import scrapy<\/p>\nclass MySpider(scrapy.Spider):<\/p>\n
name = 'myspider'<\/p>\n
start_urls = ['http:\/\/example.com']<\/p>\n
def parse(self, response):<\/p>\n
for href in response.css('a::attr(href)').getall():<\/p>\n
yield response.follow(href, self.parse)<\/p>\n
yield {<\/p>\n
'title': response.css('title::text').get(),<\/p>\n
'url': response.url,<\/p>\n
}<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5728\u8fd9\u4e2a\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u5b9a\u4e49\u4e86\u4e00\u4e2a\u722c\u866b\u7c7bMySpider<\/code>\uff0c\u6307\u5b9a\u4e86\u8d77\u59cbURL\uff0c\u5e76\u5728parse()<\/code>\u65b9\u6cd5\u4e2d\u5b9a\u4e49\u4e86\u63d0\u53d6\u6570\u636e\u7684\u903b\u8f91\u3002<\/p>\n<\/p>\n\n- \u8fd0\u884c\u722c\u866b<\/strong><\/li>\n<\/ol>\n
\u5b8c\u6210\u722c\u866b\u4ee3\u7801\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fd0\u884c\u722c\u866b\uff1a<\/p>\n<\/p>\n
scrapy crawl myspider<\/p>\n<\/code><\/pre>\n<\/p>\n
Scrapy\u4f1a\u81ea\u52a8\u5904\u7406\u8bf7\u6c42\u3001\u89e3\u6790\u54cd\u5e94\uff0c\u5e76\u5c06\u63d0\u53d6\u7684\u6570\u636e\u8f93\u51fa\u5230\u63a7\u5236\u53f0\u6216\u5b58\u50a8\u5230\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n
\u4e94\u3001\u6570\u636e\u5b58\u50a8\u4e0e\u5904\u7406<\/p>\n<\/p>\n
\u5728\u5b8c\u6210\u6570\u636e\u6293\u53d6\u540e\uff0c\u6211\u4eec\u901a\u5e38\u9700\u8981\u5bf9\u6570\u636e\u8fdb\u884c\u5b58\u50a8\u548c\u5904\u7406\u3002Python\u63d0\u4f9b\u4e86\u591a\u79cd\u6570\u636e\u5b58\u50a8\u65b9\u5f0f\uff0c\u5305\u62ec\u672c\u5730\u6587\u4ef6\u5b58\u50a8\u3001\u6570\u636e\u5e93\u5b58\u50a8\u7b49\u3002<\/p>\n<\/p>\n
\n- \u5b58\u50a8\u5230\u672c\u5730\u6587\u4ef6<\/strong><\/li>\n<\/ol>\n
\u6211\u4eec\u53ef\u4ee5\u5c06\u6293\u53d6\u7684\u6570\u636e\u5b58\u50a8\u5230CSV\u3001JSON\u3001Excel\u7b49\u683c\u5f0f\u7684\u672c\u5730\u6587\u4ef6\u4e2d\u3002Python\u5185\u7f6e\u7684csv<\/code>\u548cjson<\/code>\u6a21\u5757\uff0c\u4ee5\u53ca\u7b2c\u4e09\u65b9\u5e93pandas<\/code>\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u65b9\u4fbf\u5730\u8fdb\u884c\u6570\u636e\u5b58\u50a8\u3002<\/p>\n<\/p>\nimport csv<\/p>\ndata = [<\/p>\n
{'title': 'Example', 'url': 'http:\/\/example.com'},<\/p>\n
# \u66f4\u591a\u6570\u636e<\/p>\n
]<\/p>\n
\u5b58\u50a8\u5230CSV\u6587\u4ef6<\/strong><\/h2>\nwith open('data.csv', 'w', newline='', encoding='utf-8') as csvfile:<\/p>\n
fieldnames = ['title', 'url']<\/p>\n
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)<\/p>\n
writer.writeheader()<\/p>\n
for item in data:<\/p>\n
writer.writerow(item)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\n- \u5b58\u50a8\u5230\u6570\u636e\u5e93<\/strong><\/li>\n<\/ol>\n
\u5bf9\u4e8e\u5927\u89c4\u6a21\u6570\u636e\uff0c\u6211\u4eec\u53ef\u4ee5\u9009\u62e9\u5c06\u5176\u5b58\u50a8\u5230\u5173\u7cfb\u578b\u6570\u636e\u5e93\uff08\u5982MySQL\u3001PostgreSQL\uff09\u6216NoSQL\u6570\u636e\u5e93\uff08\u5982MongoDB\uff09\u4e2d\u3002Python\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u6570\u636e\u5e93\u8fde\u63a5\u5e93\uff0c\u5982pymysql<\/code>\u3001psycopg2<\/code>\u3001pymongo<\/code>\u7b49\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5b9e\u73b0\u6570\u636e\u7684\u5b58\u50a8\u548c\u67e5\u8be2\u3002<\/p>\n<\/p>\nimport pymysql<\/p>\n\u8fde\u63a5\u5230\u6570\u636e\u5e93<\/strong><\/h2>\nconnection = pymysql.connect(<\/p>\n
host='localhost',<\/p>\n
user='user',<\/p>\n
password='passwd',<\/p>\n
db='database',<\/p>\n
charset='utf8mb4',<\/p>\n
cursorclass=pymysql.cursors.DictCursor<\/p>\n
)<\/p>\n
try:<\/p>\n
with connection.cursor() as cursor:<\/p>\n
# \u521b\u5efa\u8868<\/p>\n
sql = "CREATE TABLE IF NOT EXISTS `webdata` (`id` int(11) NOT NULL AUTO_INCREMENT, `title` varchar(255), `url` varchar(255), PRIMARY KEY (`id`))"<\/p>\n
cursor.execute(sql)<\/p>\n
# \u63d2\u5165\u6570\u636e<\/p>\n
sql = "INSERT INTO `webdata` (`title`, `url`) VALUES (%s, %s)"<\/p>\n
cursor.execute(sql, ('Example', 'http:\/\/example.com'))<\/p>\n
connection.commit()<\/p>\n
finally:<\/p>\n
connection.close()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u7684\u4ecb\u7ecd\u548c\u793a\u4f8b\uff0c\u76f8\u4fe1\u60a8\u5df2\u7ecf\u5bf9Python\u5982\u4f55\u91c7\u96c6\u7f51\u9875\u4fe1\u606f\u6709\u4e86\u4e00\u4e2a\u5168\u9762\u7684\u4e86\u89e3\u3002\u65e0\u8bba\u662f\u7b80\u5355\u7684\u9759\u6001\u7f51\u9875\uff0c\u8fd8\u662f\u590d\u6742\u7684\u52a8\u6001\u7f51\u9875\uff0cPython\u90fd\u80fd\u63d0\u4f9b\u9ad8\u6548\u3001\u7075\u6d3b\u7684\u89e3\u51b3\u65b9\u6848\u6765\u5e2e\u52a9\u6211\u4eec\u5b9e\u73b0\u6570\u636e\u91c7\u96c6\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n \u5982\u4f55\u4f7f\u7528Python\u5e93\u8fdb\u884c\u7f51\u9875\u4fe1\u606f\u91c7\u96c6\uff1f<\/strong>
Python\u63d0\u4f9b\u4e86\u591a\u4e2a\u5f3a\u5927\u7684\u5e93\u6765\u8fdb\u884c\u7f51\u9875\u4fe1\u606f\u91c7\u96c6\uff0c\u4f8b\u5982Beautiful Soup\u3001Requests\u548cScrapy\u3002Requests\u5e93\u7528\u4e8e\u53d1\u9001HTTP\u8bf7\u6c42\u5e76\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\uff0c\u800cBeautiful Soup\u5219\u53ef\u4ee5\u8f7b\u677e\u89e3\u6790HTML\u548cXML\u6587\u6863\uff0c\u63d0\u53d6\u6240\u9700\u7684\u4fe1\u606f\u3002Scrapy\u662f\u4e00\u4e2a\u5168\u9762\u7684\u722c\u866b\u6846\u67b6\uff0c\u9002\u5408\u8fdb\u884c\u590d\u6742\u7684\u7f51\u9875\u91c7\u96c6\u4efb\u52a1\u3002\u7528\u6237\u53ef\u4ee5\u6839\u636e\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u5e93\u6216\u6846\u67b6\u6765\u5b9e\u73b0\u4fe1\u606f\u91c7\u96c6\u3002<\/p>\n\u5728\u91c7\u96c6\u7f51\u9875\u65f6\u9700\u8981\u6ce8\u610f\u54ea\u4e9b\u6cd5\u5f8b\u548c\u9053\u5fb7\u95ee\u9898\uff1f<\/strong>
\u7f51\u9875\u4fe1\u606f\u91c7\u96c6\u9700\u8981\u9075\u5faa\u4e00\u5b9a\u7684\u6cd5\u5f8b\u548c\u9053\u5fb7\u89c4\u8303\u3002\u7528\u6237\u5e94\u786e\u4fdd\u9075\u5faa\u7f51\u7ad9\u7684robots.txt\u6587\u4ef6\u89c4\u5b9a\uff0c\u907f\u514d\u8fc7\u4e8e\u9891\u7e41\u7684\u8bf7\u6c42\u5bfc\u81f4\u670d\u52a1\u5668\u8d1f\u62c5\u8fc7\u91cd\u3002\u6b64\u5916\uff0c\u91c7\u96c6\u7684\u5185\u5bb9\u5e94\u907f\u514d\u4fb5\u72af\u7248\u6743\uff0c\u6700\u597d\u5728\u4f7f\u7528\u91c7\u96c6\u6570\u636e\u65f6\u6ce8\u660e\u6765\u6e90\u6216\u83b7\u53d6\u6388\u6743\u3002\u4e86\u89e3\u5e76\u5c0a\u91cd\u7f51\u7ad9\u7684\u4f7f\u7528\u6761\u6b3e\u5bf9\u4e8e\u5408\u6cd5\u548c\u9053\u5fb7\u7684\u4fe1\u606f\u91c7\u96c6\u81f3\u5173\u91cd\u8981\u3002<\/p>\n\u5982\u4f55\u5904\u7406\u52a8\u6001\u7f51\u9875\u7684\u5185\u5bb9\u91c7\u96c6\uff1f<\/strong>
\u52a8\u6001\u7f51\u9875\u901a\u5e38\u4f7f\u7528JavaScript\u751f\u6210\u5185\u5bb9\uff0c\u4f20\u7edf\u7684HTML\u89e3\u6790\u65b9\u6cd5\u53ef\u80fd\u65e0\u6cd5\u83b7\u53d6\u6240\u9700\u4fe1\u606f\u3002\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\uff0c\u53ef\u4ee5\u4f7f\u7528Selenium\u7b49\u5de5\u5177\uff0c\u5b83\u53ef\u4ee5\u6a21\u62df\u6d4f\u89c8\u5668\u884c\u4e3a\uff0c\u52a0\u8f7dJavaScript\u751f\u6210\u7684\u5185\u5bb9\u3002\u901a\u8fc7Selenium\uff0c\u7528\u6237\u53ef\u4ee5\u5b9e\u73b0\u81ea\u52a8\u5316\u6d4b\u8bd5\u548c\u4fe1\u606f\u91c7\u96c6\uff0c\u8bbf\u95ee\u52a8\u6001\u52a0\u8f7d\u7684\u6570\u636e\u3002\u6b64\u5916\uff0c\u4f7f\u7528API\uff08\u5982\u679c\u7f51\u7ad9\u63d0\u4f9b\uff09\u4e5f\u662f\u83b7\u53d6\u52a8\u6001\u5185\u5bb9\u7684\u6709\u6548\u65b9\u5f0f\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u91c7\u96c6\u7f51\u9875\u4fe1\u606f\u7684\u65b9\u6cd5\u4e3b\u8981\u6709\uff1a\u4f7f\u7528requests\u5e93\u83b7\u53d6\u7f51\u9875\u5185\u5bb9\u3001\u5229\u7528BeautifulSoup\u5e93\u89e3\u6790 […]","protected":false},"author":3,"featured_media":1008054,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1008019"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1008019"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1008019\/revisions"}],"predecessor-version":[{"id":1008059,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1008019\/revisions\/1008059"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1008054"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1008019"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1008019"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1008019"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"Python\u5982\u4f55\u91c7\u96c6\u7f51\u9875\u4fe1\u606f\"](\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/25083501\/77e80fa5-5a67-4204-bb08-76338596b2b5.webp\")
<\/p>\n