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

pep8

Browse Source
This commit is contained in:
Kovid Goyal 2017-02-26 13:00:36 +05:30
parent 4f5155d190
commit 4ae11fa295
1 changed files with 148 additions and 92 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

214
src/calibre/ebooks/metadata/sources/google.py
View File

@ -1,37 +1,34 @@
#!/usr/bin/env python2
# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import (unicode_literals, division, absolute_import,
print_function)
# License: GPLv3 Copyright: 2011, Kovid Goyal <kovid at kovidgoyal.net>
from __future__ import absolute_import, division, print_function, unicode_literals
__license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
import time, hashlib
import hashlib
import time
from functools import partial
from Queue import Queue, Empty
from Queue import Empty, Queue
from calibre.ebooks.metadata import check_isbn
from calibre.ebooks.metadata.sources.base import Source
from calibre.ebooks.metadata.book.base import Metadata
from calibre import as_unicode
from calibre.ebooks.chardet import xml_to_unicode
from calibre.ebooks.metadata import check_isbn
from calibre.ebooks.metadata.book.base import Metadata
from calibre.ebooks.metadata.sources.base import Source
from calibre.utils.cleantext import clean_ascii_chars
from calibre.utils.localization import canonicalize_lang
from calibre import as_unicode
NAMESPACES = {
'openSearch':'http://a9.com/-/spec/opensearchrss/1.0/',
'atom' : 'http://www.w3.org/2005/Atom',
'dc' : 'http://purl.org/dc/terms',
'gd' : 'http://schemas.google.com/g/2005'
}
'openSearch': 'http://a9.com/-/spec/opensearchrss/1.0/',
'atom': 'http://www.w3.org/2005/Atom',
'dc': 'http://purl.org/dc/terms',
'gd': 'http://schemas.google.com/g/2005'
}
def get_details(browser, url, timeout): # {{{
try:
raw = browser.open_novisit(url, timeout=timeout).read()
except Exception as e:
gc = getattr(e, 'getcode', lambda : -1)
gc = getattr(e, 'getcode', lambda: -1)
if gc() != 403:
raise
# Google is throttling us, wait a little
@ -39,6 +36,8 @@ def get_details(browser, url, timeout): # {{{
raw = browser.open_novisit(url, timeout=timeout).read()
return raw
# }}}
@ -83,11 +82,12 @@ def to_metadata(browser, log, entry_, timeout): # {{{
return None
mi = Metadata(title_, authors)
mi.identifiers = {'google':google_id}
mi.identifiers = {'google': google_id}
try:
raw = get_details(browser, id_url, timeout)
feed = etree.fromstring(xml_to_unicode(clean_ascii_chars(raw),
strip_encoding_pats=True)[0])
feed = etree.fromstring(
xml_to_unicode(clean_ascii_chars(raw), strip_encoding_pats=True)[0]
)
extra = entry(feed)[0]
except:
log.exception('Failed to get additional details for', mi.title)
@ -135,7 +135,7 @@ def to_metadata(browser, log, entry_, timeout): # {{{
default = utcnow().replace(day=15)
mi.pubdate = parse_date(pubdate, assume_utc=True, default=default)
except:
log.error('Failed to parse pubdate %r'%pubdate)
log.error('Failed to parse pubdate %r' % pubdate)
# Ratings
for x in rating(extra):
@ -149,11 +149,14 @@ def to_metadata(browser, log, entry_, timeout): # {{{
# Cover
mi.has_google_cover = None
for x in extra.xpath(
'//*[@href and @rel="http://schemas.google.com/books/2008/thumbnail"]'):
'//*[@href and @rel="http://schemas.google.com/books/2008/thumbnail"]'
):
mi.has_google_cover = x.get('href')
break
return mi
# }}}
@ -162,21 +165,23 @@ class GoogleBooks(Source):
name = 'Google'
description = _('Downloads metadata and covers from Google Books')
capabilities = frozenset(['identify', 'cover'])
touched_fields = frozenset(['title', 'authors', 'tags', 'pubdate',
'comments', 'publisher', 'identifier:isbn', 'rating',
'identifier:google', 'languages'])
capabilities = frozenset({'identify', 'cover'})
touched_fields = frozenset({
'title', 'authors', 'tags', 'pubdate', 'comments', 'publisher',
'identifier:isbn', 'rating', 'identifier:google', 'languages'
})
supports_gzip_transfer_encoding = True
cached_cover_url_is_reliable = False
GOOGLE_COVER = 'https://books.google.com/books?id=%s&printsec=frontcover&img=1'
DUMMY_IMAGE_MD5 = frozenset(['0de4383ebad0adad5eeb8975cd796657'])
DUMMY_IMAGE_MD5 = frozenset({'0de4383ebad0adad5eeb8975cd796657'})
def get_book_url(self, identifiers): # {{{
goog = identifiers.get('google', None)
if goog is not None:
return ('google', goog, 'https://books.google.com/books?id=%s'%goog)
return ('google', goog, 'https://books.google.com/books?id=%s' % goog)
# }}}
def create_query(self, log, title=None, authors=None, identifiers={}): # {{{
@ -185,39 +190,55 @@ class GoogleBooks(Source):
isbn = check_isbn(identifiers.get('isbn', None))
q = ''
if isbn is not None:
q += 'isbn:'+isbn
q += 'isbn:' + isbn
elif title or authors:
def build_term(prefix, parts):
return ' '.join('in'+prefix + ':' + x for x in parts)
return ' '.join('in' + prefix + ':' + x for x in parts)
title_tokens = list(self.get_title_tokens(title))
if title_tokens:
q += build_term('title', title_tokens)
author_tokens = self.get_author_tokens(authors,
only_first_author=True)
author_tokens = self.get_author_tokens(authors, only_first_author=True)
if author_tokens:
q += ('+' if q else '') + build_term('author',
author_tokens)
q += ('+' if q else '') + build_term('author', author_tokens)
if isinstance(q, unicode):
q = q.encode('utf-8')
if not q:
return None
return BASE_URL+urlencode({
'q':q,
'max-results':20,
'start-index':1,
'min-viewability':'none',
return BASE_URL + urlencode({
'q': q,
'max-results': 20,
'start-index': 1,
'min-viewability': 'none',
})
# }}}
def download_cover(self, log, result_queue, abort, # {{{
title=None, authors=None, identifiers={}, timeout=30, get_best_cover=False):
def download_cover( # {{{
self,
log,
result_queue,
abort,
title=None,
authors=None,
identifiers={},
timeout=30,
get_best_cover=False
):
cached_url = self.get_cached_cover_url(identifiers)
if cached_url is None:
log.info('No cached cover found, running identify')
rq = Queue()
self.identify(log, rq, abort, title=title, authors=authors,
identifiers=identifiers)
self.identify(
log,
rq,
abort,
title=title,
authors=authors,
identifiers=identifiers
)
if abort.is_set():
return
results = []
@ -226,8 +247,11 @@ class GoogleBooks(Source):
results.append(rq.get_nowait())
except Empty:
break
results.sort(key=self.identify_results_keygen(
title=title, authors=authors, identifiers=identifiers))
results.sort(
key=self.identify_results_keygen(
title=title, authors=authors, identifiers=identifiers
)
)
for mi in results:
cached_url = self.get_cached_cover_url(mi.identifiers)
if cached_url is not None:
@ -263,10 +287,18 @@ class GoogleBooks(Source):
url = self.cached_identifier_to_cover_url(goog)
return url
# }}}
def get_all_details(self, br, log, entries, abort, # {{{
result_queue, timeout):
def get_all_details( # {{{
self,
br,
log,
entries,
abort,
result_queue,
timeout
):
from lxml import etree
for relevance, i in enumerate(entries):
try:
@ -277,26 +309,37 @@ class GoogleBooks(Source):
for isbn in getattr(ans, 'all_isbns', []):
self.cache_isbn_to_identifier(isbn, goog)
if getattr(ans, 'has_google_cover', False):
self.cache_identifier_to_cover_url(goog,
self.GOOGLE_COVER%goog)
self.cache_identifier_to_cover_url(
goog, self.GOOGLE_COVER % goog
)
self.clean_downloaded_metadata(ans)
result_queue.put(ans)
except:
log.exception(
'Failed to get metadata for identify entry:',
etree.tostring(i))
'Failed to get metadata for identify entry:', etree.tostring(i)
)
if abort.is_set():
break
# }}}
def identify(self, log, result_queue, abort, title=None, authors=None, # {{{
identifiers={}, timeout=30):
def identify( # {{{
self,
log,
result_queue,
abort,
title=None,
authors=None,
identifiers={},
timeout=30
):
from lxml import etree
XPath = partial(etree.XPath, namespaces=NAMESPACES)
entry = XPath('//atom:entry')
query = self.create_query(log, title=title, authors=authors,
identifiers=identifiers)
query = self.create_query(
log, title=title, authors=authors, identifiers=identifiers
)
if not query:
log.error('Insufficient metadata to construct query')
return
@ -304,13 +347,15 @@ class GoogleBooks(Source):
try:
raw = br.open_novisit(query, timeout=timeout).read()
except Exception as e:
log.exception('Failed to make identify query: %r'%query)
log.exception('Failed to make identify query: %r' % query)
return as_unicode(e)
try:
parser = etree.XMLParser(recover=True, no_network=True)
feed = etree.fromstring(xml_to_unicode(clean_ascii_chars(raw),
strip_encoding_pats=True)[0], parser=parser)
feed = etree.fromstring(
xml_to_unicode(clean_ascii_chars(raw), strip_encoding_pats=True)[0],
parser=parser
)
entries = entry(feed)
except Exception as e:
log.exception('Failed to parse identify results')
@ -318,34 +363,45 @@ class GoogleBooks(Source):
if not entries and identifiers and title and authors and \
not abort.is_set():
return self.identify(log, result_queue, abort, title=title,
authors=authors, timeout=timeout)
return self.identify(
log,
result_queue,
abort,
title=title,
authors=authors,
timeout=timeout
)
# There is no point running these queries in threads as google
# throttles requests returning 403 Forbidden errors
self.get_all_details(br, log, entries, abort, result_queue, timeout)
return None
# }}}
if __name__ == '__main__': # tests {{{
# To run these test use: calibre-debug -e src/calibre/ebooks/metadata/sources/google.py
from calibre.ebooks.metadata.sources.test import (test_identify_plugin,
title_test, authors_test)
test_identify_plugin(GoogleBooks.name,
[
(
{'identifiers':{'isbn': '0743273567'}, 'title':'Great Gatsby',
'authors':['Fitzgerald']},
[title_test('The great gatsby', exact=True),
authors_test(['F. Scott Fitzgerald'])]
),
(
{'title': 'Flatland', 'authors':['Abbott']},
[title_test('Flatland', exact=False)]
),
])
from calibre.ebooks.metadata.sources.test import (
test_identify_plugin, title_test, authors_test
)
test_identify_plugin(
GoogleBooks.name, [
({
'identifiers': {
'isbn': '0743273567'
},
'title': 'Great Gatsby',
'authors': ['Fitzgerald']
}, [
title_test('The great gatsby', exact=True),
authors_test(['F. Scott Fitzgerald'])
]),
({
'title': 'Flatland',
'authors': ['Abbott']
}, [title_test('Flatland', exact=False)]),
]
)
# }}}