def getMoviesByImdbID(self, info):
#print "getMoviesByImdbID", info.ImdbId
url = self.apiDetails
url = re.sub("<imdbid>", info.ImdbId, url)
html = WebGrabber.getHtml(url)
if html is None:
# print "if html is None"
return None;
tmp = self.getTag(info, html)
if tmp is not None:
info = tmp
tmp = self.getVotes(info, html)
if tmp is not None:
info = tmp
tmp = self.getTitle(info, html)
if tmp is not None:
info = tmp
tmp = self.getPlot(info, html)
if tmp is not None:
info = tmp
tmp = self.getRuntime(info, html)
if tmp is not None:
info = tmp
tmp = self.getGenre(info, html)
if tmp is not None:
info = tmp
return info;
def getMoviesByImdbID(self, info):
#print "getMoviesByImdbID", info.ImdbId
url = self.apiDetails
url = re.sub("<imdbid>", info.ImdbId, url)
html = WebGrabber.getHtml(url)
if html is None:
# print "if html is None"
return None
tmp = self.getTag(info, html)
if tmp is not None:
info = tmp
tmp = self.getVotes(info, html)
if tmp is not None:
info = tmp
tmp = self.getTitle(info, html)
if tmp is not None:
info = tmp
tmp = self.getPlot(info, html)
if tmp is not None:
info = tmp
tmp = self.getRuntime(info, html)
if tmp is not None:
info = tmp
tmp = self.getGenre(info, html)
if tmp is not None:
info = tmp
return info
def getSeasonAndEpisodeFromEpisodeName(self, info):
if info.SearchString is None or len(info.SearchString) == 0:
printl(" <- None (info.SearchString is None or len(info.SearchString) == 0)", self)
return (False, None)
url = self.apiSearch
url = re.sub("<search>", info.SearchString, url)
printl("Google-query: " + info.SearchString, self, "I")
html = WebGrabber.getHtml(url)
if html is None:
printl(" <- None (html is None)", self)
return (False, None)
# well there seems to be a problem with detecting tvshows,
#so lets build in a workaround, you will need at least 2 time the same
#season and episode before acepting it
count = 0
s = 0
e = 0
# Issue #205, efo => use only result tag
# htmlSplitted = html.split(self.DIV_RESULT_START)
htmlSplitted = html.split(self.DIV_RESULT_FLAG)
lobSkipEntry = True
for htmlSplitter in htmlSplitted:
# Skip first entry, since this mostly contain script stuff...
if lobSkipEntry == True:
lobSkipEntry = False
continue
htmlSplitter = htmlSplitter.strip()
# Issue #205, efo => don't split again, since we now already have a single line which can be checked...
#if htmlSplitter.startswith(self.DIV_RESULT_FLAG) is False:
# continue
#pos = htmlSplitter.find(self.DIV_RESULT_END)
#if pos < 0:
# continue
tmp = self.searchForSeasonAndEpisode(info, htmlSplitter.lower())
if tmp is not None:
info = tmp
if s == 0 or e == 0:
s = info.Season
e = info.Episode
if s == info.Season and e == info.Episode:
count = count + 1
if count == 2:
return (True, info)
else:
continue
printl(" <- None (eof)", self)
return (True, None)
def getSeasonAndEpisodeFromEpisodeName(self, info):
if info.SearchString is None or len(info.SearchString) == 0:
printl(" <- None (info.SearchString is None or len(info.SearchString) == 0)", self)
return (False, None)
url = self.apiSearch
url = re.sub("<search>", info.SearchString, url)
printl("Google-query: " + info.SearchString, self, "I")
html = WebGrabber.getHtml(url)
if html is None:
printl(" <- None (html is None)", self)
return (False, None)
# well there seems to be a problem with detecting tvshows,
#so lets build in a workaround, you will need at least 2 time the same
#season and episode before acepting it
count = 0
s = 0
e = 0
# Issue #205, efo => use only result tag
# htmlSplitted = html.split(self.DIV_RESULT_START)
htmlSplitted = html.split(self.DIV_RESULT_FLAG)
lobSkipEntry = True
for htmlSplitter in htmlSplitted:
# Skip first entry, since this mostly contain script stuff...
if lobSkipEntry == True:
lobSkipEntry = False
continue
htmlSplitter = htmlSplitter.strip()
# Issue #205, efo => don't split again, since we now already have a single line which can be checked...
#if htmlSplitter.startswith(self.DIV_RESULT_FLAG) is False:
# continue
#pos = htmlSplitter.find(self.DIV_RESULT_END)
#if pos < 0:
# continue
tmp = self.searchForSeasonAndEpisode(info, htmlSplitter.lower())
if tmp is not None:
info = tmp
if s == 0 or e == 0:
s = info.Season
e = info.Episode
if s == info.Season and e == info.Episode:
count = count + 1
if count == 2:
return (True, info)
else:
continue
printl(" <- None (eof)", self)
return (True, None)
def getMoviesByTitle(self, info):
if info.ImdbId != info.ImdbIdNull:
printl("IMDb-ID already set to '" + str(info.ImdbId) + "' - get movie by ID instead... ", self, "I")
info2 = self.getMoviesByImdbID(info)
if info2 is not None:
printl("Get movie by ID succeeded. ", self, "I")
return info2
url = self.apiSearch
url = re.sub("<search>", info.SearchString, url)
html = WebGrabber.getHtml(url)
if html is None:
printl("<- None (html is None)", self)
return None
if self.testNoResults in html:
printl("<- None (self.testNoResults in html)", self)
return None
#print "MIMDB seraches for ", info.is_Movie, info.is_Episode, info.is_Serie
year = info.Year
results = self.getResults(html)
printl("Results are: ", self)
for result in results:
printl("\t" + str(result), self)
for result in results:
if info.isTypeEpisode() or info.isTypeSerie():
if not result.IsTVSeries:
printl("Searched media is a TV-show - but result seems to be a movie => skip...", self, "I")
continue
else: # is_Movie
if result.IsTVSeries:
printl("Searched media is a movie - but result seems to be a TV-show => skip...", self, "I")
continue
# We check if year +-1, cause sometimes the year is wrong by one year
if year is None or year <= 0 or year == result.Year or (year+1) == result.Year or (year-1) == result.Year:
info.ImdbId = result.ImdbId
info.Title = result.Title
info.Year = result.Year
printl("Get movie by ID '" + str(info.ImdbId) + "'", self, "I")
tmp = self.getMoviesByImdbID(info)
if tmp is not None:
info = tmp
printl("Get movie by ID succeeded: " + str(info.ImdbId) + "'", self, "I")
return info
printl("<- None (eof)", self)
return None
def getPlot(self, mediaInfo):
if mediaInfo.ImdbId == mediaInfo.ImdbIdNull:
return mediaInfo
pageHtml = WebGrabber.getHtml(self.apiImdbLookup + mediaInfo.ImdbId + "/plotsummary")
if not pageHtml:
return mediaInfo
m = re.search(r'<p class=\"plotpar\">\s*(?P<plot>[^<]+?)<i>', pageHtml)
if m and m.group("plot"):
mediaInfo.Plot = unicode(m.group("plot").strip())
return mediaInfo
def getPlot(self, mediaInfo):
if mediaInfo.ImdbId == mediaInfo.ImdbIdNull:
return mediaInfo
pageHtml = WebGrabber.getHtml(self.apiImdbLookup + mediaInfo.ImdbId +
"/plotsummary")
if not pageHtml:
return mediaInfo
m = re.search(r'<p class=\"plotpar\">\s*(?P<plot>[^<]+?)<i>', pageHtml)
if m and m.group("plot"):
mediaInfo.Plot = unicode(m.group("plot").strip())
return mediaInfo
def getMoviesByImdbId(self, mediaInfo):
if mediaInfo.ImdbId == mediaInfo.ImdbIdNull:
return mediaInfo
pageHtml = WebGrabber.getHtml(self.apiImdbLookup + mediaInfo.ImdbId)
if not pageHtml:
return mediaInfo
m = re.search(r'<title>.+?\(\d{4}[\/IVX]*\).*?</title>', pageHtml)
if m and m.group():
mediaInfo = self.parseDetailsScreen(mediaInfo, pageHtml)
return mediaInfo
def getMoviesByImdbId(self, mediaInfo):
if mediaInfo.ImdbId == mediaInfo.ImdbIdNull:
return mediaInfo
pageHtml = WebGrabber.getHtml(self.apiImdbLookup + mediaInfo.ImdbId)
if not pageHtml:
return mediaInfo
m = re.search(r'<title>.+?\(\d{4}[\/IVX]*\).*?</title>', pageHtml)
if m and m.group():
mediaInfo = self.parseDetailsScreen(mediaInfo, pageHtml)
return mediaInfo
def getAlternatives(self, info):
url = self.apiSearch
url = re.sub("<search>", info.SearchString, url)
html = WebGrabber.getHtml(url)
if html is None:
#print "MobileImdbComProvider::getAlternatives() <- html is None"
return None
if self.testNoResults in html:
#print "MobileImdbComProvider::getAlternatives() <- self.testNoResults in html"
return None
results = self.getResults(html)
return results
def getAlternatives(self, info):
url = self.apiSearch
url = re.sub("<search>", info.SearchString, url)
html = WebGrabber.getHtml(url)
if html is None:
#print "MobileImdbComProvider::getAlternatives() <- html is None"
return None
if self.testNoResults in html:
#print "MobileImdbComProvider::getAlternatives() <- self.testNoResults in html"
return None
results = self.getResults(html)
return results
def getEpisodeByImdbID(self, info, lang):
if info.Episode == -1 or info.Season == -1:
printl(" <- None (info.Episode == -1 or info.Season == -1)", self)
return None
url = self.apiEpisodeList
url = re.sub("<imdbid>", info.ImdbId, url)
url = re.sub("<lang>", lang, url)
html = WebGrabber.getHtml(url)
if html is None:
printl(" <- None (html is None)", self)
return None
results = self.getResults(html, lang)
for result in results:
if result.Season == info.Season and result.Episode == info.Episode:
return self.getMoviesByImdbID(info, lang, result.ImdbId)
printl(" <- None (eof)", self)
return None
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 getEpisodeByImdbID(self, info, lang):
if info.Episode == -1 or info.Season == -1:
printl(" <- None (info.Episode == -1 or info.Season == -1)", self)
return None
url = self.apiEpisodeList
url = re.sub("<imdbid>", info.ImdbId, url)
url = re.sub("<lang>", lang, url)
html = WebGrabber.getHtml(url)
if html is None:
printl(" <- None (html is None)", self)
return None
results = self.getResults(html, lang)
for result in results:
if result.Season == info.Season and result.Episode == info.Episode:
return self.getMoviesByImdbID(info, lang, result.ImdbId)
printl(" <- None (eof)", self)
return None
def getMoviesByImdbID(self, info, lang, imdbid=None):
url = self.apiPlot
if imdbid is not None:
url = re.sub("<imdbid>", imdbid, url)
else:
url = re.sub("<imdbid>", info.ImdbId, url)
url = re.sub("<lang>", lang, url)
html = WebGrabber.getHtml(url)
if html is None:
printl(" <- None (html is None)", self)
return None;
tmp = self.getTitle(info, html)
if tmp is not None:
info = tmp
tmp = self.getPlot(info, html)
if tmp is not None:
info = tmp
return info;
def getMoviesByImdbID(self, info, lang, imdbid=None):
url = self.apiPlot
if imdbid is not None:
url = re.sub("<imdbid>", imdbid, url)
else:
url = re.sub("<imdbid>", info.ImdbId, url)
url = re.sub("<lang>", lang, url)
html = WebGrabber.getHtml(url)
if html is None:
printl(" <- None (html is None)", self)
return None
tmp = self.getTitle(info, html)
if tmp is not None:
info = tmp
tmp = self.getPlot(info, html)
if tmp is not None:
info = tmp
return info
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 getMoviesByTitle(self, info):
if info.ImdbId != info.ImdbIdNull:
printl(
"IMDb-ID already set to '" + str(info.ImdbId) +
"' - get movie by ID instead... ", self, "I")
info2 = self.getMoviesByImdbID(info)
if info2 is not None:
printl("Get movie by ID succeeded. ", self, "I")
return info2
url = self.apiSearch
url = re.sub("<search>", info.SearchString, url)
html = WebGrabber.getHtml(url)
if html is None:
printl("<- None (html is None)", self)
return None
if self.testNoResults in html:
printl("<- None (self.testNoResults in html)", self)
return None
#print "MIMDB seraches for ", info.is_Movie, info.is_Episode, info.is_Serie
year = info.Year
results = self.getResults(html)
printl("Results are: ", self)
for result in results:
printl("\t" + str(result), self)
for result in results:
if info.isTypeEpisode() or info.isTypeSerie():
if not result.IsTVSeries:
printl(
"Searched media is a TV-show - but result seems to be a movie => skip...",
self, "I")
continue
else: # is_Movie
if result.IsTVSeries:
printl(
"Searched media is a movie - but result seems to be a TV-show => skip...",
self, "I")
continue
# We check if year +-1, cause sometimes the year is wrong by one year
if year is None or year <= 0 or year == result.Year or (
year + 1) == result.Year or (year - 1) == result.Year:
info.ImdbId = result.ImdbId
info.Title = result.Title
info.Year = result.Year
printl("Get movie by ID '" + str(info.ImdbId) + "'", self, "I")
tmp = self.getMoviesByImdbID(info)
if tmp is not None:
info = tmp
printl(
"Get movie by ID succeeded: " + str(info.ImdbId) + "'",
self, "I")
return info
printl("<- None (eof)", self)
return None
