def getHtml(url, cache=True):
try:
rawHtml = getText(url, cache=cache)
decodedHtml = None
if rawHtml is not None:
decodedHtml = decode_htmlentities(rawHtml)
except Exception, ex:
printl("Exception (ef): " + str(ex), __name__, "E")
printl("\tURL: " + str(Utf8.utf8ToLatin(url)), __name__, "E")
def getHtml(url, cache=True):
try:
rawHtml = getText(url, cache=cache)
decodedHtml = None
if rawHtml is not None:
decodedHtml = decode_htmlentities(rawHtml)
except Exception, ex:
printl("Exception (ef): " + str(ex), __name__, "E")
printl("\tURL: " + str(Utf8.utf8ToLatin(url)), __name__, "E")
def getMovieByTitle(self, mediaInfo):
if mediaInfo.isTypeSerie():
urlTitle = mediaInfo.SearchString
urlTitle = re.sub(" ", "+", urlTitle)
pageHtml = WebGrabber.getHtml(
re.sub("<title>", urlTitle, self.apiSearchTV))
if not pageHtml:
return mediaInfo
m = re.search(r'Most Popular TV Series With Title Matching',
pageHtml)
if m and m.group():
mediaInfo = self.parseAdvancedSearchResultScreen(
mediaInfo, pageHtml)
mediaInfo = self.getMoviesByImdbId(mediaInfo)
if mediaInfo.ImdbId != "tt0000000":
return mediaInfo
urlTitle = mediaInfo.SearchString
urlTitle = re.sub(" ", "+", urlTitle)
pageHtml = WebGrabber().grab(self.apiSearch + urlTitle)
if not pageHtml:
return mediaInfo
pageHtml = decode_htmlentities(pageHtml)
m = re.search(r'<title>IMDb Title Search</title>', pageHtml)
if m and m.group():
mediaInfo = self.parseSearchResultScreen(mediaInfo, pageHtml)
mediaInfo = self.getMoviesByImdbId(mediaInfo)
else:
#m = re.search(r'<title>.+?\(?P<year>\d{4}[\/IVX]*\).*?</title>', pageHtml)
#if m and m.group():
mediaInfo = self.parseDetailsScreen(mediaInfo, pageHtml)
return mediaInfo
def getMovieByTitle(self, mediaInfo):
if mediaInfo.isTypeSerie():
urlTitle = mediaInfo.SearchString
urlTitle = re.sub(" ", "+", urlTitle)
pageHtml = WebGrabber.getHtml(re.sub("<title>", urlTitle, self.apiSearchTV))
if not pageHtml:
return mediaInfo
m = re.search(r'Most Popular TV Series With Title Matching', pageHtml)
if m and m.group():
mediaInfo = self.parseAdvancedSearchResultScreen(mediaInfo, pageHtml)
mediaInfo = self.getMoviesByImdbId(mediaInfo)
if mediaInfo.ImdbId != "tt0000000":
return mediaInfo
urlTitle = mediaInfo.SearchString
urlTitle = re.sub(" ", "+", urlTitle)
pageHtml = WebGrabber().grab(self.apiSearch + urlTitle)
if not pageHtml:
return mediaInfo
pageHtml = decode_htmlentities(pageHtml)
m = re.search(r'<title>IMDb Title Search</title>', pageHtml)
if m and m.group():
mediaInfo = self.parseSearchResultScreen(mediaInfo, pageHtml)
mediaInfo = self.getMoviesByImdbId(mediaInfo)
else:
#m = re.search(r'<title>.+?\(?P<year>\d{4}[\/IVX]*\).*?</title>', pageHtml)
#if m and m.group():
mediaInfo = self.parseDetailsScreen(mediaInfo, pageHtml)
return mediaInfo
