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

Get rid of cssselect in the amazon metadata download plugin

Browse Source
This commit is contained in:
Kovid Goyal 2015-02-20 18:24:42 +05:30
parent 3c8984d2a5
commit 88dbbefa7b
1 changed files with 6 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
src/calibre/ebooks/metadata/sources/amazon.py
View File

@ -19,11 +19,6 @@ from calibre.ebooks.metadata.sources.base import (Source, Option, fixcase,
from calibre.ebooks.metadata.book.base import Metadata from calibre.ebooks.metadata.book.base import Metadata
from calibre.utils.localization import canonicalize_lang from calibre.utils.localization import canonicalize_lang
def CSSSelect(expr):
from cssselect import HTMLTranslator
from lxml.etree import XPath
return XPath(HTMLTranslator().css_to_xpath(expr))
class Worker(Thread): # Get details {{{ class Worker(Thread): # Get details {{{
''' '''
@ -269,6 +264,8 @@ class Worker(Thread): # Get details {{{
self.log.error(msg) self.log.error(msg)
return return
from css_selectors import Select
self.selector = Select(root)
self.parse_details(oraw, root) self.parse_details(oraw, root)
def parse_details(self, raw, root): def parse_details(self, raw, root):
@ -337,7 +334,7 @@ class Worker(Thread): # Get details {{{
self.log.exception('Error parsing cover for url: %r'%self.url) self.log.exception('Error parsing cover for url: %r'%self.url)
mi.has_cover = bool(self.cover_url) mi.has_cover = bool(self.cover_url)
non_hero = CSSSelect('div#bookDetails_container_div div#nonHeroSection')(root) non_hero = tuple(self.selector('div#bookDetails_container_div div#nonHeroSection'))
if non_hero: if non_hero:
# New style markup # New style markup
try: try:
@ -417,9 +414,9 @@ class Worker(Thread): # Get details {{{
return ans return ans
def parse_authors(self, root): def parse_authors(self, root):
matches = CSSSelect('#byline .author .contributorNameID')(root) matches = tuple(self.selector('#byline .author .contributorNameID'))
if not matches: if not matches:
matches = CSSSelect('#byline .author a.a-link-normal')(root) matches = tuple(self.selector('#byline .author a.a-link-normal'))
if matches: if matches:
authors = [self.totext(x) for x in matches] authors = [self.totext(x) for x in matches]
return [a for a in authors if a] return [a for a in authors if a]
@ -490,7 +487,7 @@ class Worker(Thread): # Get details {{{
def parse_comments(self, root): def parse_comments(self, root):
ans = '' ans = ''
ns = CSSSelect('#bookDescription_feature_div noscript')(root) ns = tuple(self.selector('#bookDescription_feature_div noscript'))
if ns: if ns:
ns = ns[0] ns = ns[0]
if len(ns) == 0 and ns.text: if len(ns) == 0 and ns.text:
@ -1125,13 +1122,6 @@ if __name__ == '__main__': # tests {{{
authors_test(['F. Scott Fitzgerald'])] authors_test(['F. Scott Fitzgerald'])]
), ),
( # A newer book
{'identifiers':{'amazon': 'B004JHY6OG'}},
[title_test('The Heroes', exact=False),
authors_test(['Joe Abercrombie'])]
),
] # }}} ] # }}}
de_tests = [ # {{{ de_tests = [ # {{{