{"id":82166,"date":"2018-09-27T12:44:23","date_gmt":"2018-09-27T04:44:23","guid":{"rendered":"http:\/\/www.fagao.me\/?p=82166"},"modified":"2018-09-27T12:44:23","modified_gmt":"2018-09-27T04:44:23","slug":"python%e7%88%ac%e8%99%ab%e5%ae%9e%e6%88%98%e7%b3%bb%e5%88%974%e7%88%ac%e5%8f%96%e7%99%be%e5%ba%a6%e6%96%b0%e9%97%bb%e5%8f%91%e7%a8%bf%e4%bf%a1%e6%81%af","status":"publish","type":"post","link":"https:\/\/www.fagao.me\/p\/82166.htm","title":{"rendered":"Python\u722c\u866b\u5b9e\u6218\u7cfb\u52174\u722c\u53d6\u767e\u5ea6\u65b0\u95fb\u53d1\u7a3f\u4fe1\u606f"},"content":{"rendered":"

\"\"<\/p>\n

\u6b22\u8fce\u5927\u5bb6\u5173\u6ce8\u516c\u4f17\u53f7\u3010\u54c8\u5e0c\u5927\u6570\u636e\u3011<\/span><\/span><\/p>\n

\u524d\u9762\u6211\u4eec\u5df2\u7ecf\u4ecb\u7ecd\u4e86scrapy\u7684\u5b89\u88c5\u3001\u5165\u95e8\u6559\u7a0b\uff0c\u4ee5\u53caMongoDB\u7684\u5b89\u88c5\u4e0e\u914d\u7f6e\uff0c\u672c\u7bc7\u5c06\u5206\u4eab\u5982\u4f55\u5229\u7528scrapy\u722c\u53d6\u767e\u5ea6\u65b0\u95fb\u4fe1\u606f\uff0c\u5e76\u5c06\u722c\u53d6\u5230\u7684\u6570\u636e\u5b58\u50a8\u5230MongoDB\u6570\u636e\u5e93\u4e2d\u3002<\/span><\/p>\n

\u6293\u53d6\u76ee\u6807<\/span><\/p>\n

\u901a\u8fc7\u7ed9\u5b9a\u5173\u952e\u5b57\uff0c\u722c\u53d6\u767e\u5ea6\u65b0\u95fb\u4e2d\u641c\u7d22\u5230\u7684\u6240\u6709\u6709\u5173\u65b0\u95fb\u4fe1\u606f\uff0c\u65b0\u95fb\u6807\u9898\u3001\u65b0\u95fb\u94fe\u63a5\u3001\u65b0\u95fb\u6765\u6e90\u3002<\/span><\/p>\n

\u6280\u672f\u8def\u7ebf<\/span><\/p>\n

\u5229\u7528scrapy\u6846\u67b6\u5b9e\u73b0\u6b64\u6b21\u722c\u53d6\uff0c\u5229\u7528parse\u51fd\u6570\u83b7\u5f97\u9700\u8981\u6293\u53d6\u7684\u4fe1\u606f\uff0c\u901a\u8fc7items\u548cpiplinepipelines\u7684\u8bbe\u7f6e\u5b9e\u73b0\u6570\u636e\u5b58\u50a8\u5230MongoDB\u6570\u636e\u5e93\u4e2d\uff0c\u901a\u8fc7middleware\u8bbe\u7f6euser_agent\u964d\u4f4e\u7f51\u7ad9\u5bf9\u722c\u866b\u7684\u9650\u5236\uff0c\u4f7f\u5f97\u722c\u53d6\u901f\u5ea6\u53ef\u5728\u4e00\u4e2a\u8f83\u9ad8\u7684\u6c34\u5e73\u4e0a\u3002<\/span><\/p>\n

\u76ee\u6807\u7ad9\u70b9\u5206\u6790<\/span><\/p>\n

Python\u722c\u866b\u5b9e\u6218\u7cfb\u5217\uff083\uff09\u4e2d\u5df2\u7ecf\u4ecb\u7ecd\u4e86\u5982\u4f55\u5229\u7528chrome\u6d4f\u89c8\u5668\u83b7\u53d6\u5bf9\u5e94\u6807\u7b7e\u7684XPATH\u6216CSS\u8def\u5f84\uff0c\u672c\u6b21\u83b7\u53d6\u65b0\u95fb\u4fe1\u606f\uff0c\u91c7\u7528\u7684\u89e3\u6790\u65b9\u5f0f\u662fCSS\u3002<\/span><\/p>\n

\u7a0b\u5e8f\u7684\u7ed3\u6784\u8bbe\u8ba1<\/span><\/p>\n

\u6b65\u9aa41\uff1a\u6253\u5f00\u547d\u4ee4\u884c\u7a97\u53e3\uff0c\u8fdb\u5165\u60f3\u65b0\u5efa\u9879\u76ee\u7684\u76ee\u5f55<\/span><\/p>\n

\u6b65\u9aa42\uff1a\u5728\u547d\u4ee4\u884c\u4e2d\u8f93\u5165\uff1ascrapy startproject xxxx(\u9879\u76ee\u540d\u79f0) \u65b0\u5efa\u4e00\u4e2a\u9879\u76ee<\/span><\/p>\n

\u6b65\u9aa43\uff1a\u8fdb\u5165\u9879\u76ee\u6587\u4ef6\uff0c\u5728\u547d\u4ee4\u884c\u4e2d\u8f93\u5165\uff1ascrapy genspider <\u722c\u866b\u540d\u79f0> <\u722c\u53d6\u7f51\u5740>\u65b0\u5efa\u722c\u866b<\/span><\/p>\n

\u6b65\u9aa43\uff1a\u66f4\u6539items.py\u6587\u4ef6\uff0c\u8bbe\u7f6eitem<\/span><\/p>\n

\u6b65\u9aa44\uff1a\u7f16\u5199\u722c\u53d6\u4ee3\u7801<\/span><\/p>\n

\u6b65\u9aa45\uff1a\u66f4\u6539pipelines\u548cmiddlewares<\/span><\/p>\n

\u6b65\u9aa46\uff1a\u542f\u52a8\u722c\u866b\uff0c\u6253\u5f00\u547d\u4ee4\u884c\u8fdb\u5165\u5230\u9879\u76ee\u76ee\u5f55\u4e0b\uff0c\u8f93\u5165\uff1ascrapy crawl <\u722c\u866b\u540d\u79f0><\/span><\/p>\n

items.py\u4ee3\u7801\u5982\u4e0b\uff1a<\/span><\/span><\/p>\n

# -*- coding: utf-8 -*-<\/span># Define here the models for your scraped items<\/span>#<\/span># See documentation in:<\/span># http:\/\/doc.scrapy.org\/en\/latest\/topics\/items.html<\/span>from scrapy import Item, Field<\/span>class mmwzItem(Item):<\/span># define the fields for your item here like:<\/span> # name = Field()<\/span> article_title = Field()<\/span> article_url = Field()<\/span> article_catchroad = Field()<\/span> article_source = Field()<\/span><\/span><\/p>\n

\u672c\u4f8b\u5b50\u7684\u722c\u866b\u540d\u79f0\u4e3a\uff1axinwen\uff0c\u722c\u866b\u6587\u4ef6xinwen.py\u7684\u4ee3\u7801\u4e3a\uff1a<\/span><\/span><\/p>\n

\"\"<\/p>\n

# -*- coding: utf-8 -*-<\/span>from urllib.parse import urlencode<\/span>import re<\/span>from scrapy import Spider, Request<\/span>from scrapy_mmwz.items import mmwzItem<\/span>class XinwenSpider(Spider):<\/span>name = “xinwen”<\/span> keyword = ‘\u6bd4\u7279\u5e01’<\/span> page = 0<\/span> #\u67e5\u8a62\u4fe1\u606f<\/span> data = {<\/span> ‘word’: keyword,<\/span> ‘pn’: page,<\/span> ‘cl’: ‘2’,<\/span> ‘ct’: ‘1’,<\/span> ‘tn’: ‘news’,<\/span> ‘rn’: ’20’,<\/span> ‘ie’: ‘utf – 8’,<\/span> }<\/span> # \u751f\u6210URL\u7684\u53c2\u6570\u90e8\u5206<\/span> params = urlencode(data)<\/span> base = ‘http:\/\/news.baidu.com\/ns?’<\/span> url = base + params<\/span> allowed_domains = [“news.baidu.com”]<\/span> start_urls = [url]<\/span> def parse(self, response):<\/span> item = mmwzItem()<\/span> if response.status == 200:<\/span> news_lists = response.css(‘#wrapper_wrapper #content_left div.result’)<\/span> page_number = response.css(‘p#page strong span.pc::text’).extract_first()<\/span> # print(news_lists)<\/span> print(‘page_number:’, page_number)<\/span> if news_lists:<\/span> for news in news_lists:<\/span> # news_lists\u662f\u4e00\u4e2a\u751f\u6210\u5668\uff0c\u5728\u8c03\u7528\u51fd\u6570\u662f\u53ef\u4ee5\u7528for\u5faa\u73af\u4f9d\u6b21\u83b7\u53d6\u7ed3\u679c<\/span> lists = {<\/span> ‘article_url’: news.css(‘.c-title a::attr(href)’).extract_first(),<\/span> ‘article_title’: news.css(‘.c-title a::text’).extract_first(),<\/span> ‘article_catchroad’: ‘baidu’,<\/span> ‘article_source’: re.search(re.compile(‘(.*?)\\\\xa0’, re.S),<\/span> news.css(‘p.c-author::text’).extract_first()).group(1)<\/span> }<\/span> for field in item.fields:<\/span> if field in lists.keys():<\/span> item[field] = lists.get(field)<\/span> # \u5b83\u76f8\u5f53\u4e8ereturn\u53ea\u4e0d\u8fc7\u4e00\u6b21\u8fd4\u56de\u4e00\u4e2a<\/span> yield item<\/span> print(response.css(‘p#page a:last-child::text’).extract_first())<\/span> if response.css(‘p#page a:last-child::text’).extract_first() == ‘\u4e0b\u4e00\u9875>’:<\/span> # \u7372\u53d6\u4e0b\u4e00\u9801\u93c8\u63a5<\/span> next_page = ‘http:\/\/news.baidu.com’ + response.css(‘p#page a:last-child::attr(href)’).extract_first()<\/span> # \u5be6\u73fe\u5faa\u74b0\u7372\u53d6\u4e0b\u4e00\u9801\u5167\u5bb9<\/span> yield Request(next_page, callback=self.parse)<\/span><\/span><\/p>\n

\u901a\u8fc7pipelines\u8bbe\u7f6e\uff0c\u5c06\u722c\u53d6\u5230\u7684\u6570\u636e\u6210\u529f\u4fdd\u5b58\u5230MongoDB\u6570\u636e\u5e93\u4e2d\uff0c\u8bbe\u7f6e\u8be6\u7ec6\u4ee3\u7801\u5982\u4e0b\uff1a<\/span><\/span><\/p>\n

# -*- coding: utf-8 -*-<\/span># Define your item pipelines here<\/span>#<\/span># Don’t forget to add your pipeline to the ITEM_PIPELINES setting<\/span># See: http:\/\/doc.scrapy.org\/en\/latest\/topics\/item-pipeline.html<\/span>import pymongo<\/span>class MongoPipeline(object):<\/span>collection_name = ‘xinwen’<\/span> def __init__(self, mongo_uri, mongo_db):<\/span> self.mongo_uri = mongo_uri<\/span> self.mongo_db = mongo_db<\/span> @classmethod<\/span> def from_crawler(cls, crawler):<\/span> return cls(<\/span> mongo_uri=crawler.settings.get(‘MONGO_URI’),<\/span> mongo_db=crawler.settings.get(‘MONGO_DATABASE’, ‘items’)<\/span> )<\/span> def open_spider(self, spider):<\/span> self.client = pymongo.MongoClient(self.mongo_uri)<\/span> self.db = self.client[self.mongo_db]<\/span> def close_spider(self, spider):<\/span> self.client.close()<\/span> # def process_item(self, item, spider):<\/span> # self.db[‘user’].update({‘url_token’: item[‘url_token’]}, {‘$set’: item}, True)<\/span> #<\/span> # return item<\/span> def process_item(self, item, spider):<\/span> self.db[self.collection_name].insert(dict(item))<\/span> return item<\/span><\/span><\/p>\n

\u8fd9\u91cc\u9700\u8981\u6ce8\u610f\u4e24\u70b9\uff0c\u7b2c\u4e00\u9996\u5148\u5b89\u88c5pymongo\u5305\uff0c\u7b2c\u4e8c\u5728settings.py\u6587\u4ef6\u505a\u5982\u4e0b\u8bbe\u7f6e\uff1a<\/span><\/span><\/p>\n

MONGO_URI = ‘localhost’<\/span>MONGO_DATABASE = ‘xinwen’<\/span><\/p>\n

settings.py\u6587\u4ef6\u4e2d\u8fd8\u6709\u4e00\u4e2a\u9700\u8981\u7279\u522b\u6ce8\u610f\u7684\u662f\uff1a<\/span><\/p>\n

# Obey robots.txt rules<\/span>ROBOTSTXT_OBEY = False<\/span><\/p>\n

\u975e\u5e38\u591a\u7684\u7f51\u7ad9\u90fd\u6709robots\u534f\u8bae\uff0c\u4e0d\u5141\u8bb8\u722c\u53d6\u672c\u7f51\u7ad9\u4fe1\u606f\uff0c\u5982\u679c\u8fd9\u4e2a\u53c2\u6570\u8bbe\u7f6e\u4e3aTrue\uff0c\u975e\u5e38\u591a\u7684\u7f51\u7ad9\u90fd\u4e0d\u80fd\u722c\u53d6\u4e86\u3002<\/span><\/p>\n

\u5b8c\u6574\u9879\u76ee\u4ee3\u7801\u8bf7\u53c2\u8003\u6211\u7684GitHub\uff1a<\/span>https:\/\/github.com\/kxylxx\/scrapy_testproject<\/span><\/span><\/p>\n

\u4e3a\u4e86\u65b9\u4fbf\u67e5\u770b\u722c\u53d6\u5230\u7684\u4fe1\u606f\uff0c\u8fd9\u91cc\u7ed9\u5927\u5bb6\u63a8\u8350\u4e00\u4e2aMongoDB\u53ef\u89c6\u5316\u8f6f\u4ef6Robo 3T,\u8be6\u7ec6\u5b89\u88c5\u4f7f\u7528\u6559\u7a0b\u8bf7\u53c2\u8003\uff1ahttps:\/\/www.cnblogs.com\/dacongge\/p\/7346037.html \uff0c\u611f\u8c22\u5927\u8471\u54e5\u7684\u5206\u4eab\u3002<\/span><\/p>\n

\u7ed3\u679c\u5c55\u793a\u53ca\u5c0f\u7ed3<\/span><\/span><\/p>\n

\u83b7\u53d6\u5230\u7684\u6570\u636e\u5982\u4e0b\u56fe\u6240\u793a<\/span>\uff1a<\/span><\/p>\n

<\/div>\n

\u5c0f\u7ed3\uff1a<\/span><\/p>\n

\u901a\u8fc7\u672c\u6b21\u5b9e\u6218\u5e0c\u671b\u5927\u5bb6\u5bf9scrapy\u6846\u67b6\u6709\u66f4\u6df1\u523b\u7684\u8ba4\u8bc6\uff0c\u5e0c\u671b\u80fd\u591f\u6839\u636e\u8be5\u6848\u4f8b\u8bbe\u8ba1\u4e00\u4e2a\u57fa\u4e8escrapy\u6846\u67b6\u7684\u722c\u866b\u7a0b\u5e8f\uff0c\u4ee5\u719f\u6089\u6574\u4e2a\u722c\u53d6\u6d41\u7a0b\u3002\u5e0c\u671b\u5927\u5bb6\u80fd\u591f\u81ea\u5df1\u6572\u5199\u4ee3\u7801\uff0c\u5728\u6572\u4ee3\u7801\u7684\u8fc7\u7a0b\u4e2d\u53d1\u73b0\u95ee\u9898\u89e3\u51b3\u95ee\u9898\u3002<\/span><\/p>\n

<\/div>\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

\u6b22\u8fce\u5927\u5bb6\u5173\u6ce8\u516c\u4f17\u53f7\u3010\u54c8\u5e0c\u5927\u6570\u636e\u3011 \u524d\u9762\u6211\u4eec\u5df2\u7ecf\u4ecb\u7ecd\u4e86scrapy\u7684\u5b89\u88c5\u3001\u5165\u95e8\u6559\u7a0b\uff0c\u4ee5\u53caMongoDB\u7684\u5b89\u88c5\u4e0e\u914d […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[120],"class_list":["post-82166","post","type-post","status-publish","format-standard","hentry","category-news","tag-120"],"_links":{"self":[{"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/posts\/82166","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/comments?post=82166"}],"version-history":[{"count":0,"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/posts\/82166\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/media?parent=82166"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/categories?post=82166"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.fagao.me\/p\/wp-json\/wp\/v2\/tags?post=82166"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}