Merge branch 'master' of github.com:marco-c/autowebcompat into id_less

README.md

@@ -17,3 +17,7 @@ The aim of this project is creating a tool to automatically detect web compatibi
 
 - Install the dependencies in requirements.txt: `pip install -r requirements.txt`.
 - Run the **get_dependencies.py** script.
+
+## Communication
+
+Real-time communication for this project happens on [Mozilla's IRC network](https://wiki.mozilla.org/IRC), irc.mozilla.org, in the #webcompat channel.

collect.py

@@ -9,10 +9,10 @@
 from selenium import webdriver
 from selenium.common.exceptions import NoAlertPresentException, NoSuchWindowException, TimeoutException
 
-if sys.platform.startswith("linux"):  # linux
+if sys.platform.startswith("linux"):
     chrome_bin = "tools/chrome-linux/chrome"
     nightly_bin = 'tools/nightly/firefox-bin'
-elif sys.platform.startswith("darwin"):    # MAC OS X
+elif sys.platform.startswith("darwin"):
     chrome_bin = "tools/chrome.app/Contents/MacOS/chrome"
     nightly_bin = 'tools/Nightly.app/Contents/MacOS/firefox'
 elif sys.platform.startswith("win32"):
@@ -79,14 +79,13 @@ def close_all_windows_except_first(driver):
 
 def get_all_attributes(driver, child):
     child_attributes = driver.execute_script("""
-        let elem_attribute = {};
+      let elem_attribute = {};
 
-        for (let i = 0; i < arguments[0].attributes.length; i++) {
-          elem_attribute[arguments[0].attributes[i].name] = arguments[0].attributes[i].value;
-          }
-
-        return elem_attribute;
-        """, child)
+      for (let i = 0; i < arguments[0].attributes.length; i++) {
+        elem_attribute[arguments[0].attributes[i].name] = arguments[0].attributes[i].value;
+      }
+      return elem_attribute;
+    """, child)
 
     return child_attributes
 
@@ -104,6 +103,7 @@ def do_something(driver, elem_attributes=None):
         children = buttons + links + inputs
 
         random.shuffle(children)
+
         for child in children:
 
             # Get all the attributes of the child.
@@ -126,7 +126,9 @@ def do_something(driver, elem_attributes=None):
             links = body.find_elements_by_tag_name('a')
             inputs = body.find_elements_by_tag_name('input')
             children = buttons + links + inputs
+
             for child in children:
+
                 # Get all the attributes of the child.
                 child_attributes = get_all_attributes(driver, child)
                 if elem_attributes == child_attributes:

get_dependencies.py

@@ -38,10 +38,8 @@ def download(url, filename):
 download(url, name)
 
 print('[*] Extracting files...')
-f = tarfile.open(name, 'r:xz')
-f.extractall('.')
-f.close()
-
+with tarfile.open(name, 'r:xz') as f:
+    f.extractall('.')
 os.remove(name)
 
 print('[*] Downloading data.zip...')

network.py

@@ -127,7 +127,7 @@ def accuracy(y_true, y_pred):
     return K.mean(K.equal(y_true, K.cast(y_pred < 0.5, y_true.dtype)))
 
 
-def compile(model, optimizer=None, loss_func=contrastive_loss):
+def compile(model, optimizer='sgd', loss_func=contrastive_loss):
     allOptimizers = {
         'sgd': SGD(lr=0.0003, decay=1e-6, momentum=0.9, nesterov=True),
         'adam': Adam(),

rename_images.py

@@ -9,7 +9,7 @@
         continue
     webcompat_id = parts[0]
     sequence_no = parts[-2]
-    elem_id = parts[1:-2]
+    elem_id = '_'.join(parts[1:-2])
     browser = parts[-1]
     if webcompat_id not in image_info.keys():
         image_info[webcompat_id] = {}
@@ -22,5 +22,5 @@
         seq_no_and_elem_id = sorted(seq_no_and_elem_id.items())
         for value in seq_no_and_elem_id:
             sequence_no = value[0]
-            elem_id = value[1][0]
+            elem_id = value[1]
             text_file.write("%s %s\n" % (sequence_no, elem_id))