4e8elxml\u6765\u6784\u5efa\u7684\uff0c\u652f\u6301XPath\u9009\u62e9\u5668\u3001CSS\u9009\u62e9\u5668\u4ee5\u53ca\u6b63\u5219\u8868\u8fbe\u5f0f\uff0c\u529f\u80fd\u5168\u9762\uff0c\u89e3\u6790\u901f\u5ea6\u548c\u51c6\u786e\u5ea6\u975e\u5e38\u9ad8\u3002
\n\u6211\u4eec\u53ef\u4ee5\u76f4\u63a5\u5229\u7528Selector \u8fd9\u4e2a\u7c7b\u6765\u6784\u5efa\u4e00\u4e2a\u9009\u62e9\u5668\u5bf9\u8c61\uff0c\u7136\u540e\u8c03\u7528xpath\uff08\uff09\u3001css\uff08\uff09\u7b49\u6765\u63d0\u53d6\u6570\u636e\u3002<\/p>\n
Spider \u7684\u7528\u6cd5\uff1a<\/h4>\n
\u5728Scrapy\u722c\u866b\u9879\u76ee\u4e2d\uff0c\u6700\u6838\u5fc3\u7684\u7c7b\u5c31\u662fSpider\u7c7b\u4e86\uff0c\u5b83\u5b9a\u4e49\u4e86\u5982\u4f55\u722c\u53d6\u67d0\u4e2a\u7f51\u7ad9\u7684\u6d41\u7a0b\u548c\u89e3\u6790\u65b9\u5f0f\u3002
\n\u521b\u5efa\u722c\u866b\uff1a
\n\u5728\u5df2\u7ecf\u521b\u5efa\u597d\u9879\u76ee\u4e4b\u540e\uff0c\u8f93\u5165
\nscrapy genspider name\u00a0 url \u5373\u53ef\u521b\u5efa\u4e00\u4e2a\u722c\u866b\uff0c\u6587\u4ef6\u4f1a\u5b58\u5165spiders\u4e2d
\n\"\"
\n1.name
\n\u722c\u866b\u540d\u5b57\uff0c\u5fc5\u987b\u552f\u4e00\u3002
\n2.allowed_domains
\n\u5141\u8bb8\u722c\u53d6\u7684\u57df\u540d\uff0c\u662f\u53ef\u9009\u914d\u7f6e
\n\u6bd4\u5982\u8fd9\u91cc
\n\"\"
\n\u5982\u679cURL\u8df3\u51fa\u8be5\u7f51\u7ad9\u5219\u4e0d\u88ab\u722c\u53d6\u3002
\n3.start_urls
\n\u5176\u5b9eURL\u5217\u8868\uff0c\u5373\u4ece\u5f53\u524d\u5217\u8868\u5f00\u59cb\u722c\u53d6\u3002
\n4.custom_setting
\n\u662f\u4e00\u4e2a\u5b57\u5178\uff0c \u662f\u4e13\u5c5e\u4e8e\u672cSpider\u7c7b\u7684\u914d\u7f6e\uff0c\u6b64\u8bbe\u7f6e\u4f1a\u8986\u76d6\u9879\u76ee\u5168\u5c40\u7684\u8bbe\u7f6e\u3002
\n\"\"
\n\u6211\u4eec\u53ef\u4ee5\u5728\u9879\u76ee\u6587\u4ef6\u4e2d\u770b\u5230settings\u6587\u4ef6\uff0c\u8fd9\u4e2a\u6587\u4ef6\u4e2d\u5b58\u653e\u4e86\u8bb8\u591a\u9ed8\u8ba4\u7684\u503c\uff0c\u6bd4\u5982\u9ed8\u8ba4\u8bf7\u6c42\u5934\u7b49\uff0c\u5982\u679c\u628a\u9ed8\u8ba4\u8bf7\u6c42\u5934\u6ce8\u89c6\u6389\u5c06\u65e0\u6cd5\u8bbf\u95ee\u7f51\u7ad9\uff0c\u4f46\u662f\u6211\u4eec\u53ef\u4ee5\u5728\u65b9\u6cd5\u4e2d\u4f7f\u7528custom_setting\uff0c\u6765\u8986\u76d6\u6216\u8005\u4ee3\u66ffsetting\uff0c\u4f7f\u722c\u866b\u53ef\u4ee5\u8bbf\u95ee\u76ee\u6807\u7f51\u7ad9\u3002<\/p>\n
# -*- coding: utf-8 -*-\nimport scrapy\nclass ZhihuSpider(scrapy.Spider):\n    name = 'zhihu'\n    allowed_domains = ['www.zhihu.com']\n    start_urls = ['http:\/\/www.zhihu.com\/']\n    custom_settings = {\n        'DEFAULT_REQUEST_HEADERS': {\n            'user-agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko\/20100101 Firefox\/61.0',\n            'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',\n        }\n    }\n    def parse(self, response):\n        pass\n<\/pre>\n
 
\n5.crawler
\n\u5b83\u7531from_crawler\u65b9\u6cd5\u8bbe\u7f6e\uff0c\u4ee3\u8868\u7684\u662f\u672cSpider\u7c7b\u5bf9\u5e94\u7684Crawler\u5bf9\u8c61\uff0c\u5229\u7528\u5b83\u6211\u4eec\u53ef\u4ee5\u83b7\u53d6\u9879\u76ee\u7684\u4e00\u4e9b\u914d\u7f6e\u4fe1\u606f\uff0c\u5982piplines\u4e2d\uff1a
\n\"\"
\n6.start_requests
\n\u6b64\u65b9\u6cd5\u7528\u4e8e\u58f0\u79f0\u521d\u59cb\u8bf7\u6c42\uff0c\u4ed6\u5fc5\u987b\u8fd4\u56de\u4e00\u4e2a\u53ef\u8fed\u4ee3\u5bf9\u8c61\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u6b64\u65b9\u6cd5\u66f4\u6539\u8bbf\u95ee\u65b9\u5f0f\u3002
\n\u4f8b\u5982\u6211\u4eec\u5982\u679c\u4e0d\u52a0\u8fd9\u4e2a\u65b9\u6cd5\u8bbf\u95eepost\u7684\u65f6\u5019\uff0c\u5219\u4f1a\u8fd4\u56de\u5f02\u5e38\u72b6\u6001\u7801\uff0c\u4f46\u662f\u52a0\u4e86\u8be5\u65b9\u6cd5\u5e76\u52a0\u4e86\u4e00\u4e2a\u89e3\u6790\u51fd\u6570\uff0c\u6211\u4eec\u53ef\u4ee5\u770b\u89c1\u6b63\u786e\u7684\u8bbf\u95ee\u4e86\u9875\u9762\uff0c\u5e76\u6b63\u786e\u6267\u884c\u4e86\u89e3\u6790\u51fd\u6570\u3002
\n\"\"
\n\"\"
\n7.make_resquests_from_url
\n\u66f4\u6539\u56de\u8c03\u51fd\u6570\uff08\u9ed8\u8ba4parse\uff09<\/p>\n
# -*- coding: utf-8 -*-\nimport scrapy\nclass BaiduSpider(scrapy.Spider):\n    name = 'baidu'\n    allowed_domains = ['www.baidu.com']\n    start_urls = ['http:\/\/www.baidu.com\/']\n    def make_requests_from_url(self, url):\n        return scrapy.Request(url=url, callback=self.parse_index)\n    def parse_index(self, response):\n        print(\"Baidu\", response.status)\n    def parse(self, response):\n        pass\n<\/pre>\n
Item pipeline \u7684\u7528\u6cd5\uff1a<\/h4>\n
\u9879\u76ee\u7ba1\u9053\uff0c\u6570\u636e\u6e05\u6d17\u3001\u68c0\u67e5\u722c\u53d6\u5b57\u6bb5\uff0c\u67e5\u91cd\u5e76\u5b58\u5165\u6570\u636e\u5e93\u3002
\n\u6211\u4eec\u53ef\u4ee5\u81ea\u5b9a\u4e49item pipeline\uff0c\u53ea\u9700\u8981\u5b9e\u73b0\u6307\u5b9a\u7684\u65b9\u6cd5\uff0c\u5176\u4e2d\u5fc5\u987b\u8981\u5b9e\u73b0\u7684\u4e00\u4e2a\u65b9\u6cd5\u662fprocess_item(item, spider)
\n\u5176\u4e2d
\nitem \u662fItem\u5bf9\u8c61\uff0c\u5373\u88ab\u5904\u7406\u7684\u5bf9\u8c61\uff0c\u7531parse\uff08\uff09\u751f\u6210\u3002
\nspider\u662fSpider\u5bf9\u8c61\uff0c\u5373\u751f\u6210\u8be5item\u7684Spider\u3002
\n\u8fd8\u6709\u4e00\u4e9b\u5176\u4ed6\u7684\u65b9\u6cd5\uff1a
\nopen_spider(spider)\uff1aSpider\u5f00\u542f\u7684\u65f6\u5019\u88ab\u8c03\u7528\u3002
\nclose_spider(spider)\uff1aSpider\u5173\u95ed\u7684\u65f6\u5019\u88ab\u8c03\u7528\u3002
\nfrom_crawler(cls,crawler)\uff1a\u662f\u4e00\u4e2a\u7c7b\u65b9\u6cd5\uff0c\u7528@classmethod\u8fdb\u884c\u6807\u8bc6\uff0c\u662f\u4e00\u79cd\u4f9d\u8d56\u6ce8\u5165\u7684\u65b9\u5f0f\u3002\u4e00\u822c\u6765\u83b7\u53d6\u4e00\u4e9b\u914d\u7f6e\u4fe1\u606f\uff0c\u8bbe\u7f6e\u7b49\u3002
\n\u6211\u4eec\u53ef\u4ee5\u5728\u6784\u9020\u51fd\u6570\u4e2d\u8bbe\u7f6e\u4e00\u4e2a\u96c6\u5408\u7684set()\u6765\u8fdb\u884c\u6570\u636e\u53bb\u91cd\uff0c\u5176\u4e2dset()\u8fd4\u56de\u7684\u5c31\u662f\u6570\u636e\u7684\u96c6\u5408
\nself.ids_seen = set()
\n\u6211\u4eec\u8fd8\u53ef\u4ee5\u5728setting\u4e2d\u8bbe\u7f6e\u4f18\u5148\u7ea7\uff08\u6570\u5b57\uff080~1000\uff09\u8d8a\u5c0f\uff0c\u4f18\u5148\u7ea7\u8d8a\u9ad8\uff09\u6765\u4f7f\u7528item pipeline<\/p>\n
ITEM_PIPELINES = {\n    'tutorial.pipelines.TutorialPipeline': 300,\n    'tutorial.pipelines.MongoPipeline': 400\n}<\/pre>\n
 
\n 
\n 
\n 
\n 
\n 
\n 
\n.<\/p>\n","protected":false},"excerpt":{"rendered":"
\u672c\u9875\u4ee3\u7801\u53ef\u4ee5\u5728\u8fd9\u91cc\u4e0b\u8f7d\u3002 \u5982\u679c\u65e0\u6cd5\u542f\u52a8Scrapy\u79fb\u6b65\u8fd9\u91cc\u3002 PySpider\u548cScrapy\u7684\u533a\u522b\uff1a […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_mi_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[12],"tags":[],"views":4527,"_links":{"self":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/posts\/1147"}],"collection":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/comments?post=1147"}],"version-history":[{"count":0,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/posts\/1147\/revisions"}],"wp:attachment":[{"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/media?parent=1147"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/categories?post=1147"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/www.sniper97.cn\/index.php\/wp-json\/wp\/v2\/tags?post=1147"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}