{"id":283,"date":"2017-02-11T23:09:40","date_gmt":"2017-02-11T15:09:40","guid":{"rendered":"http:\/\/www.91tfboys.com\/?p=283"},"modified":"2019-04-02T15:35:37","modified_gmt":"2019-04-02T07:35:37","slug":"python-%e8%8e%b7%e5%8f%96%e9%a1%b5%e9%9d%a2%e8%b6%85%e9%93%be%e6%8e%a5%e6%96%87%e5%ad%97%e5%8f%8a%e5%9c%b0%e5%9d%80","status":"publish","type":"post","link":"https:\/\/www.91tfboys.com\/?p=283","title":{"rendered":"Python \u83b7\u53d6\u9875\u9762\u8d85\u94fe\u63a5\u6587\u5b57\u53ca\u5730\u5740"},"content":{"rendered":"<p>&#8221;&#8217;<br \/>\n\u53c2\u8003\u501f\u9274\u4e86\u82e5\u5e72\u7f51\u7ad9\u6587\u7ae0<br \/>\n\u5728\u6b64\u4e00\u81f4\u81f4\u8c22<br \/>\n&#8221;&#8217;<!--more--><\/p>\n<pre>import urllib\r\nfrom HTMLParser import HTMLParser\r\n\r\nurl = \"http:\/\/www.91tfboys.com\"\r\nclass MyHTMLParser(HTMLParser):\r\n\t\"\"\"Withdraw urls from html\"\"\"\r\n\tdef __init__(self):\r\n\t\tHTMLParser.__init__(self)\r\n\t\tself.links = ''\r\n\t\tself.text = ''\r\n\t\tself.items = []\r\n\t\tself.flag = 0\r\n\tdef handle_starttag(self, tag, attrs):\r\n\t\tif tag == 'a':\r\n\t\t\tif len(attrs) == 0:\r\n\t\t\t\tpass\r\n\t\t\telse:\r\n\t\t\t\tfor (variable, value) in attrs:\r\n\t\t\t\t\tif variable == 'href':\r\n\t\t\t\t\t\tif value.startswith('\/'):\r\n\t\t\t\t\t\t\tvalue = url + value\r\n\t\t\t\t\t\tself.links = value\r\n\t\t\t\t\t\tself.flag = 1\r\n\tdef handle_data(self, data):\r\n\t\tif self.flag == 1:\r\n\t\t\tself.text = data.strip()\r\n\t\t\tself.items.append((self.text, self.links))\r\n\t\t\tself.flag = 0\r\nif __name__ == '__main__':\r\n\twebdata = urllib.urlopen(url).read()\r\n\thp = MyHTMLParser()\r\n\thp.feed(webdata)\r\n\thp.close()\r\n\tfile = file('17.txt', 'w')\r\n\tt = 0\r\n\twhile t &lt; len(hp.items):\r\n\t\tfile.write(hp.items[t][0] + hp.items[t][1] + '\\r\\n')\r\n\t\tt += 1\r\n\tfile.close()\r\n<\/pre>\n<p>&#8221;&#8217;<br \/>\n\u5fcf\u6127\u5fcf\u6127<br \/>\n\u5f04\u5230\u73b0\u5728<br \/>\n&#8221;&#8217;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&#8221;&#8217; \u53c2\u8003\u501f\u9274\u4e86\u82e5\u5e72\u7f51\u7ad9\u6587\u7ae0 \u5728\u6b64\u4e00\u81f4\u81f4\u8c22 &#8221;&#8217;<\/p>\n","protected":false},"author":1,"featured_media":284,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[18,19],"class_list":["post-283","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-coding","tag-python","tag-19"],"_links":{"self":[{"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/posts\/283","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=283"}],"version-history":[{"count":2,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/posts\/283\/revisions"}],"predecessor-version":[{"id":286,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/posts\/283\/revisions\/286"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=\/wp\/v2\/media\/284"}],"wp:attachment":[{"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=283"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=283"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.91tfboys.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=283"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}