Feature: '-f' parameter without "TERM" shows the Top 20.

README.md

@@ -56,7 +56,8 @@ HTTP Headers Analyzer<br />
 :heavy_check_mark: The analysis includes dozens of references, official documentation and technical articles.<br />
 :heavy_check_mark: i10n: analysis results in English or Spanish.<br />
 :heavy_check_mark: Saves each analysis, showing (at the end) the improvements or deficiencies in relation to the last one.<br />
-:heavy_check_mark: Shows statistics: either for all scans performed against all URLs or for a specific URL.<br />
+:heavy_check_mark: Shows analysis statistics: either against a specific URL or all of them.<br />
+:heavy_check_mark: Shows fingerprint statistics: either against a specific term or the Top 20.<br />
 :heavy_check_mark: Code reviewed via <a href="https://pypi.org/project/pycodestyle/" target="_blank">pycodestyle<a>, <a href="https://marketplace.visualstudio.com/items?itemName=SonarSource.sonarlint-vscode" target="_blank">SonarLint<a> and <a href="https://marketplace.visualstudio.com/items?itemName=sourcery.sourcery" target="_blank">Sourcery<a>.<br />
 :heavy_check_mark: Tested, one by one, on thousands of URLs.<br />
 :heavy_check_mark: Fully tested and working on Windows (10 20H2 - 19042.985) and Linux (Kali 2021.1).<br />
@@ -157,20 +158,20 @@ https://github.com/rfc-st/humble/releases
 (Windows) $ py humble.py
 (Linux)   $ python3 humble.py
 
-usage: humble.py [-h] [-a] [-b] [-f TERM] [-g] [-l {es}] [-o {html,pdf,txt}] [-r] [-u URL] [-v]
+usage: humble.py [-h] [-a] [-b] [-f [TERM]] [-g] [-l {es}] [-o {html,pdf,txt}] [-r] [-u URL] [-v]
 
 humble (HTTP Headers Analyzer) - https://github.com/rfc-st/humble
 
 options:
   -h, --help         show this help message and exit
   -a                 Show statistics of the performed analysis (will be global if '-u' URL is omitted)
-  -b                 Show a brief analysis; if omitted, a detailed analysis will be shown.
-  -f TERM            Show statistics for fingerprint headers related to the term E.g., Akamai, Google.
-  -g                 Show guidelines on securing most used web servers/services.
-  -l {es}            Displays the analysis in the indicated language; if omitted, English will be used.
-  -o {html,pdf,txt}  Save analysis to file (URL_headers_yyyymmdd.ext).
-  -r                 Show HTTP response headers and a detailed analysis.
-  -u URL             URL to analyze, with schema. E.g., https://google.com
+  -b                 Show a brief analysis; if omitted, a detailed analysis will be shown
+  -f [TERM]          Show fingerprint statistics (will be the Top 20 if "TERM", e.g. "Google", is omitted)
+  -g                 Show guidelines on securing most used web servers/services
+  -l {es}            Displays the analysis in the indicated language; if omitted, English will be used
+  -o {html,pdf,txt}  Save analysis to file (URL_headers_yyyymmdd.ext)
+  -r                 Show HTTP response headers and a detailed analysis
+  -u URL             URL to analyze, with schema. E.g. https://google.com
   -v, --version      Show version and checks for updates
 ```
 

humble.py

@@ -38,7 +38,7 @@
 from fpdf import FPDF
 from time import time
 from datetime import datetime
-from collections import defaultdict
+from collections import Counter, defaultdict
 from os import linesep, path, remove
 from colorama import Fore, Style, init
 from argparse import ArgumentParser, RawDescriptionHelpFormatter
@@ -149,21 +149,44 @@ def check_updates(version):
         print(f"\n{get_detail('[update_error]')}")
 
 
+def fng_analytics_global_groups(fng_lines):
+    pattern = r'\[([^\]]+)\]'
+    content_count = Counter(match.strip() for line in fng_lines for match in
+                            re.findall(pattern, line))
+    total_lines = len(fng_lines)
+    print(f"{get_detail('[fng_top]', replace=True)}{total_lines}\
+{get_detail('[fng_top_2]', replace=True)}\n")
+    for content, count in content_count.most_common(20):
+        percentage = round(count / total_lines * 100, 2)
+        print(f" [{content}]: {percentage}% ({count})")
+
+
+def fng_analytics_global():
+    print(f"\n{Style.BRIGHT}{get_detail('[fng_stats]', replace=True)}\
+{Style.RESET_ALL}{get_detail('[fng_source]', replace=True)}\n")
+    with open(path.join('additional', F_FILE), 'r', encoding='utf8') as fng_f:
+        fng_lines = fng_f.readlines()
+    fng_analytics_global_groups(fng_lines)
+
+
 def fng_analytics_groups(fng_lines, term):
     pattern = r'\[(.*?)\]'
-    distinct_content = {re.search(pattern, line)[1].strip() for line in
-                        fng_lines if re.search(pattern, line) and term.lower()
-                        in re.search(pattern, line)[1].lower()}
-    term_count = sum(re.search(pattern, line) and term.lower() in
-                     re.search(pattern, line)[1].lower() for line in fng_lines)
+    distinct_content = \
+        {match[1].strip()
+         for line in fng_lines if (match := re.search(pattern, line)) and
+         term.lower() in match[1].lower()}
+    term_count = sum(bool((match := re.search(pattern, line)) and term.lower()
+                          in match[1].lower()) for line in fng_lines)
     return distinct_content, term_count
 
 
 def fng_analytics_sorted(fng_lines, term, distinct_content):
     for content in sorted(distinct_content):
         print(f"\n [{content}]")
         for line in fng_lines:
-            if term.lower() in line.lower() and content in line:
+            match = re.search(r'\[(.*?)\]', line)
+            if match and term.lower() in match[1].lower() \
+               and content == match[1].strip():
                 print(f"  {line[:line.find('[')].strip()}")
 
 
@@ -687,19 +710,20 @@ def request_exceptions():
 parser.add_argument("-a", dest='URL_A', action="store_true", help="Show \
 statistics of the performed analysis (will be global if '-u' URL is omitted)")
 parser.add_argument("-b", dest='brief', action="store_true", help="Show a \
-brief analysis; if omitted, a detailed analysis will be shown.")
-parser.add_argument("-f", type=str, dest='term', help="Show statistics \
-for fingerprint headers related to the term E.g., Akamai, Google.")
+brief analysis; if omitted, a detailed analysis will be shown")
+parser.add_argument("-f", nargs='?', type=str, dest='term', help="Show \
+fingerprint statistics (will be the Top 20 if \"TERM\", e.g. \"Google\", is \
+omitted)")
 parser.add_argument("-g", dest='guides', action="store_true", help="Show \
-guidelines on securing most used web servers/services.")
+guidelines on securing most used web servers/services")
 parser.add_argument("-l", dest='lang', choices=['es'], help="Displays the \
-analysis in the indicated language; if omitted, English will be used.")
+analysis in the indicated language; if omitted, English will be used")
 parser.add_argument("-o", dest='output', choices=['html', 'pdf', 'txt'],
-                    help="Save analysis to file (URL_headers_yyyymmdd.ext).")
+                    help="Save analysis to file (URL_headers_yyyymmdd.ext)")
 parser.add_argument("-r", dest='ret', action="store_true", help="Show HTTP \
-response headers and a detailed analysis.")
+response headers and a detailed analysis")
 parser.add_argument('-u', type=str, dest='URL', help="URL to analyze, with \
-schema. E.g., https://google.com")
+schema. E.g. https://google.com")
 parser.add_argument("-v", "--version", action="store_true",
                     help="Show version and checks for updates")
 
@@ -712,6 +736,13 @@ def request_exceptions():
     check_updates(version)
     sys.exit()
 
+if args.term is None and '-f' in sys.argv:
+    details_f = get_details_lines()
+    if args.lang:
+        details_f = get_details_lines()
+    fng_analytics_global()
+    sys.exit()
+
 if args.term:
     term = args.term
     details_f = get_details_lines()

i10n/details.txt

@@ -881,4 +881,10 @@ Highlights
  (source: "additional/fingerprint.txt")
 
 [fng_add]
- Related to
+ Related to
+
+[fng_top]
+ Top 20 in relation to the 
+
+[fng_top_2]
+ headers of the source

i10n/details_es.txt

@@ -881,4 +881,10 @@ A destacar
  (fuente: "additional/fingerprint.txt")
 
 [fng_add]
- Asociadas a
+ Asociadas a
+
+[fng_top]
+ Top 20 en relación a las 
+
+[fng_top_2]
+ cabeceras del fichero fuente