From 3491420b53b03dbc24b6001e4f379fd2fbdbea8d Mon Sep 17 00:00:00 2001 From: fiddlosopher Date: Fri, 29 Dec 2006 18:50:13 +0000 Subject: + Changed 'web2markdown' to 'html2markdown'. git-svn-id: https://pandoc.googlecode.com/svn/trunk@309 788f1e2b-df1e-0410-8736-df70ead52e1b --- man/man1/html2markdown.1 | 81 ++++++++++++++++++++++++++++++++++++++++++++++++ man/man1/pandoc.1 | 4 +-- man/man1/web2markdown.1 | 81 ------------------------------------------------ 3 files changed, 83 insertions(+), 83 deletions(-) create mode 100644 man/man1/html2markdown.1 delete mode 100644 man/man1/web2markdown.1 (limited to 'man/man1') diff --git a/man/man1/html2markdown.1 b/man/man1/html2markdown.1 new file mode 100644 index 000000000..413feb115 --- /dev/null +++ b/man/man1/html2markdown.1 @@ -0,0 +1,81 @@ +.TH HTML2MARKDOWN 1 "December 15, 2006" Pandoc "User Manuals" +.SH NAME +html2markdown \- converts HTML to markdown-formatted text +.SH SYNOPSIS +\fBhtml2markdown\fR [\fIoptions\fR] [\fIinput\-file\fR or \fIURL\fR] +.SH DESCRIPTION +\fBhtml2markdown\fR converts \fIinput\-file\fR or \fIURL\fR (or text +from STDIN) from HTML to markdown\-formatted plain text. +If a URL is specified, \fBhtml2markdown\fR uses an available program +(e.g. wget, w3m, lynx or curl) to fetch its contents. Output is sent +to STDOUT unless an output file is specified using the \fB\-o\fR +option. +.PP +\fBhtml2markdown\fR uses the character encoding specified in the +"Content-type" meta tag. If this is not present, or if input comes +from STDIN, UTF-8 is assumed. A character encoding may be specified +explicitly using the \fB\-e\fR option. +.PP +\fBhtml2markdown\fR is a wrapper for \fBpandoc\fR. +.SH OPTIONS +.TP +.B \-s, \-\-standalone +Include title, author, and date information (if present) at the +top of markdown output. +.TP +.B \-o FILE, \-\-output=FILE +Write output to \fIFILE\fR instead of STDOUT. +.TP +.B \-p, \-\-preserve-tabs +Preserve tabs instead of converting them to spaces. +.TP +.B \-\-tab-stop=\fITABSTOP\fB +Specify tab stop (default is 4). +.TP +.B \-R, \-\-parse-raw +Parse untranslatable HTML codes as raw HTML. +.TP +.B \-H \fIFILE\fB, \-\-include-in-header=\fIFILE\fB +Include contents of \fIFILE\fR at the end of the header. Implies +\fB\-s\fR. +.TP +.B \-B \fIFILE\fB, \-\-include-before-body=\fIFILE\fB +Include contents of \fIFILE\fR at the beginning of the document body. +.TP +.B \-A \fIFILE\fB, \-\-include-after-body=\fIFILE\fB +Include contents of \fIFILE\fR at the end of the document body. +.TP +.B \-C \fIFILE\fB, \-\-custom-header=\fIFILE\fB +Use contents of \fIFILE\fR +as the document header (overriding the default header, which can be +printed using '\fBpandoc \-D markdown\fR'). Implies +\fB-s\fR. +.TP +.B \-v, \-\-version +Print version. +.TP +.B \-h, \-\-help +Show usage message. +.TP +.B \-e \fIencoding\fR +Assume the character encoding \fIencoding\fR in reading HTML. +(Note: \fIencoding\fR will be passed to \fBiconv\fR; a list of +available encodings may be obtained using `\fBiconv \-l\fR'.) +If the \fB\-e\fR option is not specified and input is not from +STDIN, \fBhtml2markdown\fR will try to extract the character encoding +from the "Content-type" meta tag. If no character encoding is +specified in this way, or if input is from STDIN, UTF-8 will be +assumed. +.TP +.B \-g \fIcommand\fR +Use \fIcommand\fR to fetch the contents of a URL. (By default, +\fBhtml2markdown\fR searches for an available program or text-based +browser to fetch the contents of a URL.) For example: +.IP +html2markdown \-g 'wget \-\-user=foo \-\-password=bar' mysite.com + +.SH "SEE ALSO" +\fBpandoc\fR(1), +\fBiconv\fR(1) +.SH AUTHOR +John MacFarlane and Recai Oktas diff --git a/man/man1/pandoc.1 b/man/man1/pandoc.1 index f6280f463..a955e9e8a 100644 --- a/man/man1/pandoc.1 +++ b/man/man1/pandoc.1 @@ -41,7 +41,7 @@ and output through \fBiconv\fR: .PP \fIPandoc\fR's HTML parser is not very forgiving. If your input is HTML, consider running it through \fBtidy\fR(1) before passing it -to Pandoc. Or use \fBweb2markdown\fR(1), a wrapper around \fBpandoc\fR. +to Pandoc. Or use \fBhtml2markdown\fR(1), a wrapper around \fBpandoc\fR. .SH OPTIONS .TP @@ -151,7 +151,7 @@ Print version. Show usage message. .SH "SEE ALSO" -\fBweb2markdown\fR(1), +\fBhtml2markdown\fR(1), \fBmarkdown2pdf\fR(1). The .I README diff --git a/man/man1/web2markdown.1 b/man/man1/web2markdown.1 deleted file mode 100644 index 242b50671..000000000 --- a/man/man1/web2markdown.1 +++ /dev/null @@ -1,81 +0,0 @@ -.TH WEB2MARKDOWN 1 "December 15, 2006" Pandoc "User Manuals" -.SH NAME -web2markdown \- converts HTML to markdown-formatted text -.SH SYNOPSIS -\fBweb2markdown\fR [\fIoptions\fR] [\fIinput\-file\fR or \fIURL\fR] -.SH DESCRIPTION -\fBweb2markdown\fR converts \fIinput\-file\fR or \fIURL\fR (or text -from STDIN) from HTML to markdown\-formatted plain text. -If a URL is specified, \fBweb2markdown\fR uses an available program -(e.g. wget, w3m, lynx or curl) to fetch its contents. Output is sent -to STDOUT unless an output file is specified using the \fB\-o\fR -option. -.PP -\fBweb2markdown\fR uses the character encoding specified in the -"Content-type" meta tag. If this is not present, or if input comes -from STDIN, UTF-8 is assumed. A character encoding may be specified -explicitly using the \fB\-e\fR option. -.PP -\fBweb2markdown\fR is a wrapper for \fBpandoc\fR. -.SH OPTIONS -.TP -.B \-s, \-\-standalone -Include title, author, and date information (if present) at the -top of markdown output. -.TP -.B \-o FILE, \-\-output=FILE -Write output to \fIFILE\fR instead of STDOUT. -.TP -.B \-p, \-\-preserve-tabs -Preserve tabs instead of converting them to spaces. -.TP -.B \-\-tab-stop=\fITABSTOP\fB -Specify tab stop (default is 4). -.TP -.B \-R, \-\-parse-raw -Parse untranslatable HTML codes as raw HTML. -.TP -.B \-H \fIFILE\fB, \-\-include-in-header=\fIFILE\fB -Include contents of \fIFILE\fR at the end of the header. Implies -\fB\-s\fR. -.TP -.B \-B \fIFILE\fB, \-\-include-before-body=\fIFILE\fB -Include contents of \fIFILE\fR at the beginning of the document body. -.TP -.B \-A \fIFILE\fB, \-\-include-after-body=\fIFILE\fB -Include contents of \fIFILE\fR at the end of the document body. -.TP -.B \-C \fIFILE\fB, \-\-custom-header=\fIFILE\fB -Use contents of \fIFILE\fR -as the document header (overriding the default header, which can be -printed using '\fBpandoc \-D markdown\fR'). Implies -\fB-s\fR. -.TP -.B \-v, \-\-version -Print version. -.TP -.B \-h, \-\-help -Show usage message. -.TP -.B \-e \fIencoding\fR -Assume the character encoding \fIencoding\fR in reading HTML. -(Note: \fIencoding\fR will be passed to \fBiconv\fR; a list of -available encodings may be obtained using `\fBiconv \-l\fR'.) -If the \fB\-e\fR option is not specified and input is not from -STDIN, \fBweb2markdown\fR will try to extract the character encoding -from the "Content-type" meta tag. If no character encoding is -specified in this way, or if input is from STDIN, UTF-8 will be -assumed. -.TP -.B \-g \fIcommand\fR -Use \fIcommand\fR to fetch the contents of a URL. (By default, -\fBweb2markdown\fR searches for an available program or text-based -browser to fetch the contents of a URL.) For example: -.IP -web2markdown \-g 'wget \-\-user=foo \-\-password=bar' mysite.com - -.SH "SEE ALSO" -\fBpandoc\fR(1), -\fBiconv\fR(1) -.SH AUTHOR -John MacFarlane and Recai Oktas -- cgit v1.2.3