def NewzNabPlus(book=None, host=None, api_key=None, searchType=None):
#logger.info('[NewzNabPlus] Searching term [%s] for author [%s] and title [%s] on host [%s] for a [%s] item' % (book['searchterm'], book['authorName'], book['bookName'], host, searchType))
logger.info('[NewzNabPlus] searchType [%s] with Host [%s] using api [%s] for item [%s]'%(searchType, host, api_key,str(book)))
results = []
params = ReturnSearchTypeStructure(api_key, book, searchType)
if not str(host)[:4] == "http":
host = 'http://' + host
URL = host + '/api?' + urllib.urlencode(params)
try :
request = urllib2.Request(URL)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST, lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', USER_AGENT)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".ProviderCache"), SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
try:
data = ElementTree.parse(resp)
except (urllib2.URLError, IOError, EOFError), e:
logger.warn('Error fetching data from %s: %s' % (host, e))
data = None
except Exception, e:
logger.error("Error 403 openning url")
data = None
def get_author_books(self, authorid=None, authorname=None, refresh=False):
api_hits = 0
URL = 'http://www.goodreads.com/author/list/' + authorid + '.xml?' + urllib.urlencode(
self.params)
#Artist is loading
myDB = database.DBConnection()
controlValueDict = {"AuthorID": authorid}
newValueDict = {"Status": "Loading"}
myDB.upsert("authors", newValueDict, controlValueDict)
try:
# Cache our request
request = urllib2.Request(URL)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST,
lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', USER_AGENT)
opener = urllib2.build_opener(
SimpleCache.CacheHandler(".AuthorCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
api_hits = api_hits + 1
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error fetching author info: " + str(e))
def NewzNab(book=None, newznabNumber=None):
if (newznabNumber == "1"):
HOST = lazylibrarian.NEWZNAB_HOST
logger.info('Searching for %s.' % book['searchterm'] + " at: " +
lazylibrarian.NEWZNAB_HOST)
if (newznabNumber == "2"):
HOST = lazylibrarian.NEWZNAB_HOST2
logger.info('Searching for %s.' % book['searchterm'] + " at: " +
lazylibrarian.NEWZNAB_HOST2)
results = []
if lazylibrarian.EBOOK_TYPE == None:
params = {
"t": "book",
"apikey": lazylibrarian.NEWZNAB_API,
#"cat": 7020,
"author": book['searchterm']
}
else:
params = {
"t": "search",
"apikey": lazylibrarian.NEWZNAB_API,
"cat": 7020,
"q": book['searchterm'],
"extended": 1,
}
if not str(HOST)[:4] == "http":
HOST = 'http://' + HOST
URL = HOST + '/api?' + urllib.urlencode(params)
try:
request = urllib2.Request(URL)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST,
lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', common.USER_AGENT)
opener = urllib2.build_opener(
SimpleCache.CacheHandler(".ProviderCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
try:
data = ElementTree.parse(resp)
except (urllib2.URLError, IOError, EOFError), e:
logger.warn('Error fetching data from %s: %s' %
(lazylibrarian.NEWZNAB_HOST, e))
data = None
except Exception, e:
logger.error("Error 403 openning url")
data = None
def get_author_books(self, authorid=None):
URL = 'http://www.goodreads.com/author/list/' + authorid + '.xml?' + urllib.urlencode(
self.params)
try:
# Cache our request
request = urllib2.Request(URL)
opener = urllib2.build_opener(
SimpleCache.CacheHandler(".AuthorCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error fetching author info: " + str(e))
def find_author_id(self):
URL = 'http://www.goodreads.com/api/author_url/?' + urllib.urlencode(
self.name) + '&' + urllib.urlencode(self.params)
logger.debug("Searching for author with name: %s" % self.name)
# Cache our request
request = urllib2.Request(URL)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".AuthorCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
try:
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error fetching authorid: " + str(e))
def find_book(self, bookid=None, queue=None):
threading.currentThread().name = "GR-ADD-BOOK"
myDB = database.DBConnection()
URL = 'https://www.goodreads.com/book/show/' + bookid + '?' + urllib.urlencode(self.params)
try:
# Cache our request
request = urllib2.Request(URL)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST, lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', USER_AGENT)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".AuthorCache"), SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error fetching book info: " + str(e))
def find_author_id(self):
URL = 'http://www.goodreads.com/api/author_url/' + urllib.quote(self.name) + '?' + urllib.urlencode(self.params)
logger.debug("Searching for author with name: %s" % self.name)
# Cache our request
request = urllib2.Request(URL)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST, lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', USER_AGENT)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".AuthorCache"), SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
try:
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error fetching authorid: " + str(e) + str(URL))
def get_author_info(self, authorid=None, authorname=None, refresh=False):
URL = 'http://www.goodreads.com/author/show/' + authorid + '.xml?' + urllib.urlencode(
self.params)
# Cache our request
request = urllib2.Request(URL)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".AuthorCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
try:
sourcexml = ElementTree.parse(resp)
rootxml = sourcexml.getroot()
resultxml = rootxml.find('author')
author_dict = {}
except Exception, e:
logger.error("Error fetching author ID: " + str(e))
def find_results(self, authorname=None, queue=None):
threading.currentThread().name = "GR-SEARCH"
resultlist = []
api_hits = 0
url = urllib.quote_plus(authorname.encode('utf-8'))
set_url = 'http://www.goodreads.com/search.xml?q=' + url + '&' + urllib.urlencode(self.params)
logger.info('Now searching GoodReads API with keyword: ' + authorname)
logger.debug('Searching for %s at: %s' % (authorname, set_url))
try:
try:
# Cache our request
request = urllib2.Request(set_url)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST, lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', USER_AGENT)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".AuthorCache"), SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
api_hits = api_hits + 1
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error finding results: " + str(e))
rootxml = sourcexml.getroot()
resultxml = rootxml.getiterator('work')
author_dict = []
resultcount = 0
for author in resultxml:
bookdate = "0001-01-01"
if (author.find('original_publication_year').text == None):
bookdate = "0000"
else:
bookdate = author.find('original_publication_year').text
authorNameResult = author.find('./best_book/author/name').text
booksub = ""
bookpub = ""
booklang = "en"
try:
bookimg = author.find('./best_book/image_url').text
if (bookimg == 'http://www.goodreads.com/assets/nocover/111x148.png'):
bookimg = 'images/nocover.png'
except KeyError:
bookimg = 'images/nocover.png'
except AttributeError:
bookimg = 'images/nocover.png'
try:
bookrate = author.find('average_rating').text
except KeyError:
bookrate = 0
bookpages = '0'
bookgenre = ''
bookdesc = ''
bookisbn = ''
booklink = 'http://www.goodreads.com/book/show/'+author.find('./best_book/id').text
if (author.find('./best_book/title').text == None):
bookTitle = ""
else:
bookTitle = author.find('./best_book/title').text
author_fuzz = fuzz.ratio(authorNameResult.lower(), authorname.lower())
book_fuzz = fuzz.ratio(bookTitle.lower(), authorname.lower())
try:
isbn_check = int(authorname[:-1])
if (len(str(isbn_check)) == 9) or (len(str(isbn_check)) == 12):
isbn_fuzz = int(100)
else:
isbn_fuzz = int(0)
except:
isbn_fuzz = int(0)
highest_fuzz = max(author_fuzz, book_fuzz, isbn_fuzz)
resultlist.append({
'authorname': author.find('./best_book/author/name').text,
'bookid': author.find('./best_book/id').text,
'authorid' : author.find('./best_book/author/id').text,
'bookname': bookTitle.encode("ascii", "ignore"),
'booksub': booksub,
'bookisbn': bookisbn,
'bookpub': bookpub,
'bookdate': bookdate,
'booklang': booklang,
'booklink': booklink,
'bookrate': float(bookrate),
'bookimg': bookimg,
'bookpages': bookpages,
'bookgenre': bookgenre,
'bookdesc': bookdesc,
'author_fuzz': author_fuzz,
'book_fuzz': book_fuzz,
'isbn_fuzz': isbn_fuzz,
'highest_fuzz': highest_fuzz,
'num_reviews': float(bookrate)
})
resultcount = resultcount+1
try:
time.sleep(1) #sleep 1 second to respect goodreads api terms
if (book.find('isbn13').text is not None):
BOOK_URL = 'http://www.goodreads.com/book/isbn?isbn=' + book.find('isbn13').text + '&' + urllib.urlencode(self.params)
logger.debug(u"Book URL: " + str(BOOK_URL))
try:
# Cache our request
request = urllib2.Request(BOOK_URL)
if lazylibrarian.PROXY_HOST:
request.set_proxy(lazylibrarian.PROXY_HOST, lazylibrarian.PROXY_TYPE)
request.add_header('User-Agent', USER_AGENT)
opener = urllib2.build_opener(SimpleCache.CacheHandler(".AuthorCache"), SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
except Exception, e:
logger.error("Error finding results: ", e)
BOOK_sourcexml = ElementTree.parse(resp)
BOOK_rootxml = BOOK_sourcexml.getroot()
bookLanguage = BOOK_rootxml.find('./book/language_code').text
logger.debug(u"language: " + str(bookLanguage))
else:
logger.debug("No ISBN provided, skipping")
continue
except Exception, e:
try:
time.sleep(
1) #sleep 1 second to respect goodreads api terms
if (book.find('isbn13').text is not None):
BOOK_URL = 'http://www.goodreads.com/book/isbn?isbn=' + book.find(
'isbn13').text + '&' + urllib.urlencode(
self.params)
logger.debug(u"Book URL: " + str(BOOK_URL))
try:
# Cache our request
request = urllib2.Request(BOOK_URL)
opener = urllib2.build_opener(
SimpleCache.CacheHandler(".AuthorCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
except Exception, e:
logger.error("Error finding results: ", e)
BOOK_sourcexml = ElementTree.parse(resp)
BOOK_rootxml = BOOK_sourcexml.getroot()
bookLanguage = BOOK_rootxml.find(
'./book/language_code').text
logger.debug(u"language: " + str(bookLanguage))
else:
logger.debug("No ISBN provided, skipping")
continue
def find_results(self, authorname=None):
resultlist = []
logger.info(authorname)
url = urllib.quote_plus(authorname.encode('utf-8'))
set_url = 'http://www.goodreads.com/search.xml?q=' + url + '&' + urllib.urlencode(
self.params)
logger.info('Searching for author at: %s' % set_url)
try:
try:
# Cache our request
request = urllib2.Request(set_url)
opener = urllib2.build_opener(
SimpleCache.CacheHandler(".AuthorCache"),
SimpleCache.ThrottlingProcessor(5))
resp = opener.open(request)
sourcexml = ElementTree.parse(resp)
except Exception, e:
logger.error("Error finding results: " + str(e))
rootxml = sourcexml.getroot()
resultxml = rootxml.getiterator('work')
author_dict = []
resultcount = 0
for author in resultxml:
bookdate = "0001-01-01"
if (author.find('original_publication_year').text == None):
bookdate = "0000"
else:
bookdate = author.find('original_publication_year').text
authorNameResult = author.find('./best_book/author/name').text
booksub = ""
bookpub = ""
booklang = "en"
try:
bookimg = author.find('./best_book/image_url').text
if (bookimg ==
'http://www.goodreads.com/assets/nocover/111x148.png'
):
bookimg = 'images/nocover.png'
except KeyError:
bookimg = 'images/nocover.png'
except AttributeError:
bookimg = 'images/nocover.png'
try:
bookrate = author.find('average_rating').text
except KeyError:
bookrate = 0
bookpages = '0'
bookgenre = ''
bookdesc = 'Not available'
bookisbn = author.find('./best_book/id').text
if (author.find('./best_book/title').text == None):
bookTitle = ""
else:
bookTitle = author.find('./best_book/title').text
resultlist.append({
'authorname':
author.find('./best_book/author/name').text,
'bookid':
author.find('./best_book/id').text,
'authorid':
author.find('./best_book/author/id').text,
'bookname':
bookTitle.encode("ascii", "ignore"),
'booksub':
booksub,
'bookisbn':
bookisbn,
'bookpub':
bookpub,
'bookdate':
bookdate,
'booklang':
booklang,
'booklink':
'/',
'bookrate':
float(bookrate),
'bookimg':
bookimg,
'bookpages':
bookpages,
'bookgenre':
bookgenre,
'bookdesc':
bookdesc
})
resultcount = resultcount + 1
