From 93dd69b3df109e0b909292986b69b8c50d2d7e11 Mon Sep 17 00:00:00 2001
From: mkaay <mkaay@mkaay.de>
Date: Tue, 1 Feb 2011 01:25:26 +0100
Subject: fixed #206 (HoerbuchIn)

---
 module/plugins/crypter/HoerbuchIn.py | 72 +++++++++++++++++++-----------------
 1 file changed, 39 insertions(+), 33 deletions(-)

(limited to 'module/plugins/crypter')

diff --git a/module/plugins/crypter/HoerbuchIn.py b/module/plugins/crypter/HoerbuchIn.py
index 7dd52ba40..3d876d7fe 100644
--- a/module/plugins/crypter/HoerbuchIn.py
+++ b/module/plugins/crypter/HoerbuchIn.py
@@ -4,43 +4,49 @@
 import re
 
 from module.plugins.Crypter import Crypter
+from module.lib.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup
 
 class HoerbuchIn(Crypter):
     __name__ = "HoerbuchIn"
     __type__ = "container"
     __pattern__ = r"http://(www\.)?hoerbuch\.in/(blog\.php\?id=|download_(.*)\.html)"
-    __version__ = "0.4"
+    __version__ = "0.5"
     __description__ = """Hoerbuch.in Container Plugin"""
-    __author_name__ = ("spoob")
-    __author_mail__ = ("spoob@pyload.org")
+    __author_name__ = ("spoob", "mkaay")
+    __author_mail__ = ("spoob@pyload.org", "mkaay@mkaay.de")
+
+    def decrypt(self, pyfile):
+        self.pyfile = pyfile
+        
+        self.html = self.req.load(self.pyfile.url)
+        if re.search(r"Download", self.html) is None:
+            self.offline()
+        
+        soup = BeautifulSoup(self.html, convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
+        package_base = soup.find("a", attrs={"href": re.compile(self.__pattern__)}).text
+        
+        links = {}
+        out = re.compile("http://www.hoerbuch.in/cj/out.php\?pct=\d+&url=(http://rs\.hoerbuch\.in/.*)")
+        for a in soup.findAll("a", attrs={"href": out}):
+            part = int(a.text.replace("Part ", ""))
+            if not part in links.keys():
+                links[part] = []
+            links[part].append(out.search(a["href"]).group(1))
+        
+        sortedLinks = {}
+        for mirrors in links.values():
+            decrypted_mirrors = []
+            for u in mirrors:
+                src = self.load(u)
+                decrypted_mirrors.append(re.search('<FORM ACTION="(http://.*?)" METHOD="post"', src).group(1))
+            
+            results = self.core.pluginManager.parseUrls(decrypted_mirrors)
+        
+            for url, hoster in results:
+                if not sortedLinks.has_key(hoster):
+                    sortedLinks[hoster] = []
+                sortedLinks[hoster].append(url)
+        
+        for hoster, urls in sortedLinks.iteritems():
+            self.packages.append(("%s (%s)" % (package_base, hoster), urls, self.pyfile.package().folder))
 
-    def __init__(self, parent):
-        Crypter.__init__(self, parent)
-        self.parent = parent
-        self.html = None
-
-    def download_html(self):
-        url = self.parent.url
-        self.html = self.req.load(url)
-
-    def file_exists(self):
-        """ returns True or False
-        """
-        self.download_html()
-        if re.search(r"Download", self.html) is not None:
-            return True
-        return False
-
-    def proceed(self, url, location):
-        temp_links = []
-        download_container = ("Download", "Mirror #1", "Mirror #2", "Mirror #3")
-        for container in download_container:
-            download_content = re.search("<BR><B>" + container + ":</B>(.*?)<BR><B>", self.html).group(1)
-            tmp = re.findall('<A HREF="http://www.hoerbuch.in/cj/out.php\?pct=\d+&url=(http://rs\.hoerbuch\.in/.+?)" TARGET="_blank">Part \d+</A>', download_content)
-            if tmp == []: continue
-            for link in tmp:
-                link_html = self.req.load(link, cookies=True)
-                temp_links.append(re.search('<FORM ACTION="(http://.*?)" METHOD="post"', link_html).group(1))
-            break
-
-        self.links = temp_links
-- 
cgit v1.2.3