python regex non -greedy

从第一个满足条件的起点到最近的结点为一次匹配

import re searchPattern = re.compile(r"a.+?b") downloadLinkList =searchPattern.findall('ababab') print(downloadLinkList)

import re, os htmlSrc=""" <p style="text-indent:5.25pt;"> <span><b><span style="font-family:宋体;color:#17365d;">请点击播放按钮在</span><span style="color:#17365d;">IE</span></b></span><span><span><b><span style="font-family:宋体;color:#17365d;">浏览器下收听……</span></b></span></span> </p> <p> <img src="https://down.qnwz.cn/uploads/allimg/130621/107864-13062115194Y00.jpg" alt="" /> </p> <p> <embed src="https://down.qnwz.cn/uploads/media/broadcast/storymagazine/你想移民吗.mp3" type="video/x-ms-asf-plugin" width="300" height="60" autostart="false" loop="true" /> </p> <p> <img src="https://down.qnwz.cn/uploads/allimg/130621/107864-130621152111X1.jpg" alt="" /> </p> <p> <embed src="https://down.qnwz.cn/uploads/media/broadcast/storymagazine/小白.mp3" type="video/x-ms-asf-plugin" width="300" height="60" autostart="false" loop="true" /> </p> <p> <img src="https://down.qnwz.cn/uploads/allimg/130621/107864-130621152343K6.jpg" alt="" /> </p> <p> <embed src="https://down.qnwz.cn/uploads/media/broadcast/storymagazine/每个萝莉都有一个掌柜梦.mp3" type="video/x-ms-asf-plugin" width="300" height="60" autostart="false" loop="true" /> </p> <p> <img src="https://down.qnwz.cn/uploads/allimg/130621/107864-130621152550411.jpg" alt="" /> </p> <p> <embed src="https://down.qnwz.cn/uploads/media/broadcast/storymagazine/爸爸的山峦被儿女移平.mp3" type="video/x-ms-asf-plugin" width="300" height="60" autostart="false" loop="true" /> </p> <p> """ searchPattern = re.compile(r"http.+?mp3")#re.DOTALL downloadLinkList =searchPattern.findall(htmlSrc) fileNameList=map(os.path.basename, downloadLinkList) rawNetworkFileInfoList=zip(downloadLinkList, fileNameList) print(list(rawNetworkFileInfoList))

import re,os fileNameSearchPattern = re.compile(r'>(.+?)</a>') htmlSrc='''(function ($) { if($('#result').html().indexOf('loading')>0) $('#result').html('');flvout('56网的视频请用IE浏览器下载<br/>');flvout('<span style="color:red">[wvga]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd_super.flv.mp4?v=1&t=N8Wift4mnRo0WuRrXWgKCQ&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).mp4</a><br/>');flvout('<span style="color:red">[vga]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd_clear.flv.mp4?v=1&t=a80AftMertF0AL06IWXOkA&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).mp4</a><br/>');flvout('<span style="color:red">[super]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd_super.flv?v=1&t=eXQLGx3hSDK_HjXITVobjg&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).flv</a><br/>');flvout('<span style="color:red">[qvga]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd.flv.mp4?v=1&t=fXXhQcUHgpXpa6QM9fI1rg&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).mp4</a><br/>');flvout('<span style="color:red">[qqvga]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd_qqvga.mp4?v=1&t=SGVhMsV0qJvxOJ84eTCs-w&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).mp4</a><br/>');flvout('<span style="color:red">[normal]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd.flv?v=1&t=RMT6nOJwsrkhhsLgu_MUEg&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).flv</a><br/>');flvout('<span style="color:red">[clear]</span><br/><a href="https://f9.r.56.com/f9.c84.56.com/flvdownload/14/22/sc_mp4_133633254658hd_clear.flv?v=1&t=jDqGmS-KrnfpeGwouQiM4Q&r=74284&e=1368068963">哨声响起10 (KTKKT|国语动画).flv</a><br/>'); } (jQuery));''' print(fileNameSearchPattern.findall(htmlSrc))
评论

© ID4333709 | Powered by LOFTER