v2.94

maaaaz · Aug 23, 2020 · 16e5c2a · 16e5c2a
1 parent defc86b
commit 16e5c2a
Show file tree

Hide file tree

Showing 3 changed files with 64 additions and 14 deletions.
diff --git a/README.md b/README.md
@@ -36,13 +36,13 @@ domain_or_ip(/resource)
 
 ### Options
 ```
-webscreenshot.py version 2.93
+webscreenshot.py version 2.94
 
-usage: webscreenshot.py [-h] [-i INPUT_FILE] [-o OUTPUT_DIRECTORY] [-w WORKERS] [-v] [--no-error-file] [-p PORT] [-s] [-m]
+usage: webscreenshot.py [-h] [-i INPUT_FILE] [-o OUTPUT_DIRECTORY] [-w WORKERS] [-v] [--no-error-file] [-z SINGLE_OUTPUT_FILE] [-p PORT] [-s] [-m]
                         [-r {phantomjs,chrome,chromium,edgechromium,firefox}] [--renderer-binary RENDERER_BINARY] [--no-xserver] [--window-size WINDOW_SIZE]
-                        [-f {pdf,png,jpg,jpeg,bmp,ppm}] [-q [0-100]] [--ajax-max-timeouts AJAX_MAX_TIMEOUTS] [--crop CROP] [-l] [--label-size LABEL_SIZE]
-                        [--label-bg-color LABEL_BG_COLOR] [--imagemagick-binary IMAGEMAGICK_BINARY] [-c COOKIE] [-a HEADER] [-u HTTP_USERNAME]
-                        [-b HTTP_PASSWORD] [-P PROXY] [-A PROXY_AUTH] [-T PROXY_TYPE] [-t TIMEOUT]
+                        [-f {pdf,png,jpg,jpeg,bmp,ppm}] [-q [0-100]] [--ajax-max-timeouts AJAX_MAX_TIMEOUTS] [--crop CROP] [--custom-js CUSTOM_JS] [-l]
+                        [--label-size LABEL_SIZE] [--label-bg-color LABEL_BG_COLOR] [--imagemagick-binary IMAGEMAGICK_BINARY] [-c COOKIE] [-a HEADER]
+                        [-u HTTP_USERNAME] [-b HTTP_PASSWORD] [-P PROXY] [-A PROXY_AUTH] [-T PROXY_TYPE] [-t TIMEOUT]
                         [URL]
 
 optional arguments:
@@ -58,6 +58,8 @@ Main parameters:
                         <WORKERS> (optional): number of parallel execution workers (default 4)
   -v, --verbosity       <VERBOSITY> (optional): verbosity level, repeat it to increase the level { -v INFO, -vv DEBUG } (default verbosity ERROR)
   --no-error-file       <NO_ERROR_FILE> (optional): do not write a file with the list of URL of failed screenshots (default false)
+  -z SINGLE_OUTPUT_FILE, --single-output-file SINGLE_OUTPUT_FILE
+                        <SINGLE_OUTPUT_FILE> (optional): name of a file which will be the single output of all inputs. Ex. test.png
 
 Input processing parameters:
   -p PORT, --port PORT  <PORT> (optional): use the specified port for each target in the input list. Ex: -p 80
@@ -85,6 +87,9 @@ Screenshot image parameters:
                         <AJAX_MAX_TIMEOUTS> (optional, phantomjs only): per AJAX request, and max URL timeout in milliseconds (default '1400,1800')
   --crop CROP           <CROP> (optional, phantomjs only): rectangle <t,l,w,h> to crop the screen capture to (default to WINDOW_SIZE: '0,0,w,h'), only
                         numbers, w(idth) and h(eight). Ex. "10,20,w,h"
+  --custom-js CUSTOM_JS
+                        <CUSTOM_JS> (optional, phantomjs only): path of a file containing JavaScript code to be executed before taking the screenshot. Ex:
+                        js.txt
 
 Screenshot label parameters:
   -l, --label           <LABEL> (optional): for each screenshot, create another one displaying inside the target URL (requires imagemagick)
@@ -192,6 +197,7 @@ Options not listed here below are supported by every current renderer
 |                       | quality (`-q`)                                                                  | [**Yes**](https://web.archive.org/web/20200111184123/https://phantomjs.org/api/webpage/method/render.html)                    | No                             | No                   
 |                       | ajax and request timeouts (`--ajax-max-timeouts`)                                         | **Yes**                    | No                             | No                   
 |                       | crop (`--crop`)                                                                  | [**Yes**](https://web.archive.org/web/20200111184050/https://phantomjs.org/api/webpage/property/clip-rect.html)                    | No                             | No                   
+|                       | custom JavaScript (`--custom-js`)                                                                  | [**Yes**](https://web.archive.org/web/20200823123026/https://phantomjs.org/api/webpage/method/evaluate-java-script.html)                    | No                             | No                   
 |                       |                                                                              |                        |                                |                      |
 | **HTTP parameters**   |                                                                              |                        |                                |                      |
 |                       | cookie (`-c`)                                                                  | **Yes**                    | No                             | No                   |
@@ -222,6 +228,7 @@ Requirements
 
 Changelog
 ---------
+* version 2.94 - 08/23/2020: Added custom-js and single output file options
 * version 2.93 - 08/16/2020: Added support of Python 3.8 and Microsoft Edge Chromium ; file output for failed webscreenshots ; filename length limitation for long URL 
 * version 2.92 - 06/21/2020: no_xserver option autodetection
 * version 2.91 - 05/08/2020: Multiprotocol mode fix

diff --git a/webscreenshot.js b/webscreenshot.js
@@ -18,7 +18,7 @@
 # along with webscreenshot.	 If not, see <http://www.gnu.org/licenses/>.
 ***/
 
-var Page = (function(custom_headers, http_username, http_password, image_width, image_height, image_format, image_quality, ajax_timeout, max_timeout, crop_rect) {
+var Page = (function(custom_headers, http_username, http_password, image_width, image_height, image_format, image_quality, ajax_timeout, max_timeout, crop_rect, custjs) {
 	var opts = {
 		width: image_width || 1200,
 		height: image_height || 800,
@@ -104,7 +104,12 @@ var Page = (function(custom_headers, http_username, http_password, image_width,
 		page.evaluate(function() {
 			document.body.bgColor = 'white';
 		});
-
+		if (custjs)
+		{
+			var fs = require('fs');
+			var content = fs.read(custjs);
+			page.evaluateJavaScript(content);
+		}
 		page.render(opts.file, {format: opts.format, quality: opts.quality});
 		phantom.exit(0);
 	}
@@ -147,6 +152,9 @@ function main() {
 
 	var p_crop = new RegExp('crop=(.*)');
 	var crop_rect = '';
+
+	var p_custjs = new RegExp('customjs=(.*)');
+	var custjs = '';
 
 	var temp_custom_headers = {
 		// Nullify Accept-Encoding header to disable compression (https://github.com/ariya/phantomjs/issues/10930)
@@ -219,6 +227,11 @@ function main() {
 		{
 			crop_rect = p_crop.exec(system.args[i])[1].split(',');
 		}
+
+		if (p_custjs.test(system.args[i]) === true)
+		{
+			custjs = p_custjs.exec(system.args[i])[1].split(',');
+		}
 	}
 
 	if (typeof(URL) === 'undefined' || URL.length == 0 || typeof(output_file) === 'undefined' || output_file.length == 0) {
@@ -228,7 +241,7 @@ function main() {
 		phantom.exit(1);
 	}
 	else {
-		var page = Page(temp_custom_headers, http_username, http_password, image_width, image_height, image_format, image_quality, ajax_timeout, max_timeout, crop_rect);
+		var page = Page(temp_custom_headers, http_username, http_password, image_width, image_height, image_format, image_quality, ajax_timeout, max_timeout, crop_rect, custjs);
 		page.render(URL, output_file);
 	}
 }

diff --git a/webscreenshot.py b/webscreenshot.py
@@ -49,7 +49,7 @@
     izip = zip
 
 # Script version
-VERSION = '2.93'
+VERSION = '2.94'
 
 # Options definition
 parser = argparse.ArgumentParser()
@@ -61,6 +61,7 @@
 main_grp.add_argument('-w', '--workers', help = '<WORKERS> (optional): number of parallel execution workers (default 4)', default = 4)
 main_grp.add_argument('-v', '--verbosity', help = '<VERBOSITY> (optional): verbosity level, repeat it to increase the level { -v INFO, -vv DEBUG } (default verbosity ERROR)', action = 'count', default = 0)
 main_grp.add_argument('--no-error-file', help = '<NO_ERROR_FILE> (optional): do not write a file with the list of URL of failed screenshots (default false)', action = 'store_true', default = False)
+main_grp.add_argument('-z', '--single-output-file', help = '<SINGLE_OUTPUT_FILE> (optional): name of a file which will be the single output of all inputs. Ex. test.png')
 
 proc_grp = parser.add_argument_group('Input processing parameters')
 proc_grp.add_argument('-p', '--port', help = '<PORT> (optional): use the specified port for each target in the input list. Ex: -p 80')
@@ -78,6 +79,7 @@
 image_grp.add_argument('-q', '--quality', help = '<QUALITY> (optional, phantomjs only): specify the output image quality, an integer between 0 and 100 (default 75)', metavar="[0-100]", choices = range(0,101), type = int, default = 75)
 image_grp.add_argument('--ajax-max-timeouts', help = '<AJAX_MAX_TIMEOUTS> (optional, phantomjs only): per AJAX request, and max URL timeout in milliseconds (default \'1400,1800\')', default = '1400,1800')
 image_grp.add_argument('--crop', help = '<CROP> (optional, phantomjs only): rectangle <t,l,w,h> to crop the screen capture to (default to WINDOW_SIZE: \'0,0,w,h\'), only numbers, w(idth) and h(eight). Ex. "10,20,w,h"')
+image_grp.add_argument('--custom-js', help = '<CUSTOM_JS> (optional, phantomjs only): path of a file containing JavaScript code to be executed before taking the screenshot. Ex: js.txt')
 
 image_grp = parser.add_argument_group('Screenshot label parameters')
 image_grp.add_argument('-l', '--label', help = '<LABEL> (optional): for each screenshot, create another one displaying inside the target URL (requires imagemagick)', action = 'store_true', default = False)
@@ -287,7 +289,7 @@ def extract_all_matched_named_groups(regex, match):
         if matched_value != None: result[name] = matched_value
 
     return result
-    
+
 def entry_format_validator(line):
     """
         Validate the current line against several regexes and return matched parameters (ip, domain, port etc.)
@@ -380,6 +382,9 @@ def parse_targets(options):
     return target_list
 
 def craft_bin_path(options, context=CONTEXT_RENDERER):
+    """
+        Craft the proper binary path for renderer 
+    """
     global PHANTOMJS_BIN, CHROME_BIN, CHROMIUM_BIN, FIREFOX_BIN, XVFB_BIN, IMAGEMAGICK_BIN
 
     final_bin = []
@@ -414,6 +419,9 @@ def craft_bin_path(options, context=CONTEXT_RENDERER):
     return " ".join(final_bin)
 
 def craft_arg(param):
+    """
+        Craft arguments with proper quotes
+    """
     if is_windows():
         return '%s' % param
     else:
@@ -429,6 +437,23 @@ def launch_cmd(logger, url, cmd_parameters, options, context):
 
     return execution_retval
 
+def craft_output_filename_and_format(url, options):
+    """
+        Craft the output filename and format
+    """
+    output_format = options.format if options.renderer == 'phantomjs' else 'png'
+
+    if options.single_output_file:
+        if options.single_output_file.lower().endswith('.%s' % output_format):
+            output_filename = os.path.abspath(filter_bad_filename_chars_and_length(options.single_output_file))
+        else:
+            output_filename = os.path.abspath(filter_bad_filename_chars_and_length('%s.%s' % (options.single_output_file, output_format)))
+
+    else:
+        output_filename = os.path.join(options.output_directory, ('%s.%s' % (filter_bad_filename_chars_and_length(url), output_format)))
+
+    return output_format, output_filename
+
 def craft_cmd(url_and_options):
     """
         Craft the correct command with url and options
@@ -441,8 +466,7 @@ def craft_cmd(url_and_options):
     logger_url.addHandler(logger_output)
     logger_url.setLevel(options.log_level)
 
-    output_format = options.format if options.renderer == 'phantomjs' else 'png'
-    output_filename = os.path.join(options.output_directory, ('%s.%s' % (filter_bad_filename_chars_and_length(url), output_format)))
+    output_format, output_filename = craft_output_filename_and_format(url, options)
 
     # PhantomJS renderer
     if options.renderer == 'phantomjs':
@@ -470,8 +494,8 @@ def craft_cmd(url_and_options):
             cmd_parameters.append('header="Authorization: Basic %s"' % basic_authentication_header)
 
         width = options.window_size.split(',')[0]
-
         height = options.window_size.split(',')[1]
+
         cmd_parameters.append('width=%d' % int(width))
         cmd_parameters.append('height=%d' % int(height))
 
@@ -488,6 +512,10 @@ def craft_cmd(url_and_options):
         if options.header:
             for header in options.header:
                 cmd_parameters.append('header="%s"' % header.rstrip(';'))
+
+        if options.custom_js and os.path.exists(options.custom_js):
+            cmd_parameters.append('customjs=%s' % craft_arg(os.path.abspath(options.custom_js)))
+
 
     # Chrome and chromium renderers
     elif (options.renderer == 'chrome') or (options.renderer == 'chromium') or (options.renderer == 'edgechromium'): 
@@ -532,7 +560,6 @@ def craft_cmd(url_and_options):
 
     return execution_retval, url
 
-
 def take_screenshot(url_list, options):
     """
         Launch the screenshot workers
@@ -592,6 +619,9 @@ def main():
     if (options.input_file != None) and (options.URL != None):
         parser.error('Please specify either an input file or an URL')
 
+    if options.single_output_file:
+        options.workers = 1
+
     if options.output_directory != None:
         options.output_directory = os.path.join(os_getcwd(), options.output_directory)
     else: