1 files changed, 116 insertions, 0 deletions
diff --git a/homepageAve.py b/homepageAve.py
new file mode 100644
index 0000000..7ea4726
--- /dev/null
+++ b/homepageAve.py
@@ -0,0 +1,116 @@
+# 首页ipv6访问成功率和时延  成功率可以用requests，访问时延用selenium
+import requests
+from selenium import webdriver
+from selenium.webdriver.chrome.options import Options
+import time
+from tqdm import tqdm
+import csv
+from multiprocessing import Process, Lock
+
+
+# 单页面访问是否成功, 返回是状态码
+def page_status(url):
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE'}
+    try:
+        r = requests.get(url, headers=headers, verify=False, timeout=10)
+        status = r.status_code
+    except Exception:
+        status = 404
+    return status
+
+
+# 单页面单次访问加载时间
+def page_time(url):
+    opts = Options()
+    opts.headless = True
+    driver = webdriver.Chrome(options=opts)
+    driver.set_page_load_timeout(20)  # 设置加载超时时间
+    try:
+        start = time.perf_counter()
+        driver.get(url)
+        end = time.perf_counter()
+        delay = end - start  # 网页加载时间
+    except Exception:
+        delay = float(20)
+    driver.close()
+    return delay
+
+# 网站首页10次访问的成功次数与平均时延
+def deal_websites(websites, start, end, lock):
+    for count in tqdm(range(start, end)):
+        web = websites[count]
+        success_status = 0
+        ave_delay = float(0)
+        if web.startswith('http'):
+            url = web
+        else:
+            url = 'http://' + web
+        for i in range(0, 10):
+            status = page_status(url)
+            if int(status) < 400:  # 访问成功
+                success_status += 1
+            else:
+                continue
+
+        for j in range(0, 10):
+            delay = page_time(url)
+            ave_delay += delay
+
+        lock.acquire()
+        ff = open('./result/websitesTimeInfo.csv', 'a', encoding='utf-8', newline='')
+        # 访问网站首页10次，记录成功访问次数和平均加载时延
+        wr = csv.writer(ff)
+        row = [web, success_status, (ave_delay / 10)]
+        wr.writerow(row)
+        ff.close()
+        lock.release()
+
+# 批量获得网站首页的响应响应码
+def deal_urls(urls, start, end, lock):
+    for count in tqdm(range(start, end)):
+        url = urls[count]
+        status = page_status(url)
+        lock.acquire()
+        ff = open('./result/urls_status.csv', 'a', encoding='utf-8', newline='')
+        wr = csv.writer(ff)
+        row = [url, status]
+        wr.writerow(row)
+        ff.close()
+        lock.release()
+
+
+def get_webs():
+    # 待检测的网页列表
+    webs = []
+    f = open('./data/websites.txt', 'r')  # 读取的网站列表
+    # txt存储格式： 每行一个网站首页网址或者域名
+    for line in f:
+        line = line.strip('\n')
+        if line.startswith('http'):
+            pass
+        else:
+            line = 'http://' + line
+        webs.append(line)
+    f.close()
+    return webs
+
+
+if __name__ == '__main__':
+    websites = get_webs()
+    lock = Lock()
+    process_list = []
+    p1 = Process(target=deal_urls, args=(websites, 0, 10, lock)) #实例化进程对象
+    p1.start()
+    process_list.append(p1)
+    p2 = Process(target=deal_urls, args=(websites, 10, 20, lock))  # 实例化进程对象
+    p2.start()
+    process_list.append(p2)
+    p3 = Process(target=deal_urls, args=(websites, 20, 30, lock))  # 实例化进程对象
+    p3.start()
+    process_list.append(p3)
+
+
+    for p in process_list:
+        p.join()
+