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

Google books metadata plugin: Use the https URL from the Google books feed

Browse Source 
Fixes #1350 (Use HTTPS when downloading metadata via Google Books feed)
This commit is contained in:
Kovid Goyal 2021-02-07 12:44:43 +05:30
parent a5308d1dc7
commit b4cad0b8fa
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/calibre/ebooks/metadata/sources/google.py
View File

@ -68,6 +68,7 @@ def to_metadata(browser, log, entry_, timeout): # {{{
# items_per_page = XPath('//openSearch:itemsPerPage') # items_per_page = XPath('//openSearch:itemsPerPage')
entry = XPath('//atom:entry') entry = XPath('//atom:entry')
entry_id = XPath('descendant::atom:id') entry_id = XPath('descendant::atom:id')
url = XPath('descendant::atom:link[@href and @rel="self"]/@href')
creator = XPath('descendant::dc:creator') creator = XPath('descendant::dc:creator')
identifier = XPath('descendant::dc:identifier') identifier = XPath('descendant::dc:identifier')
title = XPath('descendant::dc:title') title = XPath('descendant::dc:title')
@ -92,6 +93,7 @@ def to_metadata(browser, log, entry_, timeout): # {{{
id_url = entry_id(entry_)[0].text id_url = entry_id(entry_)[0].text
google_id = id_url.split('/')[-1] google_id = id_url.split('/')[-1]
details_url = url(entry_)[0]
title_ = ': '.join([x.text for x in title(entry_)]).strip() title_ = ': '.join([x.text for x in title(entry_)]).strip()
authors = [x.text.strip() for x in creator(entry_) if x.text] authors = [x.text.strip() for x in creator(entry_) if x.text]
if not authors: if not authors:
@ -103,7 +105,7 @@ def to_metadata(browser, log, entry_, timeout): # {{{
mi = Metadata(title_, authors) mi = Metadata(title_, authors)
mi.identifiers = {'google': google_id} mi.identifiers = {'google': google_id}
try: try:
raw = get_details(browser, id_url, timeout) raw = get_details(browser, details_url, timeout)
feed = etree.fromstring( feed = etree.fromstring(
xml_to_unicode(clean_ascii_chars(raw), strip_encoding_pats=True)[0], xml_to_unicode(clean_ascii_chars(raw), strip_encoding_pats=True)[0],
parser=etree.XMLParser(recover=True, no_network=True, resolve_entities=False) parser=etree.XMLParser(recover=True, no_network=True, resolve_entities=False)
@ -174,7 +176,7 @@ def to_metadata(browser, log, entry_, timeout): # {{{
class GoogleBooks(Source): class GoogleBooks(Source):
name = 'Google' name = 'Google'
version = (1, 0, 1) version = (1, 0, 2)
minimum_calibre_version = (2, 80, 0) minimum_calibre_version = (2, 80, 0)
description = _('Downloads metadata and covers from Google Books') description = _('Downloads metadata and covers from Google Books')