1
0
mirror of https://github.com/moparisthebest/wget synced 2024-07-03 16:38:41 -04:00

stsc: -i URL improvements.

This commit is contained in:
Micah Cowan 2008-07-22 13:33:42 -07:00
parent b28a6abfe6
commit e4371807f6
5 changed files with 32 additions and 1 deletions

View File

@ -1,3 +1,10 @@
2008-07-17 Steven Schubiger <stsc@members.fsf.org>
* wget.texi (Logging and Input File Options): Document
for --input-file and according remote input file URLs, the
implicit enforcement of treating a document as HTML and
the possible baseref assumption.
2008-06-29 Micah Cowan <micah@cowan.name>
* wget.texi <Contributors>: Added Joao Ferreira, Mike Frysinger,

View File

@ -497,6 +497,11 @@ relative links, which you can solve either by adding @code{<base
href="@var{url}">} to the documents or by specifying
@samp{--base=@var{url}} on the command line.
If the @var{file} is an external one, the document will be automatically
treated as @samp{html} if the Content-Type matches @samp{text/html}.
Furthermore, the @var{file}'s location will be implicitly used as base
href if none was specified.
@cindex force html
@item -F
@itemx --force-html

View File

@ -1,3 +1,12 @@
2008-07-17 Steven Schubiger <stsc@members.fsf.org>
* retr.c (retrieve_from_file): When given an URL as input file,
use it as baseref if none was specified and treat the input file
as HTML if its content type is text/html.
* init.c (cleanup): Free the memory associated with the base
option (when DEBUG_MALLOC is defined).
2008-06-28 Steven Schubiger <stsc@members.fsf.org>
* retr.c (retrieve_from_file): Allow for reading the links from

View File

@ -1548,6 +1548,8 @@ cleanup (void)
xfree_null (opt.cookies_output);
xfree_null (opt.user);
xfree_null (opt.passwd);
xfree_null (opt.base_href);
#endif /* DEBUG_MALLOC */
}

View File

@ -830,10 +830,18 @@ retrieve_from_file (const char *file, bool html, int *count)
if (url_has_scheme (url))
{
int dt;
uerr_t status;
status = retrieve_url (url, &input_file, NULL, NULL, NULL, false);
if (!opt.base_href)
opt.base_href = xstrdup (url);
status = retrieve_url (url, &input_file, NULL, NULL, &dt, false);
if (status != RETROK)
return status;
if (dt & TEXTHTML)
html = true;
}
else
input_file = (char *) file;