Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Minor fix for nicebooks.py

Browse Source
This commit is contained in:
Sengian 2010-11-21 01:28:56 +01:00
parent eb4e7154db
commit fd711e6075
1 changed files with 23 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
src/calibre/ebooks/metadata/nicebooks.py
View File

@ -52,7 +52,7 @@ class NiceBooksCovers(CoverDownload):
br = browser() br = browser()
try: try:
entry = Query(isbn=mi.isbn, max_results=1)(br, False, timeout)[0] entry = Query(isbn=mi.isbn, max_results=1)(br, False, timeout)[0]
if Covers(isbn)(entry).check_cover(): if Covers(mi.isbn)(entry).check_cover():
self.debug('cover for', mi.isbn, 'found') self.debug('cover for', mi.isbn, 'found')
ans.set() ans.set()
except Exception, e: except Exception, e:
@ -64,7 +64,7 @@ class NiceBooksCovers(CoverDownload):
br = browser() br = browser()
try: try:
entry = Query(isbn=mi.isbn, max_results=1)(br, False, timeout)[0] entry = Query(isbn=mi.isbn, max_results=1)(br, False, timeout)[0]
cover_data, ext = Covers(isbn)(entry).get_cover(br, timeout) cover_data, ext = Covers(mi.isbn)(entry).get_cover(br, timeout)
if not ext: if not ext:
ext = 'jpg' ext = 'jpg'
result_queue.put((True, cover_data, ext, self.name)) result_queue.put((True, cover_data, ext, self.name))
@ -109,20 +109,12 @@ class Query(object):
self.max_results = int(max_results) self.max_results = int(max_results)
q = ''
if isbn is not None: if isbn is not None:
q += isbn q = isbn
else: else:
q = ' '.join([i for i in (title, author, publisher, keywords) \
if title is not None: if i is not None])
q += title
if author is not None:
q += author
if publisher is not None:
q += publisher
if keywords is not None:
q += keywords
if isinstance(q, unicode): if isinstance(q, unicode):
q = q.encode('utf-8') q = q.encode('utf-8')
self.urldata = 'search?' + urlencode({'q':q,'s':'Rechercher'}) self.urldata = 'search?' + urlencode({'q':q,'s':'Rechercher'})
@ -185,15 +177,15 @@ class ResultList(list):
BASE_URL = 'http://fr.nicebooks.com' BASE_URL = 'http://fr.nicebooks.com'
def __init__(self): def __init__(self):
self.repub = re.compile(r'\s*.diteur\s*', re.I) self.repub = re.compile(u'\s*.diteur\s*', re.I)
self.reauteur = re.compile(r'\s*auteur.*', re.I) self.reauteur = re.compile(u'\s*auteur.*', re.I)
self.reautclean = re.compile(r'\s*\(.*\)\s*') self.reautclean = re.compile(u'\s*\(.*\)\s*')
def get_title(self, entry): def get_title(self, entry):
title = deepcopy(entry.find("div[@id='book-info']")) title = deepcopy(entry.find("div[@id='book-info']"))
title.remove(title.find("dl[@title='Informations sur le livre']")) title.remove(title.find("dl[@title='Informations sur le livre']"))
title = ' '.join([i.text_content() for i in title.iterchildren()]) title = ' '.join([i.text_content() for i in title.iterchildren()])
return title.replace('\n', '') return unicode(title.replace('\n', ''))
def get_authors(self, entry): def get_authors(self, entry):
author = entry.find("div[@id='book-info']/dl[@title='Informations sur le livre']") author = entry.find("div[@id='book-info']/dl[@title='Informations sur le livre']")
@ -203,7 +195,7 @@ class ResultList(list):
elt = x.getnext() elt = x.getnext()
i = 0 i = 0
while elt.tag <> 'dt' and i < 20: while elt.tag <> 'dt' and i < 20:
authortext.append(elt.text_content()) authortext.append(unicode(elt.text_content()))
elt = elt.getnext() elt = elt.getnext()
i += 1 i += 1
break break
@ -213,7 +205,7 @@ class ResultList(list):
def get_description(self, entry, verbose): def get_description(self, entry, verbose):
try: try:
return 'RESUME:\n' + entry.xpath("//p[@id='book-description']")[0].text return 'RESUME:\n' + unicode(entry.xpath("//p[@id='book-description']")[0].text)
except: except:
report(verbose) report(verbose)
return None return None
@ -225,15 +217,16 @@ class ResultList(list):
if self.repub.match(x.text): if self.repub.match(x.text):
publitext = x.getnext().text_content() publitext = x.getnext().text_content()
break break
return publitext return unicode(publitext).strip()
def get_date(self, entry, verbose): def get_date(self, entry, verbose):
date = entry.find("div[@id='book-info']/dl[@title='Informations sur le livre']") date = entry.find("div[@id='book-info']/dl[@title='Informations sur le livre']")
d = ''
for x in date.getiterator('dt'): for x in date.getiterator('dt'):
if x.text == 'Date de parution': if x.text == 'Date de parution':
d = x.getnext().text_content() d = x.getnext().text_content()
break break
if not len(d): if len(d) == 0:
return None return None
try: try:
default = utcnow().replace(day=15) default = utcnow().replace(day=15)
@ -252,8 +245,9 @@ class ResultList(list):
isbntext = x.getnext().text_content() isbntext = x.getnext().text_content()
if not check_isbn(isbntext): if not check_isbn(isbntext):
return None return None
isbntext = isbntext.replace('-', '')
break break
return isbntext return unicode(isbntext)
def get_language(self, entry): def get_language(self, entry):
language = entry.find("div[@id='book-info']/dl[@title='Informations sur le livre']") language = entry.find("div[@id='book-info']/dl[@title='Informations sur le livre']")
@ -262,7 +256,7 @@ class ResultList(list):
if x.text == 'Langue': if x.text == 'Langue':
langtext = x.getnext().text_content() langtext = x.getnext().text_content()
break break
return langtext return unicode(langtext).strip()
def fill_MI(self, entry, title, authors, verbose): def fill_MI(self, entry, title, authors, verbose):
mi = MetaInformation(title, authors) mi = MetaInformation(title, authors)
@ -371,12 +365,12 @@ class Covers(object):
def search(title=None, author=None, publisher=None, isbn=None, def search(title=None, author=None, publisher=None, isbn=None,
verbose=False, max_results=5, keywords=None): max_results=5, verbose=False, keywords=None):
br = browser() br = browser()
entries = Query(title=title, author=author, isbn=isbn, publisher=publisher, entries = Query(title=title, author=author, isbn=isbn, publisher=publisher,
keywords=keywords, max_results=max_results)(br, verbose) keywords=keywords, max_results=max_results)(br, verbose)
if entries is None: if entries is None or len(entries) == 0:
return return
#List of entry #List of entry
@ -434,6 +428,9 @@ def main(args=sys.argv):
report(True) report(True)
parser.print_help() parser.print_help()
return 1 return 1
if results is None or len(results) == 0:
print 'No result found for this search!'
return 0
for result in results: for result in results:
print unicode(result).encode(preferred_encoding, 'replace') print unicode(result).encode(preferred_encoding, 'replace')
covact = int(opts.covers) covact = int(opts.covers)