Learning git

.py

@@ +1 @@
+#!/bin/env python
+# Original @ https://gist.github.com/tloredo/8483682
 """
 Scrape a user's Netflix movie ratings by automating a Safari browsing
 session (with the user already logged in).  The ratings are written
@@ -106 +108 @@
 
 from jinja2 import Template
 from lxml import html
+import re
+
+fname_regex = re.compile(r'(\w+?)_?(\d+)?\.(\w+)')
+rating_regex = re.compile(r'You rated this movie: (\d)\.(\d)')
 
 
 # AppleScript functions asrun and asquote (presently unused) are from:
@@ -159 +165 @@
     All values are strings.
     """
     # Load the page, grab the HTML, and parse it to a tree.
-    script = ASTemplate.render(URL=url, DTIME=dtime)
-    reply = asrun(script)
+    reply = ''
+    try:
+      with open(url) as infile:
+        for str_ in infile:
+          reply += str_
+    except IOError:
+      return [], None
+
+
     tree = html.fromstring(reply)
     rows = tree.xpath('//table[@class="listHeader"]//tr')
 
@@ -180 +193 @@
             # changing from page to page.  For info on XPath for such cases, see:
             # http://stackoverflow.com/questions/8808921/selecting-a-css-class-with-xpath
             # rating = data[3].xpath('//span[@class="stbrMaskFg sbmfrt sbmf-50"]')[0].text_content()
-            rating = data[3].xpath('//span[contains(concat(" ", normalize-space(@class), " "), " stbrMaskFg ")]')[0].text_content()
-            rating = rating.split(':')[1].strip()  # keep only the number
+            rating_cut = rating_regex.match(data[3].text_content())
+            rating = '0.0'
+            if rating_cut:
+               rating = "%s.%s"%(rating_cut.group(1), rating_cut.group(2))
+
             info.append((title, year, genre, rating))
 
     # Next URL to load:
-    next_elem = tree.xpath('//li[@class="navItem paginationLink paginationLink-next"]/a')
-    if next_elem:
-        next_url = next_elem[0].get('href')
-    else:  # empty list
-        next_url = None
+    fname_cut = fname_regex.match(url)
+    if fname_cut:
+      if None == fname_cut.group(2):
+        num = 0
+      else:
+        num = fname_cut.group(2)
+      next_url = "%s_%03.f.%s"%(fname_cut.group(1),int(num)+1,fname_cut.group(3))
+    else:
+      print "Regex failed."
+      next_url = None
+
 
     return info, next_url
 
 
 # Use this initial URL for DVD accounts:
-url = 'http://dvd.netflix.com/MoviesYouveSeen'
+url = 'MoviesYouveSeen.htm'
 # Use this initial URL for streaming accounts:
 # url = 'http://movies.netflix.com/MoviesYouveSeen'