Hi,
the diff attached is only a proof of concept since it's a quick hack, but is
working for my needs.
It adds an "--transform-html" option which specifies a shell command to use as
a preprocessor on the downloading html files.
I wanted to download a site with a url which had a domain redirecting to it.
However, the domain expired in the past and the site relied all his links on
the domain, so the site became unusable.
Solution with the option I'm proposing:
wget -rkpE --transform-html "sed s/www.bad-domain.net/www.good-url.net/g"
www.good-url.net
--- http.c
+++ http.c
1345a1346,1352
>
> FILE *topen (const char *, const char *); /* --transform-html */
>
> #ifdef WINDOWS
> #define pclose _pclose
> #endif
>
2224c2231
< fp = fopen (hs->local_file, "ab");
---
> fp = topen (hs->local_file, "ab");
2226c2233
< fp = fopen (hs->local_file, "wb");
---
> fp = topen (hs->local_file, "wb");
2294a2302,2303
> {
> pclose (fp); /* --transform-html */
2295a2305
> }
+++ init.c
239a240
> { "transformhtml", &opt.transform_html, cmd_string },
--- main.c
+++ main.c
240a241
> { "transform-html", 0, OPT_VALUE, "transformhtml", required_argument },
587c588
< -r, --recursive specify recursive download.\n"),
---
> -r, --recursive specify recursive download.\n"),
589c590
< -l, --level=NUMBER maximum recursion depth (inf or 0 for
infinite).\n"),
---
> -l, --level=NUMBER maximum recursion depth (inf or 0 for
> infinite).\n"),
591c592
< --delete-after delete files locally after downloading them.\n"),
---
> --delete-after delete files locally after downloading
> them.\n"),
593c594
< -k, --convert-links make links in downloaded HTML point to local
files.\n"),
---
> -k, --convert-links make links in downloaded HTML point to
> local files.\n"),
595c596
< -K, --backup-converted before converting file X, back up as X.orig.\n"),
---
> -K, --backup-converted before converting file X, back up as
> X.orig.\n"),
597c598
< -m, --mirror shortcut for -N -r -l inf
--no-remove-listing.\n"),
---
> -m, --mirror shortcut for -N -r -l inf
> --no-remove-listing.\n"),
599c600
< -p, --page-requisites get all images, etc. needed to display HTML
page.\n"),
---
> -p, --page-requisites get all images, etc. needed to display
> HTML page.\n"),
601c602,604
< --strict-comments turn on strict (SGML) handling of HTML
comments.\n"),
---
> --strict-comments turn on strict (SGML) handling of HTML
> comments.\n"),
> N_("\
> --transform-html=SHELLCMD preprocess html files through a shell
> command.\n"),
+++ options.h
236a237,238
>
> char *transform_html; /* preprocess html files through a
> shell command */
--- utils.c
+++ utils.c
531a531,551
>
> #undef O_EXCL /* hack --transform-html */
>
> #ifdef WINDOWS
> #define popen _popen
> #endif
>
> FILE *
> topen (const char *fname, const char *mode)
> {
> if (opt.transform_html && has_html_suffix_p(fname))
> {
> char s[512];
>
> sprintf(s, "%s>%s", opt.transform_html, fname);
> return popen(s, mode);
> }
> else
> return fopen(fname, mode);
> }
>
555c575
< return fopen (fname, binary ? "wb" : "w");
---
> return topen (fname, binary ? "wb" : "w");
_________________________________________________________________
Tecnología, moda, motor, viajes,…suscríbete a nuestros boletines para estar
siempre a la última
Guapos y guapas, clips musicales y estrenos de cine.
