FIX:(#281) Re-downloading random issues (adding to Wanted list), FIX:(#383) Filechecker should now pick up special characters

mylar/comicbookdb.py

@@ -142,12 +142,12 @@ def IssueDetails(cbdb_id):
 
     while (i < noresults):
         resultit = tableno[i]   # 7th table, 1st set of tr (which indicates an issue).
-        #print ("resultit: " + str(resultit))
+        print ("resultit: " + str(resultit))
         issuet = resultit.find("a", {"class" : "page_link" })  # gets the issue # portion
         try:
             issue = issuet.findNext(text=True)
         except:
-            #print ("blank space - skipping")
+            print ("blank space - skipping")
             i+=1
             continue
         if 'annual' not in issue.lower(): 
@@ -161,9 +161,13 @@ def IssueDetails(cbdb_id):
         #since we don't know which one contains the story arc, we need to iterate through to find it
         #we need to know story arc, because the following td is the Publication Date
         n=0
+        issuetitle = 'None'
         while (n < lengtht):
             storyt = lent[n] # 
-            #print ("storyt: " + str(storyt))
+            print ("storyt: " + str(storyt))
+            if 'issue.php' in storyt:
+                issuetitle = storyt.findNext(text=True)
+                print ("title:" + issuetitle)
             if 'storyarc.php' in storyt:
                 #print ("found storyarc")
                 storyarc = storyt.findNext(text=True)
@@ -174,15 +178,25 @@ def IssueDetails(cbdb_id):
         publen = len(pubd) # find the # of <td>'s
         pubs = pubd[publen-1] #take the last <td> which will always contain the publication date
         pdaters = pubs.findNext(text=True) #get the actual date :)
-        pubdate = re.sub("[^0-9]", "", pdaters)
+        basmonths = {'january':'01','february':'02','march':'03','april':'04','may':'05','june':'06','july':'07','august':'09','september':'10','october':'11','december':'12'}
+        for numbs in basmonths:
+            if numbs in pdaters.lower():
+                pconv = basmonths[numbs]
+                ParseYear = re.sub('/s','',pdaters[-5:])
+                pubdate= str(ParseYear) + "-" + str(pconv)
+                #logger.fdebug("!success - Publication date: " + str(ParseDate))
+
+        #pubdate = re.sub("[^0-9]", "", pdaters)
         print ("Issue : " + str(issue) + "  (" + str(pubdate) + ")")
-  
+        print ("Issuetitle " + str(issuetitle))
+
         annualslist.append({
-            'AnnualIssue':             str(issue),
-            'AnnualDate':              pubdate
+            'AnnualIssue':  str(issue),
+            'AnnualTitle':  issuetitle,
+            'AnnualDate':   str(pubdate)
             })
         gcount+=1 
-
+        print("annualslist appended...")
         i+=1
 
     annuals['annualslist'] = annualslist

mylar/filechecker.py

@@ -41,12 +41,12 @@ def listFiles(dir,watchcomic,AlternateSearch=None):
     comiclist = []
     comiccnt = 0
     not_these = ['\#',
-               '\,',
+               ',',
                '\/',
                '\:',
                '\;',
                '.',
-               '\-',
+               '-',
                '\!',
                '\$',
                '\%',
@@ -76,7 +76,6 @@ def listFiles(dir,watchcomic,AlternateSearch=None):
                     #print (subit + "  - assuming versioning. Removing from initial search pattern.")
                     subname = re.sub(str(subit), '', subname)
                     volrem = subit
-                    #print ("removed " + str(volrem) + " from filename wording")
                 if subit.lower()[:3] == 'vol':
                     #if in format vol.2013 etc
                     #because the '.' in Vol. gets removed, let's loop thru again after the Vol hit to remove it entirely
@@ -84,7 +83,10 @@ def listFiles(dir,watchcomic,AlternateSearch=None):
                     subname = re.sub(subit, '', subname)
                     volrem = subit
 
-        subname = re.sub('\_', ' ', subname)
+        #remove the brackets..
+        subname = re.findall('[^()]+', subname)
+        logger.fdebug("subname no brackets: " + str(subname[0]))
+        subname = re.sub('\_', ' ', subname[0])
         nonocount = 0
         for nono in not_these:
             if nono in subname:
@@ -98,7 +100,7 @@ def listFiles(dir,watchcomic,AlternateSearch=None):
                     subname = re.sub(str(nono), ' ', subname)
                     nonocount = nonocount + subcnt
         #subname = re.sub('[\_\#\,\/\:\;\.\-\!\$\%\+\'\?\@]',' ', subname)
-        modwatchcomic = re.sub('[\_\#\,\/\:\;\.\-\!\$\%\+\'\?\@]', ' ', u_watchcomic)
+        modwatchcomic = re.sub('[\_\#\,\/\:\;\.\-\!\$\%\'\?\@]', ' ', u_watchcomic)
         detectand = False
         modwatchcomic = re.sub('\&', ' and ', modwatchcomic)
         modwatchcomic = re.sub('\s+', ' ', str(modwatchcomic)).strip()
@@ -117,7 +119,7 @@ def listFiles(dir,watchcomic,AlternateSearch=None):
             altsearchcomic = "127372873872871091383 abdkhjhskjhkjdhakajhf"
         #if '_' in subname:
         #    subname = subname.replace('_', ' ')
-        #logger.fdebug("watchcomic:" + str(modwatchcomic) + " ..comparing to found file: " + str(subname))
+        logger.fdebug("watchcomic:" + str(modwatchcomic) + " ..comparing to found file: " + str(subname))
         if modwatchcomic.lower() in subname.lower() or altsearchcomic.lower() in subname.lower():
             if 'annual' in subname.lower():
                 #print ("it's an annual - unsure how to proceed")

mylar/helpers.py

@@ -540,3 +540,19 @@ def updateComicLocation():
         #raise cherrypy.HTTPRedirect("config")
     return
 
+def cleanhtml(raw_html):
+    #cleanr = re.compile('<.*?>')
+    #cleantext = re.sub(cleanr, '', raw_html)
+    #return cleantext
+    from bs4 import BeautifulSoup
+
+    VALID_TAGS = ['div', 'p']
+
+    soup = BeautifulSoup(raw_html)
+
+    for tag in soup.findAll('p'):
+        if tag.name not in VALID_TAGS:
+            tag.replaceWith(tag.renderContents())
+    flipflop = soup.renderContents()
+    print flipflop
+    return flipflop

mylar/webserve.py

@@ -616,13 +616,15 @@ class WebInterface(object):
         mvupcome = myDB.select("SELECT * from upcoming WHERE IssueDate < date('now') order by IssueDate DESC")
         #get the issue ID's
         for mvup in mvupcome:
-            myissue = myDB.action("SELECT * FROM issues WHERE Issue_Number=?", [mvup['IssueNumber']]).fetchone()
+            myissue = myDB.action("SELECT * FROM issues WHERE IssueID=?", [mvup['IssueID']]).fetchone()
+            #myissue =  myDB.action("SELECT * FROM issues WHERE Issue_Number=?", [mvup['IssueNumber']]).fetchone()
+
             if myissue is None: pass
             else:
-                #print ("ComicName: " + str(myissue['ComicName']))
-                #print ("Issue number : " + str(myissue['Issue_Number']) )
+                logger.fdebug("--Updating Status of issues table because of Upcoming status--")
+                logger.fdebug("ComicName: " + str(myissue['ComicName']))
+                logger.fdebug("Issue number : " + str(myissue['Issue_Number']) )
  
-
                 mvcontroldict = {"IssueID":    myissue['IssueID']}
                 mvvalues = {"ComicID":         myissue['ComicID'],
                             "Status":          "Wanted"}
@@ -1211,6 +1213,7 @@ class WebInterface(object):
                 soma,noids = librarysync.libraryScan()
             except Exception, e:
                 logger.error('Unable to complete the scan: %s' % e)
+                return
             if soma == "Completed":
                 print ("sucessfully completed import.")
             else:
@@ -1253,8 +1256,8 @@ class WebInterface(object):
                 # unzip -z filename.cbz < /dev/null  will remove the comment field, and thus the metadata.
 
                     
-                self.importResults()
-
+                #self.importResults()
+                raise cherrypy.HTTPRedirect("importResults")
         if redirect:
             raise cherrypy.HTTPRedirect(redirect)
         else: