- 课堂交流区
- 帖子详情
64
回复
-
<p><code class="brush:python;toolbar:false" >import requests import time start = time.perf_counter() for i in range(100): try: r = requests.get("https://python123.io/", timeout=30) r.raise_for_status() r.encoding = r.apparent_encoding except: print("产生异常") end = time.perf_counter() print(end - start)</code>爬取https://python123.io100次耗时63.7722963s。</p>添加评论
-
<p>import time<br >import requests<br >def getHTMLtext(url):<br > try:<br > r = requests.get(url,timeout = 30)<br > r.raise_for_status()<br > r.encoding = r.apparent_encoding<br > return r.text<br > except:<br > return '产生异常'<br ><br >start = time.perf_counter()<br >if __name__ == '__main__':<br > for i in range(100):<br > url = 'https://www.fishc.com.cn'<br > getHTMLtext(url)<br > dur = time.perf_counter() - start<br > print(f'执行程序一共耗费了{dur}s')</p><p><br ></p><p>爬取鱼C工作室(https://www.fishc.com.cn)100次耗时45.1654737s</p>添加评论
-
<p>import time<br >import requests<br >def getHTML(url):<br > try:<br > r = requests.get(url, timeout=30)<br > r.raise_for_status()<br > r.encoding = r.apparent_encoding<br > return r.text<br > except:<br > return '产生异常'<br >start = time.time()<br >for i in range(100):<br > url = f'https://movie.douban.com/'<br > getHTML(url)<br >end = start = time.time()<br >print(f'time:{i}s'.format(i=end-start))</p><p><br ></p><p>运行结果 time:99s</p>添加评论
-
<p><code class="brush:python;toolbar:false" >import requests import time def getHTML(Url): try: r = requests.get(Url, timeout=30) r.raise_for_status() r.encoding = r.apparent_encoding except: print("产生异常") start = time.perf_counter() if __name__ == "__main__": for i in range(100): url = "https://www.icourse163.org" getHTML(url) end = time.perf_counter() print("爬虫100次mooc官网用时为'{}'s".format(end - start))</code></p>添加评论
-
<p>import requests</p><p>import time</p><p><br ></p><p><br ></p><p>def getHTML(Url):</p><p> try:</p><p> r = requests.get(Url, timeout=30)</p><p> r.raise_for_status()</p><p> r.encoding = r.apparent_encoding</p><p> except:</p><p> print("产生异常")</p><p><br ></p><p><br ></p><p>start = time.perf_counter()</p><p>if __name__ == "__main__":</p><p> for i in range(100):</p><p> url = "https://www.hbue.edu.cn"</p><p> getHTML(url)</p><p> end = time.perf_counter()</p><p><br ></p><p> print("爬虫100次湖北经济学院官网用时为'{}'s".format(end - start))</p><p><br ></p><p>爬虫100次湖北经济学院官网用时为'20.27549691699994's<img src="https://mooc-image.nosdn.127.net/c01ee606ff364afc8c0947b7664465aa.png" /></p>添加评论
-
<p><code class="brush:python;toolbar:false" >import requests import time def getHTMLText(url): try: r = requests.get(url,timeout = 30) r.raise_for_status() r.encoding = r.apparent_encoding return r.text except: return "产生异常" if __name__ == "__main__": url = "https://www.bilibili.com/" start_time = time.time() for i in range(100): getHTMLText(url) end_time = time.time() print("The time is :", end_time - start_time)</code>爬取B站，总用时：52.18911814689636s</p>添加评论
-
<p>import requests</p><p>import time</p><p><br ></p><p><br ></p><p>def getHtmlText(url):</p><p> try:</p><p> start_time=time.time()</p><p> hd={"user-agent":"Mozilla/5.0"}</p><p> r=requests.get(url,headers=hd,timeout=30)</p><p> r.raise_for_status()</p><p> r.encoding=r.apparent_encoding</p><p> except:</p><p> return "失败"</p><p>def main():</p><p> url="https://movie.douban.com/top250"</p><p> start_time=time.time()</p><p> for i in range(100):</p><p> getHtmlText(url)</p><p> finish_time=time.time()-start_time</p><p> print(finish_time)</p><p><br ></p><p>main()</p><p><code class="brush:python;toolbar:false" ><br ></code></p>添加评论
-
<p>import requests<br >import time<br ><br >def getHTMLText(url):<br > try:<br > r = requests.get(url, timeout=30)<br > r.raise_for_status() # 如果状态不是200，引发HTTPError异常<br > r.encoding = r.apparent_encoding<br > return r.text<br > except:<br > return "产生异常！"<br ><br >if __name__ == "__main__":<br > url = "https://www.bilibili.com"<br > start_time = time.time()<br > for i in range(100):<br > getHTMLText(url)<br > end_time = time.time()<br > print(start_time)<br > print(end_time)<br > print("爬取时间： ", end_time - start_time)<br ></p><p><br ></p><p>1679542387.7249022</p><p>1679542438.832644</p><p>爬取时间： 51.107741832733154</p><p><br ></p>添加评论
-
<p><code class="brush:python;toolbar:false" >import requests import time def HTMLtest(url): try: r=requests.get(url,timeout=30) r.encoding=r.apparent_encoding r.raise_for_status() return r.text except: return "产生异常" url="https://www.baidu.com" start_time=time.time() for i in range(100): HTMLtest(url) end_time=time.time() print("爬取百度100次需要时间：%.10f"%(end_time-start_time))</code>爬取百度100次需要时间：6.2275991440</p>添加评论
-
importrequestsimporttimedefHTMLtest(url):try:r=requests.get(url,timeout=30)r.encoding=r.apparent_encodingr.raise_for_status()returnr.textexcept:return"产生异常"url="https://www.baidu.com"start_time=time.time()foriinrange(100):HTMLtest(url)end_time=time.time()print("爬取百度100次需要时间：%.10f"%(end_time-start_time))爬取百度100次需要时间：6.2275991440添加评论
-
<p>import requests<br >import time<br ><br >def gethtmltxt(url):<br > try:<br > r = requests.get(url,timeout=30)<br > r.raise_for_status()<br > r.encoding = r.apparent_encoding<br > return r.text<br > except:<br > return "爬取异常"<br >if __name__=="__main__":<br > url = "https://www.baidu.com"<br > star = time.time()<br > for i in range(100):<br > gethtmltxt(url)<br > end = time.time()<br > print("爬取百度首页100次耗时{}秒".format(end-star))</p><p><br ></p><p>爬取百度首页100次耗时8.04139757156372秒<br ></p>添加评论
-
<p>import requests<br >import time<br >def getHTMLText(url):<br > try:<br > r = request.get(url, timeout=30)<br > r.raise_for_status()<br > r.encoding=r.apparent_encoding<br > return r.text<br > except:<br > return "产生异常"<br >start_time=time.perf_counter()<br >url="https://www.icourse163.org/"<br >for i in range(100):<br > getHTMLText(url)<br >end_time=time.perf_counter()<br >print('爬取"{}"网站100次耗时{:.6f} s。'.format(url,end_time-start_time))<br ><br ><br >爬取"https://www.icourse163.org/"网站100次耗时0.000056 s。<br ></p>添加评论
-
<p>import requests</p><p>import time</p><p>def getHTMLText(url):</p><p> try:</p><p> r=requests.get(url,timeout=30)</p><p> r.raise_for_status()</p><p> r.encoding=r.apparent_encoding</p><p> return r.text</p><p> except:</p><p> return "产生异常"</p><p>url=r'https://www.runoob.com/python3/python3-date-time.html#comment-35499'</p><p>a=time.perf_counter()</p><p>for i in range(100):</p><p> getHTMLText(url)</p><p>b=time.perf_counter()</p><p>print("爬取了{}网址一百次耗费时间{:.6f}".format(url,b-a))</p><p> </p><p><br ></p>添加评论
-
<p># -*- coding:utf-8 -*-</p><p><br ></p><p>import requests</p><p>from datetime import datetime</p><p><br ></p><p>def get_page_content(url,ii):</p><p> try:</p><p> r = requests.get(url,timeout=30)</p><p> r.raise_for_status()</p><p> r.encoding = r.apparent_encoding</p><p> return r.text</p><p> except:</p><p> return '第'+str(ii)+'次，爬取失败'</p><p><br ></p><p>def main():</p><p> url = 'https://www.csdn.net/'</p><p> print('爬取网站：'+url)</p><p><br ></p><p> t_start = datetime.now()</p><p> </p><p> for ii in range(1,101):</p><p> get_page_content(url,ii)</p><p> </p><p> t_end = datetime.now()</p><p><br ></p><p> print('爬取100次网页所需时间为',t_end-t_start)</p><p><br ></p><p>if __name__=='__main__':</p><p> main()</p><p><br ></p><p>结果：</p><p> 爬取网站：https://www.csdn.net/</p><p> 爬取100次网页所需时间为 0:02:41.812902</p>添加评论
-
<p>import requests<br >import time<br >url = 'https://baidu.com'<br >def gehttptext(url):<br > try:<br > r = requests.get(url,timeout=30)<br > r.raise_for_status()<br > r.encoding = r.encoding<br > return r.text<br > except:<br > print("error")<br >def main():<br > for i in range(1,100):<br > gehttptext(url)<br >start = time.perf_counter()<br >main()<br >end = time.perf_counter()<br >print("爬取{}网址所用的时间为{:.5f}".format(url,end-start))</p><p>结果为：19.54443s</p>添加评论
-
import requestsimport timeurl = 'https://baidu.com'def gehttptext(url): try: r = requests.get(url,timeout=30) r.raise_for_status() r.encoding = r.encoding return r.text except: print("error")def main(): for i in range(1,100): gehttptext(url)start = time.perf_counter()main()end = time.perf_counter()print("爬取{}网址所用的时间为{:.5f}".format(url,end-start))结果为：19.54443s添加评论
-
<p>try:</p><p> import time</p><p> import requests</p><p> start_time=time.perf_counter()</p><p> for i in range(100):</p><p> r=requests.get('https://www.baidu.com',timeout=30)</p><p> r.raise_for_status()</p><p> r.encoding=r.apparent_encoding</p><p> r.text</p><p> end_time=time.perf_counter()</p><p> all_time=end_time-start_time</p><p> print('成功爬取100次baidu网页首页的时间为：{:.6f}s'.format(all_time))</p><p><br ></p><p><br ></p><p>except:</p><p> print('程序异常!')</p><p>运行结果：成功爬取100次baidu网页首页的时间为：14.811744s</p>添加评论
-
<p>import requests</p><p>import time</p><p>try:</p><p> start_time = time.perf_counter()</p><p> for i in range(100):</p><p> r = requests.get("https://www.baidu.com",timeout = 30)</p><p> r.raise_for_status()</p><p> r.encoding = r.apparent_encoding</p><p> r.text</p><p> end_time = time.perf_counter()</p><p> all_time=end_time-start_time</p><p> print('成功爬取100次baidu网页首页的时间为：{}s'.format(all_time))</p><p>except:</p><p> print("程序异常")</p><p><br ></p><p>成功爬取100次baidu网页首页的时间为：10.521762099997432s</p><p><br ></p>添加评论
-
<p><code class="brush:python;toolbar:false" >import requests import time try: start_time=time.perf_counter() for i in range(100): r=requests.get("https://www.baidu.com",timeout=30) r.raise_for_status() r.encoding=r.apparent_encoding r.text end_time=time.perf_counter() all_time=end_time-start_time print("成功爬取100次百度网页首页的时间为：{}s".format(all_time)) except: print("程序异常")</code><code class="brush:python;toolbar:false" >成功爬取100次百度网页首页的时间为：11.2087748s</code></p>添加评论
-
<p>import requests<br >import time<br ><br ># 爬取bing首页100次计时<br ><br >try:<br > start_time = time.perf_counter() # 初始计时<br > for i in range(100):<br > r = requests.get("https://www.bing.com", timeout=10) # requests 在经过以 timeout 参数设定的秒数时间之后停止等待响应<br > r.raise_for_status()<br > r.encoding = r.apparent_encoding<br > r.text<br > end_time = time.perf_counter() # 末尾计时<br > all_time = end_time - start_time # 计算总时长<br > print("成功爬取100次bing网页首页的时间为：{}s".format(all_time))<br >except:<br > print("程序异常")<br ></p><p><br ></p><p>运行结果：成功爬取100次bing网页首页的时间为：42.14350469969213s</p>添加评论
1楼
2楼
3楼
4楼
5楼
6楼
7楼
8楼
9楼
10楼
11楼
12楼
13楼
14楼
15楼
16楼
17楼
18楼
19楼
20楼
点击加载更多
到底啦~
浙公网安备 33010802012594号