def GetMediaInfo(url, mediainfo, query_external=False):
"""
Retrieve meta data about the passed in LMWT item from a meta provider.
Additionally, for any info not returned by the meta provider, try to
collect the info directly from the LMWT item page.
"""
try:
if (mediainfo.id and re.match("tt\d+", mediainfo.id)):
imdb_id = mediainfo.id
else:
soup = BeautifulSoup(HTTP.Request(ICEFILMS_URL + url).content)
imdb_link = soup.find('a','iframe')['href']
imdb_id = re.search("(tt\d+)", str(imdb_link)).group()
if (query_external):
# Construct kwargs.
kwargs = {}
kwargs['imdb_id'] = imdb_id
kwargs['season'] = mediainfo.season
if hasattr(mediainfo, 'show_name'):
kwargs['show_name'] = mediainfo.show_name
if hasattr(mediainfo, 'ep_num'):
kwargs['ep_num'] = mediainfo.ep_num
#Log("Query-ing External Provider. Args:" + str(kwargs))
mediainfo = DBProvider().GetProvider(mediainfo.type).RetrieveItemFromProvider(**kwargs)
#Log(str(mediainfo))
else:
mediainfo.id = imdb_id
return mediainfo
except Exception, ex:
Log.Exception("Error whilst retrieveing media info")
return None
def GetMediaInfo(url, mediainfo, query_external=False):
"""
Retrieve meta data about the passed in LMWT item from a meta provider.
Additionally, for any info not returned by the meta provider, try to
collect the info directly from the LMWT item page.
"""
try:
if (mediainfo.id and re.match("tt\d+", mediainfo.id)):
imdb_id = mediainfo.id
else:
soup = BeautifulSoup(HTTP.Request(ICEFILMS_URL + url).content)
imdb_link = soup.find('a', 'NOiframe')['href']
imdb_id = re.search("(tt\d+)", str(imdb_link)).group()
if (query_external):
# Construct kwargs.
kwargs = {}
kwargs['imdb_id'] = imdb_id
kwargs['season'] = mediainfo.season
if hasattr(mediainfo, 'show_name'):
kwargs['show_name'] = mediainfo.show_name
if hasattr(mediainfo, 'ep_num'):
kwargs['ep_num'] = mediainfo.ep_num
#Log("Query-ing External Provider. Args:" + str(kwargs))
mediainfo = DBProvider().GetProvider(
mediainfo.type).RetrieveItemFromProvider(**kwargs)
#Log(str(mediainfo))
else:
mediainfo.id = imdb_id
return mediainfo
except Exception, ex:
Log.Exception("Error whilst retrieveing media info")
return None
def GetMediaInfo(url, mediainfo, query_external=False):
"""
Retrieve meta data about the passed in LMWT item from a meta provider.
Additionally, for any info not returned by the meta provider, try to
collect the info directly from the LMWT item page.
"""
# The description meta header for some shows inserts random double quotes in the
# content which breaks the parsing of the page. Work around that by simply
# removing the head section in which the meta elements are contained.
headMassage = [(re.compile('<head>(.*)</head>', re.S), lambda match: '')]
soupMassage = copy.copy(BeautifulSoup.MARKUP_MASSAGE)
soupMassage.extend(headMassage)
soup = BeautifulSoup(HTTP.Request(Dict['LMWT_URL'] + url).content,
markupMassage=soupMassage)
try:
imdb_id = None
try:
imdb_link = soup.find('div', 'mlink_imdb').a['href']
imdb_id = re.search("(tt\d+)", str(imdb_link)).group()
except:
pass
# Construct kwargs.
kwargs = {}
kwargs['imdb_id'] = imdb_id
kwargs['show_name'] = mediainfo.show_name
kwargs['season'] = mediainfo.season
if hasattr(mediainfo, 'ep_num'):
kwargs['ep_num'] = mediainfo.ep_num
if (query_external):
#Log("Query-ing External Provider")
mediainfo_ret = DBProvider().GetProvider(
mediainfo.type).RetrieveItemFromProvider(**kwargs)
#Log(str(mediainfo))
else:
mediainfo_ret = MediaInfo()
mediainfo_ret.id = imdb_id
# Also parse the LMWT page and extract out any info not set by the meta provider.
info_div = soup.find('div', 'movie_info')
# First, extract out description...
info = {}
info['Description:'] = info_div.find('td', {'colspan': '2'}).text
# Then, ratings....
info['Rating:'] = info_div.find('li', 'current-rating').text
# Extract out any other info.
for row in info_div.findAll('tr'):
row_items = row.findAll('td')
if len(row_items) <> 2 or "colspan" in str(row_items[0]):
continue
info[row_items[0].text] = row_items[1].text
# Map available extracted info back to the media info object.
# First, define the mapping between LMWT items and media info and an additional function
# to extract out sane info out of the LMWT data.
item_map = {
'Description:':
['summary', lambda x: Utils.decode_htmlentities(x)],
'Air Date:':
['releasedate', lambda x: datetime.strptime(x, '%B %d, %Y')],
'Runtime:': [
'duration',
lambda x: int(re.search("(\d*)", x).group(0)) * 60 * 1000
if int(re.search("(\d*)", x).group(0)
) * 60 * 1000 < sys.maxint else 0
],
'Rating:': [
'rating',
lambda x: float(re.search("([\d\.]+)", x).group(0)) * 2
],
'Title:': ['title', lambda x: decode_htmlentities(x)],
}
# For each extracted item from LMWT...
for lmwt_item in info.keys():
#Log("Processing: " + lmwt_item)
# Look for matching entry in map...
if lmwt_item not in item_map.keys():
#Log("Not processing - no mapping")
continue
mi_item = item_map[lmwt_item]
if (mi_item is None):
#Log("Couldn't find a mi attr!")
continue
try:
# And see if it's already set in the mediaInfo object.
mi_val = getattr(mediainfo_ret, mi_item[0], None)
#Log("Current mi value: " + str(mi_val))
# And set it if it's not already.
if (not mi_val):
#Log("Setting mi attr " + mi_item[0] + " to: " + str(mi_item[1](info[lmwt_item])))
setattr(mediainfo_ret, mi_item[0],
mi_item[1](info[lmwt_item]))
except Exception, ex:
#Log.Exception("Error whilst reading in info from LMWT Page. Field " + lmwt_item)
pass
return mediainfo_ret
def GetMediaInfo(url, mediainfo, query_external=False):
"""
Retrieve meta data about the passed in LMWT item from a meta provider.
Additionally, for any info not returned by the meta provider, try to
collect the info directly from the LMWT item page.
"""
# The description meta header for some shows inserts random double quotes in the
# content which breaks the parsing of the page. Work around that by simply
# removing the head section in which the meta elements are contained.
headMassage = [(re.compile('<head>(.*)</head>', re.S), lambda match: '')]
soupMassage = copy.copy(BeautifulSoup.MARKUP_MASSAGE)
soupMassage.extend(headMassage)
soup = BeautifulSoup(HTTP.Request(Dict['LMWT_URL'] + url).content, markupMassage=soupMassage)
try:
imdb_id = None
try:
imdb_link = soup.find('div','mlink_imdb').a['href']
imdb_id = re.search("(tt\d+)", str(imdb_link)).group()
except:
pass
# Construct kwargs.
kwargs = {}
kwargs['imdb_id'] = imdb_id
kwargs['show_name'] = mediainfo.show_name
kwargs['season'] = mediainfo.season
if hasattr(mediainfo, 'ep_num'):
kwargs['ep_num'] = mediainfo.ep_num
if (query_external):
#Log("Query-ing External Provider")
mediainfo_ret = DBProvider().GetProvider(mediainfo.type).RetrieveItemFromProvider(**kwargs)
#Log(str(mediainfo))
else:
mediainfo_ret = MediaInfo()
mediainfo_ret.id = imdb_id
# Also parse the LMWT page and extract out any info not set by the meta provider.
info_div = soup.find('div', 'movie_info')
# First, extract out description...
info = {}
info['Description:'] = info_div.find('td', { 'colspan': '2' }).text
# Then, ratings....
info['Rating:'] = info_div.find('li', 'current-rating').text
# Extract out any other info.
for row in info_div.findAll('tr'):
row_items = row.findAll('td')
if len(row_items) <> 2 or "colspan" in str(row_items[0]):
continue
info[row_items[0].text] = row_items[1].text
# Map available extracted info back to the media info object.
# First, define the mapping between LMWT items and media info and an additional function
# to extract out sane info out of the LMWT data.
item_map = {
'Description:' : ['summary', lambda x: Utils.decode_htmlentities(x)],
'Air Date:' : ['releasedate', lambda x: datetime.strptime(x, '%B %d, %Y')],
'Runtime:' : ['duration', lambda x: int(re.search("(\d*)", x).group(0)) * 60 * 1000 if int(re.search("(\d*)", x).group(0)) * 60 * 1000 < sys.maxint else 0],
'Rating:' : ['rating', lambda x: float(re.search("([\d\.]+)", x).group(0)) * 2],
'Title:': ['title', lambda x: decode_htmlentities(x)],
}
# For each extracted item from LMWT...
for lmwt_item in info.keys():
#Log("Processing: " + lmwt_item)
# Look for matching entry in map...
if lmwt_item not in item_map.keys():
#Log("Not processing - no mapping")
continue
mi_item = item_map[lmwt_item]
if (mi_item is None):
#Log("Couldn't find a mi attr!")
continue
try:
# And see if it's already set in the mediaInfo object.
mi_val = getattr(mediainfo_ret, mi_item[0], None)
#Log("Current mi value: " + str(mi_val))
# And set it if it's not already.
if (not mi_val):
#Log("Setting mi attr " + mi_item[0] + " to: " + str(mi_item[1](info[lmwt_item])))
setattr(mediainfo_ret, mi_item[0], mi_item[1](info[lmwt_item]))
except Exception, ex:
#Log.Exception("Error whilst reading in info from LMWT Page. Field " + lmwt_item)
pass
return mediainfo_ret
