RTP changed the site again, fixed.

Also used some better practices on the code.

rtp.py

@@ -2,7 +2,6 @@
 # -*- coding: utf-8 -*-
 # vim: tabstop=8 expandtab shiftwidth=4 softtabstop=4
 
-from bs4 import BeautifulSoup
 import urllib2
 import re
 import unicodedata
@@ -10,21 +9,22 @@ import os
 import string
 import sys
 import time
+from bs4 import BeautifulSoup
 
 months = {
-        'Jan': '01',
+    'Jan': '01',
-        'Fev': '02',
+    'Fev': '02',
-        'Mar': '03',
+    'Mar': '03',
-        'Abr': '04',
+    'Abr': '04',
-        'Mai': '05',
+    'Mai': '05',
-        'Jun': '06',
+    'Jun': '06',
-        'Jul': '07',
+    'Jul': '07',
-        'Ago': '08',
+    'Ago': '08',
-        'Set': '09',
+    'Set': '09',
-        'Out': '10',
+    'Out': '10',
-        'Nov': '11',
+    'Nov': '11',
-        'Dez': '12'
+    'Dez': '12'
-        }
+}
 
 scriptpath = os.path.dirname(os.path.realpath(__file__))
 validFilenameChars = "-_. %s%s" % (string.ascii_letters, string.digits)
@@ -33,19 +33,19 @@ def removeDisallowedFilenameChars(filename):
     cleanedFilename = unicodedata.normalize('NFKD', filename).encode('ASCII', 'ignore')
     return ''.join(c for c in cleanedFilename if c in validFilenameChars)
 
-def parseRTMP(url,title,progId):
+def parseRTMP(url, title, progId):
     url = 'http://www.rtp.pt' + url
 
     match = re.search(r"play/p\d+/(e\d+)/", url)
     episode_id = match.group(1)
 
     programpath = scriptpath+"/"+progId
-    if os.path.isdir(programpath) == False:
+    if os.path.isdir(programpath) is False:
         os.makedirs(programpath)
     destfn = programpath + "/" + title + "_" + episode_id + '.mp3'
     page = urllib2.urlopen(url)
 
-    match = re.search('"hls_url": "(.+?)",', page.read())
+    match = re.search('file: "(.+?)",', page.read())
     if match:
         if os.path.isfile(destfn):
             print "- Ja downloadada... a ignorar"
@@ -56,60 +56,61 @@ def parseRTMP(url,title,progId):
         print "- Done"
         return True
 
-if len(sys.argv) != 2:
+if __name__ == "__main__":
-    sys.exit("Correr com "+sys.argv[0]+" [progId]")
+    if len(sys.argv) != 2:
+        sys.exit("Correr com "+sys.argv[0]+" [progId]")
 
-if sys.argv[1].isdigit():
+    if sys.argv[1].isdigit():
-    id = sys.argv[1]
+        progId = sys.argv[1]
-else:
+    else:
-    sys.exit("progId tem de ser um numero")
+        sys.exit("progId tem de ser um numero")
 
-exists = 0
+    exists = 0
-c = 1
+    c = 1
-while True:
+    while True:
-    print "--- Pagina " + str(c)
+        print "--- Pagina " + str(c)
-    url = "http://www.rtp.pt/play/bg_l_ep/?stamp=" + str(int(time.time())) + "&listDate=&listQuery=&listProgram=" + str(id) + "&listcategory=&listchannel=&listtype=recent&page=" + str(c) + "&type=all"
+        url = "http://www.rtp.pt/play/bg_l_ep/?stamp=" + str(int(time.time())) + "&listDate=&listQuery=&listProgram=" + str(progId) + "&listcategory=&listchannel=&listtype=recent&page=" + str(c) + "&type=all"
 
-    page = urllib2.urlopen(url)
+        page = urllib2.urlopen(url)
-    soup = BeautifulSoup(page.read(), "html.parser")
+        soup = BeautifulSoup(page.read(), "html.parser")
 
-    if (soup.find('div') == None):
+        if soup.find('div') is None:
-        sys.exit("ultima pagina")
+            sys.exit("ultima pagina")
 
-    # apanha todos os items da pagina
+        # apanha todos os items da pagina
-    items = soup.findAll('div',{'class': 'lazy'})
+        items = soup.findAll('div', {'class': 'lazy'})
 
-    for item in items:
+        for item in items:
-        if exists >= 5:
+            if exists >= 5:
-            sys.exit("A sair apos 5 falhas, ja devo ter tudo...")
+                sys.exit("A sair apos 5 falhas, ja devo ter tudo...")
 
-        # url
+            # url
-        link = item.find('a')
+            link = item.find('a')
-        # data
+            # data
-        dt = item.find('span',{'class': 'small'}).contents[0].strip()
+            dt = item.find('span', {'class': 'small'}).contents[0].strip()
-        dt = dt.replace(' ', '_')
+            dt = dt.replace(' ', '_')
-        dt = dt.replace(',', '')
+            dt = dt.replace(',', '')
 
-        # mudar para AAAA_MM_DD
+            # mudar para AAAA_MM_DD
-        match = re.search(r"(\d+)_(\w+)_(\d+)", dt)
+            match = re.search(r"(\d+)_(\w+)_(\d+)", dt)
-        if match:
+            if match:
-           dt = match.group(3) + "_" + months[match.group(2)] + "_" + match.group(1)
+                dt = match.group(3) + "_" + months[match.group(2)] + "_" + match.group(1)
 
-        # parte ?
+            # parte ?
-        pts = item.findAll('b',{'class': 'text-dark-gray'})
+            pts = item.findAll('b', {'class': 'text-dark-gray'})
-        try:
+            try:
-            pt = pts[1].contents[0]
+                pt = pts[1].contents[0]
-            pt = pt.replace('...', '').strip()
+                pt = pt.replace('...', '').strip()
-            pt = pt.replace(' ', '_')
+                pt = pt.replace(' ', '_')
-            pt = pt.replace('\n','')
+                pt = pt.replace('\n', '')
-        except IndexError:
+            except IndexError:
-            pt = ""
+                pt = ""
 
-        print "-- " +  dt, pt
+            print "-- " +  dt, pt
 
-        title = removeDisallowedFilenameChars(dt + "-" + pt)
+            title = removeDisallowedFilenameChars(dt + "-" + pt)
-        if parseRTMP(link['href'],title,id) == False:
-           exists = exists + 1
 
-    c = c + 1
+            if parseRTMP(link['href'], title, progId) is False:
+                exists = exists + 1
 
+        c = c + 1