erp5: check cache hit script enhanced to handle CSS and favicons

Previously, only images (from <img> tag) and scripts (from <script> tag) were handled

stack/erp5/buildout.cfg

@@ -191,7 +191,7 @@ output = ${buildout:directory}/template-http-monitor.cfg.in
 < = download-base
 url = ${:_profile_base_location_}/monitor-templates/monitor-check-cache-hit.in
 download-only = true
-md5sum = 878833710ffd2e0734989cb9c93a8103
+md5sum = b9f3f93bc41287698a44a687e6483f01
 filename = monitor-check-cache-hit.in
 mode = 0644
 

stack/erp5/monitor-templates/monitor-check-cache-hit.in

@@ -35,14 +35,23 @@ class MyHTMLParser(HTMLParser):
     HTMLParser.__init__(self)
     self.base_url = base_url
   def handle_starttag(self, tag, attrs):
-    if tag == 'img' or tag == 'script': # TODO: CSS & JS
+    def handle_url(url):
+      if not url.startswith("http"):
+        url = self.base_url + url
+      do_request(url)
+    # handle images and js scripts
+    if tag == 'img' or tag == 'script':
       debug(tag, attrs)
       for attr in attrs:
         if attr[0] == 'src':
-          url = attr[1]
-          if not url.startswith('http'):
-            url = self.base_url + url
-          do_request(url)
+          handle_url(attr[1])
+    # handle css and favicon
+    if tag == 'link' and \
+       any(attr[0] == "rel" and attr[1] in ("stylesheet", "shortcut icon") for attr in attrs):
+      debug(tag, attrs)
+      for attr in attrs:
+        if attr[0] == "href":
+          handle_url(attr[1])
 
 headers = {
   "User-Agent": "test",
@@ -53,9 +62,7 @@ headers = {
 }
 
 url_list = {{ url_list }}
-# url_list = ["http://www.erp5.com"]
 resolve_list = {{ resolve_list }}
-# resolve_list = ["www.erp5.com:80:5.135.149.226"]
 
 parsed_url_dict = {}