From 3005b91df9e47ff871693d0797ca3eefe02956d6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=C2=AF=5C=5F=28=E3=83=84=29=5F/=C2=AF=20feel=20free=20to?=
 =?UTF-8?q?=20copy=20my=20code=20=2C=20I=20do=20it=20too?=
 <96356684+behind24proxies@users.noreply.github.com>
Date: Fri, 2 Sep 2022 11:11:18 -0400
Subject: [PATCH] last push

---
 website_report/stats.py | 75 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)
 create mode 100644 website_report/stats.py

diff --git a/website_report/stats.py b/website_report/stats.py
new file mode 100644
index 0000000..dadac79
--- /dev/null
+++ b/website_report/stats.py
@@ -0,0 +1,75 @@
+import requests
+import html_to_json
+import time
+import warnings
+
+# removes useless data from the url
+def clean_url(url):
+
+    url = url.replace('www.', '')
+    url = url.replace('https://', '')
+    url = url.replace('http://', '')
+    url = url.split('/')[0]
+    return url
+
+def create_full_url(url):
+    return f'https://nibbler.insites.com/en_US/reports/{clean_url(url)}'
+def generate_report(website_url,
+             step=5,
+             max_time=60,
+             debug=False,
+             info=True):
+    full_url = create_full_url(website_url)
+    max_loop = max_time//step
+    while True:
+        resp = requests.get(full_url).text
+        length = len(resp)
+        
+        # if the length is less than 15000, then the page is not ready yet
+
+        if length < 15000:
+            if debug:
+                print(f'[DEBUG] : max time left {max_loop*step}s')
+                print(f'[DEBUG] : sleeping for {step}s ')
+
+            max_loop -= 1
+            if max_loop < 0:
+                if info:
+                    print('[INFO] : max time reached')
+                    print(f'[INFO] : check the report yourself {full_url}')
+
+                return False
+            time.sleep(step)
+        else:
+            # if the code reaches here, then we convert all html data in json
+            jned = html_to_json.convert(resp)
+            break
+    returner = []
+    try:
+        for x in jned['html'][0]['body'][0]['div'][0]['div'][1]['div'][0]['div'][0]['div'][0]['div']:
+            current = x['h3'][0]
+
+            values = {
+                'name': current['_value'],
+                'rating': current['span'][0]['_attributes']['class'][1],
+                'value': current['span'][0]['_value']
+            }
+            returner.append(values)
+
+        for x in jned['html'][0]['body'][0]['div'][0]['div'][1]['div'][2]['div'][0]['div']:
+            try:
+                attribute = x['h2'][0]['_value']
+                value = x['h2'][0]['span'][0]['_value']
+                values = {
+                    'name': attribute,
+                    'value': value
+                }
+                returner.append(values)
+            except Exception as e :
+                # warnings.warn(e)
+                pass
+        return returner
+    except Exception as e:
+        print(e)
+        warnings.warn(e)
+