Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-08 10:44:09 -04:00
Code Issues Packages Projects Releases Wiki Activity

Use the mechanize browser for downloading external resources instead of python stdlib

Browse Source 
Also remove deprecated import of cgi
This commit is contained in:
Kovid Goyal 2023-05-16 06:55:01 +05:30
parent dc8be3bbcd
commit 84ec9819f2
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 13 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
src/calibre/ebooks/oeb/polish/download.py
View File

@ -2,7 +2,6 @@
# License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net> # License: GPLv3 Copyright: 2016, Kovid Goyal <kovid at kovidgoyal.net>
import cgi
import mimetypes import mimetypes
import os import os
import posixpath import posixpath
@ -15,7 +14,7 @@ from io import BytesIO
from multiprocessing.dummy import Pool from multiprocessing.dummy import Pool
from tempfile import NamedTemporaryFile from tempfile import NamedTemporaryFile
from calibre import as_unicode, sanitize_file_name as sanitize_file_name_base from calibre import as_unicode, browser, sanitize_file_name as sanitize_file_name_base
from calibre.constants import iswindows from calibre.constants import iswindows
from calibre.ebooks.oeb.base import OEB_DOCS, OEB_STYLES, barename, iterlinks from calibre.ebooks.oeb.base import OEB_DOCS, OEB_STYLES, barename, iterlinks
from calibre.ebooks.oeb.polish.utils import guess_type from calibre.ebooks.oeb.polish.utils import guess_type
@ -23,7 +22,7 @@ from calibre.ptempfile import TemporaryDirectory
from calibre.web import get_download_filename_from_response from calibre.web import get_download_filename_from_response
from polyglot.binary import from_base64_bytes from polyglot.binary import from_base64_bytes
from polyglot.builtins import iteritems from polyglot.builtins import iteritems
from polyglot.urllib import unquote, urlopen, urlparse from polyglot.urllib import unquote, urlparse
def is_external(url): def is_external(url):
@ -57,15 +56,17 @@ def get_external_resources(container):
def get_filename(original_url_parsed, response): def get_filename(original_url_parsed, response):
ans = get_download_filename_from_response(response) or posixpath.basename(original_url_parsed.path) or 'unknown' ans = get_download_filename_from_response(response) or posixpath.basename(original_url_parsed.path) or 'unknown'
ct = response.info().get('Content-Type', '') headers = response.info()
try:
ct = headers.get_params()[0][0].lower()
except Exception:
ct = ''
if ct: if ct:
ct = cgi.parse_header(ct)[0].lower() mt = guess_type(ans)
if ct: if mt != ct:
mt = guess_type(ans) exts = mimetypes.guess_all_extensions(ct)
if mt != ct: if exts:
exts = mimetypes.guess_all_extensions(ct) ans += exts[0]
if exts:
ans += exts[0]
return ans return ans
@ -137,7 +138,7 @@ def download_one(tdir, timeout, progress_report, data_uri_map, url):
break break
filename = 'data-uri.' + ext filename = 'data-uri.' + ext
else: else:
src = urlopen(url, timeout=timeout) src = browser().open(url, timeout=timeout)
filename = get_filename(purl, src) filename = get_filename(purl, src)
sz = get_content_length(src) sz = get_content_length(src)
progress_report(url, 0, sz) progress_report(url, 0, sz)