{"id":865,"date":"2021-01-28T05:37:57","date_gmt":"2021-01-27T21:37:57","guid":{"rendered":"https:\/\/byy3.com\/?p=865"},"modified":"2021-01-28T05:41:01","modified_gmt":"2021-01-27T21:41:01","slug":"python%e5%ae%9e%e4%be%8b%e7%88%ac%e5%8f%96%e7%bd%91%e7%ab%99%e6%89%80%e6%9c%89url%e9%93%be%e6%8e%a5","status":"publish","type":"post","link":"https:\/\/byy3.com\/?p=865","title":{"rendered":"python\u5b9e\u4f8b\u722c\u53d6\u7f51\u7ad9\u6240\u6709url\u94fe\u63a5"},"content":{"rendered":"<pre><code class=\"language-python\">import re\nimport requests\n\n# \u83b7\u53d6\u5e76\u68c0\u9a8c\u8981\u722c\u53d6\u7684\u7f51\u7ad9\ndef url_get():\n url=input(&quot;please input the url:&quot;)\n try:\n kv={&#039;user_agent&#039;:&#039;Mozilla\/5.0&#039;}\n requests.get(url,headers=kv)\n return url\n except:\n print(&quot;your url is incorrect!!&quot;)\n return url_get()\n\n&#039;&#039;&#039;\n\u627e\u51faurl\u4e2d\u7684\u57df\u540d\n\u6bd4\u5982\u4ecehttps:\/\/www.xiaogeng.top\/article\/page\/id=3\u7b5b\u9009\u51fawww.xiaogeng.top\n&#039;&#039;&#039;\ndef url_same(url):\n\n #\u5224\u65ad\u8f93\u5165\u7684\u7f51\u7ad9\u4f7f\u7528\u7684\u662fhttps\u8fd8\u662fhttp\n urlprotocol=re.findall(r&#039;.*(?=:\/\/)&#039;,url)[0]\n print(&#039;\u8be5\u7ad9\u4f7f\u7528\u7684\u534f\u8bae\u662f\uff1a&#039; + urlprotocol)\n\n if len(re.findall(r&#039;\/&#039;,url)) &gt;2:\n if urlprotocol==&#039;https&#039;:\n sameurl = re.findall(r&#039;(?&lt;=https:\/\/).*?(?=\/)&#039;, url)[0]\n else:\n sameurl = re.findall(r&#039;(?&lt;=http:\/\/).*?(?=\/)&#039;, url)[0]\n else:\n url = url + &#039;\/&#039;\n if urlprotocol==&#039;https&#039;:\n sameurl = re.findall(r&#039;(?&lt;=https:\/\/).*?(?=\/)&#039;,url)[0]\n else:\n sameurl = re.findall(r&#039;(?&lt;=http:\/\/).*?(?=\/)&#039;,url)[0]\n\n print(&#039;\u57df\u540d\u5730\u5740\uff1a&#039; + sameurl)\n return sameurl\n\n# \u722c\u53d6url\u9875\u9762\u4e2d\u7684\u6240\u6709\u94fe\u63a5\ndef spiderpage(url):\n kv={&#039;user_agent&#039;:&#039;Mozilla\/5.0&#039;}\n r=requests.get(url,headers=kv)\n r.encoding=r.apparent_encoding\n pagetext=r.text\n pagelinks = re.findall(r&#039;(?&lt;=href=\\&quot;).*?(?=\\&quot;)|(?&lt;=href=\\&#039;).*?(?=\\&#039;)&#039;,pagetext)\n return pagelinks\n\n#\u7b5b\u9009pagelinks\u4e2d\u7684url\ndef url_filtrate(pagelinks):\n &#039;&#039;&#039;\n print(&quot;\u6211\u73b0\u5728\u5728\u7b5b\u9009&quot;)\n &#039;&#039;&#039;\n #\u53bb\u9664\u4e0d\u662f\u8be5\u7ad9\u70b9\u7684url\n same_target_url = []\n for l in pagelinks:\n if re.findall(sameurl,l):\n same_target_url.append(l)\n #\u53bb\u9664\u91cd\u590durl\n unrepect_url = []\n for l in same_target_url:\n if l not in unrepect_url:\n unrepect_url.append(l)\n return unrepect_url\n#\u5c06\u4e00\u4e2a\u5217\u8868\u5199\u5165\u6587\u4ef6\ndef writetofile(list):\n file=open(&#039;urls.txt&#039;,&#039;w&#039;)\n for url in list:\n file.write(url)\n file.write(&#039;\\n&#039;)\n file.close() \n\n# url\u96c6\u5408\uff0c\u5faa\u73af\u904d\u5386\u4f1a\u7528\u5230\nclass linkQuence:\n def __init__(self):\n #\u5df2\u8bbf\u95ee\u7684url\u96c6\u5408\n self.visited=[]\n #\u5f85\u8bbf\u95ee\u7684url\u96c6\u5408\n self.unvisited=[]\n #\u83b7\u53d6\u8bbf\u95ee\u8fc7\u7684url\u961f\u5217\n def getvisitedurl(self):\n return self.visited\n #\u83b7\u53d6\u672a\u8bbf\u95ee\u7684url\u961f\u5217\n def getunvisitedurl(self):\n return self.unvisited\n #\u6dfb\u52a0url\u5230\u8bbf\u95ee\u8fc7\u5f97\u961f\u5217\u4e2d\n def addvisitedurl(self,url):\n return self.visited.append(url)\n #\u79fb\u9664\u8bbf\u95ee\u8fc7\u5f97url\n def removevisitedurl(self,url):\n return self.visited.remove(url)\n #\u4ece\u672a\u8bbf\u95ee\u961f\u5217\u4e2d\u53d6\u4e00\u4e2aurl\n def unvisitedurldequence(self):\n try:\n return self.unvisited.pop()\n except:\n return None\n #\u6dfb\u52a0url\u5230\u672a\u8bbf\u95ee\u7684\u961f\u5217\u4e2d\n def addunvisitedurl(self,url):\n if url!=&quot;&quot; and url not in self.visited and url not in self.unvisited:\n return self.unvisited.insert(0,url)\n #\u83b7\u5f97\u5df2\u8bbf\u95ee\u7684url\u6570\u76ee\n def getvisitedurlount(self):\n return len(self.visited)\n #\u83b7\u5f97\u672a\u8bbf\u95ee\u7684url\u6570\u76ee\n def getunvistedurlcount(self):\n return len(self.unvisited)\n #\u5224\u65ad\u672a\u8bbf\u95ee\u7684url\u961f\u5217\u662f\u5426\u4e3a\u7a7a\n def unvisitedurlsempty(self):\n return len(self.unvisited)==0\n\n# \u771f\u6b63\u7684\u722c\u53d6\u51fd\u6570\nclass Spider():\n def __init__(self,url):\n self.linkQuence = linkQuence() #\u5f15\u5165linkQuence\u7c7b\n self.linkQuence.addunvisitedurl(url) #\u5e76\u5c06\u9700\u8981\u722c\u53d6\u7684url\u6dfb\u52a0\u8fdblinkQuence\u5bf9\u5217\u4e2d\n\n def crawler(self):\n while not self.linkQuence.unvisitedurlsempty():# \u82e5\u672a\u8bbf\u95ee\u961f\u5217\u975e\u7a7a\n print(&quot;\u5600\u5600\u5600\u6211\u53c8\u722c\u5230\u4e00\u4e2a&quot;)\n visitedurl = self.linkQuence.unvisitedurldequence()# \u53d6\u4e00\u4e2aurl\n if visitedurl is None or visitedurl == &#039;&#039;:\n continue\n initial_links=spiderpage(visitedurl) # \u722c\u51fa\u8be5url\u9875\u9762\u4e2d\u6240\u6709\u7684\u94fe\u63a5\n right_links = url_filtrate(initial_links) # \u7b5b\u9009\u51fa\u5408\u683c\u7684\u94fe\u63a5\n self.linkQuence.addvisitedurl(visitedurl) # \u5c06\u8be5url\u653e\u5230\u8bbf\u95ee\u8fc7\u7684url\u961f\u5217\u4e2d\n for link in right_links: # \u5c06\u7b5b\u9009\u51fa\u7684\u94fe\u63a5\u653e\u5230\u672a\u8bbf\u95ee\u961f\u5217\u4e2d\n self.linkQuence.addunvisitedurl(link)\n # print(self.linkQuence.visited)\n print(&quot;\u54e5\u6211\u722c\u5b8c\u4e86&quot;)\n return self.linkQuence.visited\n\nif __name__ == &#039;__main__&#039;:\n url=url_get()\n sameurl=url_same(url)\n spider=Spider(url)\n urllist=spider.crawler()\n writetofile(urllist)<\/code><\/pre>\n<p>\u722c\u53d6\u7f51\u7ad9\u7684\u6240\u6709\u94fe\u63a5url<br \/>\n<img decoding=\"async\" data-original=\"https:\/\/byy3.com\/wp-content\/uploads\/2021\/01\/2021012721404985.png\" src=\"https:\/\/byy3.com\/wp-content\/themes\/MNews%20V2.4\/images\/post-loading.gif\" title=\"python\u5b9e\u4f8b\u722c\u53d6\u7f51\u7ad9\u6240\u6709url\u94fe\u63a5\u63d2\u56fe\" alt=\"python\u5b9e\u4f8b\u722c\u53d6\u7f51\u7ad9\u6240\u6709url\u94fe\u63a5\u63d2\u56fe\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>import re import requests # \u83b7\u53d6\u5e76\u68c0\u9a8c\u8981\u722c\u53d6\u7684\u7f51\u7ad9 def url_get(): [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[33,402,352,51],"class_list":["post-865","post","type-post","status-publish","format-standard","hentry","category-python","tag-python","tag-python-scrapy"],"_links":{"self":[{"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/posts\/865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=865"}],"version-history":[{"count":0,"href":"https:\/\/byy3.com\/index.php?rest_route=\/wp\/v2\/posts\/865\/revisions"}],"wp:attachment":[{"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=865"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=865"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/byy3.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}