通过apache,和nginx模块去除html中的空格和tab
最近一个项目中，合作方要求去除html中的空格，不想改代码，所以百度了一下通过apache,和nginx模块去除html中的空格和tab的方案，下面记录下来：
一、nginx
nginx可以通过mod_strip模块来实现该功能
1. mod_strip安装：
# cd /usr/local/src/
# wget http://wiki.nginx.org/images/6/63/Mod_strip-0.1.tar.gz
# tar -xzvf Mod_strip-0.1.tar.gz
# cd nginx-1.4.2 //提前解压好的nginx
# ./configure --prefix=/usr/local/nginx-1.4.2 --add-module=../mod_strip
# make
# make install
2. mod_strip简单用法：
location / {
strip on;
}
strip指令：
语法: strip on|off
默认: off
可用配置段: main, http, server, location
所有响应给用户的MIME类型为text/html将会使用该模块
二、apache
apche可以通过mod_pagespeed http://www.modpagespeed.com/ 来实现,我的服务器是ubuntu
1、下载mode_pagespeed
wget https://dl-ssl.google.com/dl/linux/direct/mod-pagespeed-beta_current_i386.deb
2、安装
dpkg -i mod-pagespeed*
执行完毕后会提示重启
3、修改配置文件
/etc/apache2/mods-available/pagespeed.conf，下面我着重介绍一下ModPagespeedEnableFilters这个是启用的过滤器，collapse_whitespace,remove_comments分别为替换空白字符和删除注释，其它参数请见mod_pagespeed官网
<IfModule pagespeed_module>
# Turn on mod_pagespeed. To completely disable mod_pagespeed, you
# can set this to "off".
ModPagespeed on
# We want VHosts to inherit global configuration.
# If this is not included, they'll be independent (except for inherently
# global options), at least for backwards compatibility.
ModPagespeedInheritVHostConfig on
# Direct Apache to send all HTML output to the mod_pagespeed
# output handler.
AddOutputFilterByType MOD_PAGESPEED_OUTPUT_FILTER text/html
AddOutputFilterByType MOD_PAGESPEED_OUTPUT_FILTER application/javascript
AddOutputFilterByType MOD_PAGESPEED_OUTPUT_FILTER text/css
# If you want mod_pagespeed process XHTML as well, please uncomment this
# line.
#AddOutputFilterByType MOD_PAGESPEED_OUTPUT_FILTER application/xhtml+xml
# The ModPagespeedFileCachePath directory must exist and be writable
# by the apache user (as specified by the User directive).
ModPagespeedFileCachePath "/var/cache/mod_pagespeed/"
# LogDir is needed to store various logs, including the statistics log
# required for the console.
ModPagespeedLogDir "/var/log/pagespeed"
# The locations of SSL Certificates is distribution-dependent.
ModPagespeedSslCertDirectory "/etc/ssl/certs"
# If you want, you can use one or more memcached servers as the store for
# the mod_pagespeed cache.
# ModPagespeedMemcachedServers localhost:11211
# A portion of the cache can be kept in memory only, to reduce load on disk
# (or memcached) from many small files.
# ModPagespeedCreateSharedMemoryMetadataCache "/var/cache/mod_pagespeed/" 51200
# Override the mod_pagespeed 'rewrite level'. The default level
# "CoreFilters" uses a set of rewrite filters that are generally
# safe for most web pages. Most sites should not need to change
# this value and can instead fine-tune the configuration using the
# ModPagespeedDisableFilters and ModPagespeedEnableFilters
# directives, below. Valid values for ModPagespeedRewriteLevel are
# PassThrough, CoreFilters and TestingCoreFilters.
#
# ModPagespeedRewriteLevel PassThrough
# Explicitly disables specific filters. This is useful in
# conjuction with ModPagespeedRewriteLevel. For instance, if one
# of the filters in the CoreFilters needs to be disabled for a
# site, that filter can be added to
# ModPagespeedDisableFilters. This directive contains a
# comma-separated list of filter names, and can be repeated.
#
#ModPagespeedDisableFilters remove_comments,collapse_whitespace
# Explicitly enables specific filters. This is useful in
# conjuction with ModPagespeedRewriteLevel. For instance, filters
# not included in the CoreFilters may be enabled using this
# directive. This directive contains a comma-separated list of
# filter names, and can be repeated.
#
#ModPagespeedEnableFilters rewrite_javascript,rewrite_css
ModPagespeedEnableFilters collapse_whitespace,elide_attributes,remove_comments
# Explicitly forbids the enabling of specific filters using either query
# parameters or request headers. This is useful, for example, when we do
# not want the filter to run for performance or security reasons. This
# directive contains a comma-separated list of filter names, and can be
# repeated.
#
# ModPagespeedForbidFilters rewrite_images
# How long mod_pagespeed will wait to return an optimized resource
# (per flush window) on first request before giving up and returning the
# original (unoptimized) resource. After this deadline is exceeded the
# original resource is returned and the optimization is pushed to the
# background to be completed for future requests. Increasing this value will
# increase page latency, but might reduce load time (for instance on a
# bandwidth-constrained link where it's worth waiting for image
# compression to complete). If the value is less than or equal to zero
# mod_pagespeed will wait indefinitely for the rewrite to complete before
# returning.
#
# ModPagespeedRewriteDeadlinePerFlushMs 10
# ModPagespeedDomain
# authorizes rewriting of JS, CSS, and Image files found in this
# domain. By default only resources with the same origin as the
# HTML file are rewritten. For example:
#
# ModPagespeedDomain cdn.myhost.com
#
# This will allow resources found on http://cdn.myhost.com to be
# rewritten in addition to those in the same domain as the HTML.
#
# Other domain-related directives (like ModPagespeedMapRewriteDomain
# and ModPagespeedMapOriginDomain) can also authorize domains.
#
# Wildcards (* and ?) are allowed in the domain specification. Be
# careful when using them as if you rewrite domains that do not
# send you traffic, then the site receiving the traffic will not
# know how to serve the rewritten content.
# Other defaults (cache sizes and thresholds):
#
# ModPagespeedFileCacheSizeKb 102400
# ModPagespeedFileCacheCleanIntervalMs 3600000
# ModPagespeedLRUCacheKbPerProcess 1024
# ModPagespeedLRUCacheByteLimit 16384
# ModPagespeedCssFlattenMaxBytes 2048
# ModPagespeedCssInlineMaxBytes 2048
# ModPagespeedCssImageInlineMaxBytes 0
# ModPagespeedImageInlineMaxBytes 3072
# ModPagespeedJsInlineMaxBytes 2048
# ModPagespeedCssOutlineMinBytes 3000
# ModPagespeedJsOutlineMinBytes 3000
# ModPagespeedMaxCombinedCssBytes -1
# ModPagespeedMaxCombinedJsBytes 92160
# Limit the number of inodes in the file cache. Set to 0 for no limit.
# The default value if this paramater is not specified is 0 (no limit).
ModPagespeedFileCacheInodeLimit 500000
# Bound the number of images that can be rewritten at any one time; this
# avoids overloading the CPU. Set this to 0 to remove the bound.
#
# ModPagespeedImageMaxRewritesAtOnce 8
# You can also customize the number of threads per Apache process
# mod_pagespeed will use to do resource optimization. Plain
# "rewrite threads" are used to do short, latency-sensitive work,
# while "expensive rewrite threads" are used for actual optimization
# work that's more computationally expensive. If you live these unset,
# or use values <= 0 the defaults will be used, which is 1 for both
# values when using non-threaded MPMs (e.g. prefork) and 4 for both
# on threaded MPMs (e.g. worker and event). These settings can only
# be changed globally, and not per virtual host.
#
# ModPagespeedNumRewriteThreads 4
# ModPagespeedNumExpensiveRewriteThreads 4
# Randomly drop rewrites (*) to increase the chance of optimizing
# frequently fetched resources and decrease the chance of optimizing
# infrequently fetched resources. This can reduce CPU load. The default
# value of this parameter is 0 (no drops). 90 means that a resourced
# fetched once has a 10% probability of being optimized while a resource
# that is fetched 50 times has a 99.65% probability of being optimized.
#
# (*) Currently only CSS files and images are randomly dropped. Images
# within CSS files are not randomly dropped.
#
# ModPagespeedRewriteRandomDropPercentage 90
# Many filters modify the URLs of resources in HTML files. This is typically
# harmless but pages whose Javascript expects to read or modify the original
# URLs may break. The following parameters prevent filters from modifying
# URLs of their respective types.
#
# ModPagespeedJsPreserveURLs on
# ModPagespeedImagePreserveURLs on
# ModPagespeedCssPreserveURLs on
# Settings for image optimization:
#
# Lossy image recompression quality (0 to 100, -1 just strips metadata):
# ModPagespeedImageRecompressionQuality 85
#
# Jpeg recompression quality (0 to 100, -1 uses ImageRecompressionQuality):
# ModPagespeedJpegRecompressionQuality -1
# ModPagespeedJpegRecompressionQualityForSmallScreens 70
#
# WebP recompression quality (0 to 100, -1 uses ImageRecompressionQuality):
# ModPagespeedImageWebpRecompressionQuality 80
# ModPagespeedImageWebpRecompressionQualityForSmallScreens 70
#
# Timeout for conversions to WebP format, in
# milliseconds. Negative values mean no timeout is applied. The
# default value is -1:
# ModPagespeedImageWebpTimeoutMs 5000
#
# Percent of original image size below which optimized images are retained:
# ModPagespeedImageLimitOptimizedPercent 100
#
# Percent of original image area below which image resizing will be
# attempted:
# ModPagespeedImageLimitResizeAreaPercent 100
# Settings for inline preview images
#
# Setting this to n restricts preview images to the first n images found on
# the page. The default of -1 means preview images can appear anywhere on
# the page (if those images appear above the fold).
# ModPagespeedMaxInlinedPreviewImagesIndex -1
# Sets the minimum size in bytes of any image for which a low quality image
# is generated.
# ModPagespeedMinImageSizeLowResolutionBytes 3072
# The maximum URL size is generally limited to about 2k characters
# due to IE: See http://support.microsoft.com/kb/208427/EN-US.
# Apache servers by default impose a further limitation of about
# 250 characters per URL segment (text between slashes).
# mod_pagespeed circumvents this limitation, but if you employ
# proxy servers in your path you may need to re-impose it by
# overriding the setting here. The default setting is 1024
# characters.
#
# ModPagespeedMaxSegmentLength 250
# Uncomment this if you want to prevent mod_pagespeed from combining files
# (e.g. CSS files) across paths
#
# ModPagespeedCombineAcrossPaths off
# Renaming JavaScript URLs can sometimes break them. With this
# option enabled, mod_pagespeed uses a simple heuristic to decide
# not to rename JavaScript that it thinks is introspective.
#
# You can uncomment this to let mod_pagespeed rename all JS files.
#
# ModPagespeedAvoidRenamingIntrospectiveJavascript off
# Certain common JavaScript libraries are available from Google, which acts
# as a CDN and allows you to benefit from browser caching if a new visitor
# to your site previously visited another site that makes use of the same
# libraries as you do. Enable the following filter to turn on this feature.
#
# ModPagespeedEnableFilters canonicalize_javascript_libraries
# The following line configures a library that is recognized by
# canonicalize_javascript_libraries. This will have no effect unless you
# enable this filter (generally by uncommenting the last line in the
# previous stanza). The format is:
# ModPagespeedLibrary bytes md5 canonical_url
# Where bytes and md5 are with respect to the *minified* JS; use
# js_minify --print_size_and_hash to obtain this data.
# Note that we can register multiple hashes for the same canonical url;
# we do this if there are versions available that have already been minified
# with more sophisticated tools.
#
# Additional library configuration can be found in
# pagespeed_libraries.conf included in the distribution. You should add
# new entries here, though, so that file can be automatically upgraded.
# ModPagespeedLibrary 43 1o978_K0_LNE5_ystNklf http://www.modpagespeed.com/rewrite_javascript.js
# Explicitly tell mod_pagespeed to load some resources from disk.
# This will speed up load time and update frequency.
#
# This should only be used for static resources which do not need
# specific headers set or other processing by Apache.
#
# Both URL and filesystem path should specify directories and
# filesystem path must be absolute (for now).
#
# ModPagespeedLoadFromFile "http://example.com/static/" "/var/www/static/"
# Enables server-side instrumentation and statistics. If this rewriter is
# enabled, then each rewritten HTML page will have instrumentation javacript
# added that sends latency beacons to /mod_pagespeed_beacon. These
# statistics can be accessed at /mod_pagespeed_statistics. You must also
# enable the mod_pagespeed_statistics and mod_pagespeed_beacon handlers
# below.
#
# ModPagespeedEnableFilters add_instrumentation
# The add_instrumentation filter sends a beacon after the page onload
# handler is called. The user might navigate to a new URL before this. If
# you enable the following directive, the beacon is sent as part of an
# onbeforeunload handler, for pages where navigation happens before the
# onload event.
#
# ModPagespeedReportUnloadTime on
# Uncomment the following line so that ModPagespeed will not cache or
# rewrite resources with Vary: in the header, e.g. Vary: User-Agent.
# Note that ModPagespeed always respects Vary: headers on html content.
# ModPagespeedRespectVary on
# Uncomment the following line if you want to disable statistics entirely.
#
# ModPagespeedStatistics off
# This page lets you view statistics about the mod_pagespeed module.
<Location /mod_pagespeed_statistics>
Order allow,deny
# You may insert other "Allow from" lines to add hosts you want to
# allow to look at generated statistics. Another possibility is
# to comment out the "Order" and "Allow" options from the config
# file, to allow any client that can reach your server to examine
# statistics. This might be appropriate in an experimental setup or
# if the Apache server is protected by a reverse proxy that will
# filter URLs in some fashion.
Allow from localhost
Allow from 127.0.0.1
SetHandler mod_pagespeed_statistics
</Location>
# Enable logging of mod_pagespeed statistics, needed for the console.
ModPagespeedStatisticsLogging on
<Location /pagespeed_console>
Order allow,deny
Allow from localhost
Allow from 127.0.0.1
SetHandler pagespeed_console
</Location>
# Page /mod_pagespeed_message lets you view the latest messages from
# mod_pagespeed, regardless of log-level in your httpd.conf
# ModPagespeedMessageBufferSize is the maximum number of bytes you would
# like to dump to your /mod_pagespeed_message page at one time,
# its default value is 100k bytes.
# Set it to 0 if you want to disable this feature.
ModPagespeedMessageBufferSize 100000
<Location /mod_pagespeed_message>
Order allow,deny
Allow from localhost
Allow from 127.0.0.1
SetHandler mod_pagespeed_message
</Location>
</IfModule>
