def check_created_image_regex(first_image_url, second_image_url, regex):
matches = Regex.Matches(first_page_source._source, regex,
RegexOptions.IgnoreCase)
escaped_first_image_url = escape_uri_string(first_image_url)
escaped_second_image_url = escape_uri_string(second_image_url)
if matches.Count == 0:
return False, 0
else:
if debug:
print "\nFound " + str(
matches.Count
) + " match(es) on the first page with regex: " + regex
print "Captured: " + matches[0].Value
print "link group: " + matches[0].Groups["link"].Value
#We don't care if there is more than one result. As long as the first result is the correct image
result, image_uri = Uri.TryCreate(first_page_uri,
matches[0].Groups["link"].Value)
#Valid url and matches the input image url
if result and image_uri.AbsoluteUri in (first_image_url,
escaped_first_image_url):
if debug: print "Valid uri and matches image url"
else:
if debug: print "Not a valid uri or doesn't match image url"
return False, 0
matches_second = Regex.Matches(second_page_source._source, regex,
RegexOptions.IgnoreCase)
if matches_second.Count == 0:
if debug: print "No matches on the second page"
return False, 0
#Regex match on the second page. Same deal as above. We don't care if there is more than one result
if debug:
print "\nFound " + str(
matches_second.Count) + " match(es) on the second page"
print "Captured: " + matches_second[0].Value
print "link group: " + matches_second[0].Groups["link"].Value
result, image_uri = Uri.TryCreate(
second_page_uri, matches_second[0].Groups["link"].Value)
if result and image_uri.AbsoluteUri in (second_image_url,
escaped_second_image_url):
if debug:
print "Regex works on both pages and returns the correct image"
return True, matches.Count
else:
if debug: print "Invalid Uri or doesn't match the second image url"
return False, 0
return False, matches.Count
def browserEnum():
summary = printHeader("BROWSER ENUM")
regex = Regex('(http|ftp|https|file)://([\w_-]+(?:(?:\.[\w_-]+)+))([\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-])?')
#Active IE Urls
summary += printSubheader("ACTIVE EXPLORER URLS")
app = Activator.CreateInstance(Type.GetTypeFromProgID("Shell.Application"))
summary += "\n".join([w.LocationUrl() for w in app.Windows()])
#Chrome History
summary += printSubheader("\n\nChrome History")
try:
cHistPath = "{0}\Users\{1}\AppData\Local\Google\Chrome\User Data\Default\History".format(Env.GetEnvironmentVariable("systemdrive"), Env.UserName)
cHist = open(cHistPath, "r").read()
summary += "\n".join(["[*] {0}\n".format(m.Value) for m in regex.Matches(cHist)][-10:])
except:
pass
summary += printSubheader("\nChrome Bookmarks")
#Chrome Bookmarks
try:
cBMPath = "{0}\Users\{1}\AppData\Local\Google\Chrome\User Data\Default\Bookmarks".format(Env.GetEnvironmentVariable("systemdrive"), Env.UserName)
js = JavaScriptSerializer()
cBM = js.DeserializeObject(open(cBMPath, "r").read())
urls = cBM["roots"]["bookmark_bar"]["children"]
for url in urls:
u = url['url']
d = url['name']
summary += "[*] {0}\n{1}\n\n".format(d, u)
except:
pass
summary += printSubheader("Firefox History")
#Firefox History
try:
regex = Regex('(http|ftp|https|file)://([\w_-]+(?:(?:\.[\w_-]+)+))([\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-])?')
fHistPath = "{0}\Users\{1}\AppData\Roaming\Mozilla\Firefox\Profiles".format(Env.GetEnvironmentVariable("systemdrive"), Env.UserName)
for path in DirectoryInfo(fHistPath).EnumerateDirectories("*.default"):
places = open(path.FullName + "\places.sqlite", "r").read()
summary += "\n".join(["[*] {0}\n".format(m.Value) for m in regex.Matches(places)][:10])
except:
pass
summary += printSubheader("IE History")
typedUrlPath = "\Software\Microsoft\Internet Explorer\TypedURLs"
for sid in Registry.Users.GetSubKeyNames():
if sid != ".DEFAULT" and not sid.endswith("Classes"):
try:
typedUrlsKey = Registry.Users.OpenSubKey(sid + typedUrlPath)
if typedUrlsKey != None:
summary += "[{0}][{1}]\n".format(sid, SecurityIdentifier(sid.ToString()).Translate(NTAccount))
for value in typedUrlsKey.GetValueNames():
summary += "\t{0}\n".format(typedUrlsKey.GetValue(value))
summary += "\n"
except SystemError:
pass
return summary
def check_regex_against_source(regex, check_value, check_value2):
matches = Regex.Matches(first_page_source._source, regex._regex,
RegexOptions.IgnoreCase)
if matches.Count != 0:
if debug:
print "\n\nFound " + str(
matches.Count
) + " match(es) on the first page with regex: " + regex._regex
print "Captured: " + matches[0].Value
print "link group: " + matches[0].Groups["link"].Value
#We don't care if there is more than one result. As long as the first result is the correct image
result, result_uri = Uri.TryCreate(first_page_uri,
matches[0].Groups["link"].Value)
if result and result_uri.AbsoluteUri in (check_value, check_value2):
#Valid url and matches against the check_value
if debug: print "Valid uri"
else:
return False
matches_second = Regex.Matches(second_page_source._source,
regex._regex, RegexOptions.IgnoreCase)
if matches_second.Count == 0:
if debug: print "No matches found on the second page"
return False
#Regex match on the second page. Same deal as above. We don't care if there is more than one result
if debug:
print "\nFound " + str(
matches_second.Count) + " match(es) on the second page"
print "Captured: " + matches_second[0].Value
print "link group: " + matches_second[0].Groups["link"].Value
result, result_uri = Uri.TryCreate(
second_page_uri, matches_second[0].Groups["link"].Value)
if result:
regex._matches = matches.Count
if debug: print "Added to valid regex"
return regex
else:
if debug: print "Invalid uri"
return False
return False
def FindScanners(worker, books):
#Load the various settings. settings is a dict
settings = LoadSettings()
#Load the scanners
unformatedscanners = LoadListFromFile(SCANNERSFILE)
#Sort the scanners by length and reverse it. For example cl will come after clickwheel allowing them to be matched correctly.
unformatedscanners.sort(key=len, reverse=True)
#Format the scanners for use in the regex
scanners = "|".join(unformatedscanners)
scanners = "(?<Tags>" + scanners + ")"
#Load the blacklist and format it
blacklist = LoadListFromFile(BLACKLISTFILE)
blacklist.extend(LoadUserBlackListFromFile(USERBLACKLISTFILE))
formatedblacklist = "|".join(blacklist)
#Add in the blacklist
#These amazing regex are designed by the amazing Helmic.
pattern = r"(?:(?:__(?!.*__[^_]))|[(\[])(?!(?:" + formatedblacklist + r"|[\s_\-\|/,])+[)\]])(?<Tags>(?=[^()\[\]]*[^()\[\]\W\d_])[^()\[\]]{2,})[)\]]?"
replacePattern = r"(?:[^\w]|_|^)(?:" + formatedblacklist + r")(?:[^\w]|_|$)"
#Create the regex
regex = Regex(pattern, RegexOptions.IgnoreCase)
regexScanners = Regex(scanners, RegexOptions.IgnoreCase)
regexReplace = Regex(replacePattern, RegexOptions.IgnoreCase)
ComicBookFields = ComicRack.App.GetComicFields()
ComicBookFields.Remove("Scan Information")
ComicBookFields.Add("Language", "LanguageAsText")
for book in books:
#.net Regex
#Note that every possible match is found and then the last one is used.
#This is because in some rare cases more than one thing is mistakenly matched and the scanner is almost always the last match.
matches = regex.Matches(book.FileName)
unknowntag = ""
try:
match = matches[matches.Count - 1]
except ValueError:
#No match
#print "Trying the Scanners.txt list"
#Check the defined scanner names
match = regexScanners.Match(book.FileName)
#Still no match
if match.Success == False:
if settings["Unknown"] != "":
unknowntag = settings["Unknown"]
else:
continue
#Check if what was grabbed is a field in the comic
fields = []
for field in ComicBookFields.Values:
fields.append(unicode(getattr(book, field)).lower())
if match.Groups["Tags"].Value.lower() in fields:
print "Uh oh. That matched tag is in the info somewhere."
newmatch = False
for n in reversed(range(0, matches.Count - 1)):
if not matches[n].Groups["Tags"].Value.lower() in fields:
match = matches[n]
newmatch = True
break
if newmatch == False:
if settings["Unknown"] != "":
unknowntag = settings["Unknown"]
else:
continue
#Check if the match can be found in () in the series, title or altseries
titlefields = [
book.ShadowSeries, book.ShadowTitle, book.AlternateSeries
]
abort = False
for title in titlefields:
titleresult = re.search("\((?P<match>.*)\)", title)
if titleresult != None and titleresult.group(
"match").lower() == match.Groups["Tags"].Value.lower():
#The match is part of the title, series or altseries so skip it
print "The match is part of the title, series or altseries"
abort = True
break
if abort == True:
if settings["Unknown"] != "":
unknowntag = settings["Unknown"]
else:
continue
#Get a list of the old ScanInformation
oldtags = book.ScanInformation
ListOfTagsTemp = oldtags.split(",")
if '' in ListOfTagsTemp:
ListOfTagsTemp.remove('')
ListOfTags = []
if ListOfTagsTemp != []:
for indtag in ListOfTagsTemp:
ListOfTags.append(indtag.strip())
#Create our new tag
if unknowntag != "":
newtag = settings["Prefix"] + unknowntag
else:
newtag = settings["Prefix"] + regexReplace.Replace(
match.Groups["Tags"].Value.strip("_, "), "")
if newtag not in ListOfTags:
ListOfTags.append(newtag)
#Sort alphabeticaly to be neat
ListOfTags.sort()
#Add to ScanInformation field
book.ScanInformation = ", ".join(ListOfTags)