FIX:(#2164) When adding TPB series with collected information in the description, if there were bulleted items in the description in some cases would cause an error, FIX: When searching for TPBs, would incorrectly reference a portion of the publication date as the issue # when logging, FIX: When searching for TPBs make sure to only remove the issue number for relevant search queries, FIX: Adjust the parser to use correct hyphens instead of unicode version in all usable instances

mylar/cv.py

@@ -285,6 +285,7 @@ def GetComicInfo(comicid, dom, safechk=None):
 
     desdeck = 0
     #the description field actually holds the Volume# - so let's grab it
+    desc_soup = None
     try:
         descchunk = dom.getElementsByTagName('description')[0].firstChild.wholeText
         desc_soup = Soup(descchunk, "html.parser")
@@ -368,12 +369,21 @@ def GetComicInfo(comicid, dom, safechk=None):
         #logger.info('comic_desc: %s' % comic_desc)
         #logger.info('desclinks: %s' % desclinks)
         issue_list = []
+        micdrop = []
+        if desc_soup is not None:
+            #if it's point form bullets, ignore it cause it's not the current volume stuff.
+            test_it = desc_soup.find('ul')
+            if test_it:
+                for x in test_it.findAll('a'):
+                    micdrop.append(x['data-ref-id'])
+
         for fc in desclinks:
             #logger.info('fc: %s'  % fc)
             fc_id = fc['data-ref-id']
             #logger.info('fc_id: %s'  % fc_id)
+            if fc_id in micdrop:
+                continue
             fc_name = fc.findNext(text=True)
-            #logger.info('fc_name: %s'  % fc_name)
             if fc_id.startswith('4000'):
                 fc_cid = None
                 fc_isid = fc_id

mylar/filechecker.py

@@ -49,6 +49,7 @@ class FileChecker(object):
             self.og_watchcomic = watchcomic
             self.watchcomic = re.sub('\?', '', watchcomic).strip()  #strip the ? sepearte since it affects the regex.
             self.watchcomic = re.sub(u'\u2014', ' - ', watchcomic).strip()  #replace the \u2014 with a normal - because this world is f'd up enough to have something like that.
+            self.watchcomic = re.sub(u'\u2013', ' - ', watchcomic).strip()  #replace the \u2013 with a normal - because again, people are dumb.
             self.watchcomic = unicodedata.normalize('NFKD', self.watchcomic).encode('ASCII', 'ignore')
         else:
             self.watchcomic = None
@@ -97,7 +98,7 @@ class FileChecker(object):
             self.pp_mode = False
 
         self.failed_files = []
-        self.dynamic_handlers = ['/','-',':','\'',',','&','?','!','+','(',')','\u2014']
+        self.dynamic_handlers = ['/','-',':','\'',',','&','?','!','+','(',')','\u2014','\u2013']
         self.dynamic_replacements = ['and','the']
         self.rippers = ['-empire','-empire-hd','minutemen-','-dcp']
 
@@ -1355,6 +1356,7 @@ class FileChecker(object):
                             mod_watchcomic = mod_watchcomic[:wd] + spacer + mod_watchcomic[wd+len(wdrm):]
 
         series_name = re.sub(u'\u2014', ' - ', series_name)
+        series_name = re.sub(u'\u2013', ' - ', series_name)
         seriesdynamic_handlers_match = [x for x in self.dynamic_handlers if x.lower() in series_name.lower()]
         #logger.fdebug('series dynamic handlers recognized : ' + str(seriesdynamic_handlers_match))
         seriesdynamic_replacements_match = [x for x in self.dynamic_replacements if x.lower() in series_name.lower()]

mylar/search.py

@@ -379,8 +379,14 @@ def search_init(ComicName, IssueNumber, ComicYear, SeriesYear, Publisher, IssueD
                     if IssueNumber is not None:
                         issuedisplay = IssueNumber
                     else:
-                        issuedisplay = StoreDate[5:]
-                    logger.info('Could not find Issue %s of %s (%s) using %s [%s]' % (issuedisplay, ComicName, SeriesYear, searchprov, searchmode))
+                        if any([booktype == 'One-Shot', booktype == 'TPB']):
+                            issuedisplay = None
+                        else:
+                            issuedisplay = StoreDate[5:]
+                    if issuedisplay is None:
+                        logger.info('Could not find %s (%s) using %s [%s]' % (ComicName, SeriesYear, searchprov, searchmode))
+                    else:
+                        logger.info('Could not find Issue %s of %s (%s) using %s [%s]' % (issuedisplay, ComicName, SeriesYear, searchprov, searchmode))
                 prov_count+=1
 
             if findit['status'] is True:
@@ -1345,8 +1351,15 @@ def NZB_SEARCH(ComicName, IssueNumber, ComicYear, SeriesYear, Publisher, IssueDa
                             logger.fdebug("integer value of issue we have found : %s" % comintIss)
                         else:
                             comintIss = 11111111111
+
+                        #do this so that we don't touch the actual value but just use it for comparisons
+                        if parsed_comic['issue_number'] is None:
+                            pc_in = None
+                        else:
+                            pc_in = int(parsed_comic['issue_number'])
+
                         #issue comparison now as well
-                        if int(intIss) == int(comintIss) or all([cmloopit == 4, findcomiciss is None, parsed_comic['issue_number'] is None]):
+                        if int(intIss) == int(comintIss) or all([cmloopit == 4, findcomiciss is None, pc_in is None]) or all([cmloopit == 4, findcomiciss is None, pc_in == 1]):
                             nowrite = False
                             if all([nzbprov == 'torznab', 'worldwidetorrents' in entry['link']]):
                                 nzbid = generate_id(nzbprov, entry['id'])