有关文章采集的问题，放到这里讨论。

新闻类

福建日报：www.fujian.gov.cn ,12#TD#fjyw_xldbt#t ,12#TD#fjyw_xldbt#t ,12#TD#tgray14#t ,1#printdiv##t ,福建日报 ,1#printdiv##h ,海蓝

我的所有的模板：

==========开始===============

www.gov.cn ,4#title##innerText ,12#TD#txt12#t#/来源[:|：]\s?([^\s　]*)/ ,1#Zoom##h#/^([\d\D]*)<p[^>]*><img/img#a ,12#TD#txt12#t ,12#td#txt18#innerText , ,海蓝
news.163.com ,2#keywords##content ,12#span#info#t#/来源[:|：]\s?([^\s　]*)/ ,1#endText##h##a ,12#span#info#innerText#/^(\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2}).*$/im ,1#h1title##innerText , ,海蓝
news.sina.com.cn ,2#keywords##content ,1#media_name##innerText ,1#artibody##innerHTML#/^([\s\S]*?)<div/img ,1#pub_date##innerText ,1#artibodyTitle##innerText , ,海蓝
money.163.com ,2#keywords##content ,12#span#info#t#/来源[:|：]\s?([^\s　]*)/ ,1#endText##innerHTML ,12#SPAN#info#t ,1#h1title##innerText , ,海蓝
news.xinhuanet.com ,2#keywords##content ,4#body##t#/来源[:|：]\s?([^\s　]*)/ ,1#content##innerHTML##span ,1#pubtime##innerText ,1#title##innerText , ,海蓝
news.ciir.edu.cn ,4#title##innerText ,千客网 ,1#Zoom##innerHTML ,1#atc_info##innerText#/^[\s\S]*日期：(\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}).*$/ig ,4#title##innerText , ,美人鱼
renshi.people.com.cn ,2#keywords##content ,8#ly_red##innerText#/^.*来源：(.*)$/ ,1#zoom##innerHTML ,8#ly_red##innerText#/^(\d{4}年\d{1,2}月\d{1,2}日\d{2}:\d{2}).*$/ ,8#ftitle##innerText ,8#fsubtitle##innerText ,海蓝
news.qq.com ,2#keywords##content ,12#span#where#innerText ,1#Cnt-Main-Article-QQ##innerHTML##a#img#div#span ,12#span#pubTime#innerText ,4#h1##innerText , ,海蓝
news.sohu.com ,2#keywords##content ,1#media_span##innerText ,1#contentText##innerHTML#/^([\d\D]*?)<script/img ,12#div#time#innerText ,4#h1##innerText , ,海蓝
news.ifeng.com ,2#keywords##content#/^([\d\D]*?)凤凰/img ,1#artical_sth##innerText#/来源：(.*?)\s/ ,1#artical_real##innerHTML#/^([\d\D]*?)<span/img#a ,1#artical_sth##innerText#/(\d{4}年\d{2}月\d{2}日\s\d{2}:\d{2})/ ,1#artical_topic##innerText , ,海蓝
www.chinanews.com ,4#h1##innerText ,12#div#left_time#innerHTML#/来源：([^<]*)/ ,1#fontzoom##innerHTML ,12#div#left_time#innerText#/(\d{4}年\d{2}月\d{2}日\s\d{2}:\d{2})/ ,4#h1##innerText , ,海蓝
cn.reuters.com ,4#h1##innerText ,路透中文网 ,1#resizeableText##innerText ,12#div#timestampHeader#innerText#/^([\s\S]*)星期.([\s\S]*)BJT/ ,4#h1##innerText , ,
v.youku.com , , , , , ,12#ul#pack_number#innerHTML#/id=A_(.*?)\s/ ,
www.wenming.cn ,2#keywords##content ,1#time_tex##innerText#/来源：(.*)$/ ,1#tex##innerHTML#/(<p>[\d\D]*</p>)/img ,1#time_tex##innerText#/发表时间：([\d-]*)/ ,1#title_tex##innerText , ,海蓝
mil.chinaiiss.com ,2#keywords##content ,12#div#bar#innerText#/来源[:|：](.*?)\s/ ,1#content_text##innerHTML##A#span ,12#div#bar#innerText#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,4#title##innerText#/([^_]*)/ , ,海蓝
cpc.people.com.cn ,2#keywords##content ,8#ly_red##t#/来源[:|：]\s?([^\s　]*)/ ,1#zoom##h#/^([\d\D]*?)<center>/img ,8#ly_red##t ,8#ftitle##innerText ,8#fsubtitle##innerText ,海蓝
www.bjnews.com.cn ,4#h1##innerText ,12#dl#ctdate#innerText#/([^\d-:\s]+)/ ,12#div#content#innerHTML ,12#dl#ctdate#innerText#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,4#h1##innerText , ,海蓝
politics.gmw.cn ,2#keywords##content , , ,4#body##innerText ,4#title##innerText#/([^_]+)/ , ,
china.huanqiu.com ,2#keywords##content ,1#fromsite##innerText ,1#text##innerHTML##a ,1#get_date##innerText ,4#title##innerText#/([^_]*)/ , ,海蓝
www.infzm.com ,4#h1##innerText ,12#span#source#innerText#/来源[:：](.*)/ ,1#content-context##innerHTML ,12#span#pubTime#innerText#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,4#h1##innerText , ,海蓝
www.minshenglife.com ,2#keywords##content ,4#body##innerText#/来源：\s?(.*?)\s/img ,1#textflag##h ,now ,4#title##t#/-(.*)/ , ,海蓝
www.sinosig.com ,12#td#article_title_font#t ,4#body##innerText#/来源[:|：](.*?)[\s\u3000]/ ,4#body##innerHTML#/(<p>[\d\D]*</p>)/img ,4#body##innerText#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,12#td#article_title_font#t , ,4#table##h#/<td>\s(<p.*)/i
zwpd.daynews.com.cn ,2#keywords##content , , , ,4#title##innerText , ,
news.ycwb.com ,4#H1##t ,12#DIV#time#t#/来源[:|：](.*?)[\s　]/ ,12#DIV#con-txt#h#/(<p>[\d\D]*<\/p>)/ ,12#DIV#time#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,4#H1##t , ,海蓝
world.banyuetan.org ,2#keywords##content ,12#DIV#xinxi#t#/来源[:|：](.*)[\s　]?/ ,1#lblContent##h ,12#DIV#xinxi#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,1#lblTitle##t , ,海蓝
news.dahe.cn ,4#H1##t ,1#msg##t#/来源[:|：](.*)/ ,1#main##h ,12#SPAN#sTime#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,4#H1##t , ,海蓝
hsb.hsw.cn ,4#H1##t ,华商网-华商报 ,12#TD#f14_top#h#/(<p>[\d\D]*<\/p>)/ ,12#TD#sfont#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2}))/ ,12#P#bt1#t ,12#P#yt#t ,海蓝
www.gxnews.com.cn ,2#keywords##content ,1#left_2##t#/来源[:|：](.*?)[\s　]/ ,1#left_3##h##a ,1#left_2##t ,1#left_1##t , ,海蓝
www.yangtse.com ,2#keywords##content ,2#source##content ,4#body##innerHTML#/<!--enpcontent-->([\d\D]*)<!--\/enpcontent-->/img ,12#SPAN#STYLE3#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,12#SPAN#STYLE1#t , ,海蓝
news.cyol.com ,2#keywords##content ,中青报 ,12#DIV#zhengwen#t ,12#H6#laiy#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2}))/ ,12#H5#bttitle#t , ,海蓝
news.china.com.cn ,2#keywords##content ,4#BODY##h#/来源[:|：]\s([^<]*)</ ,1#fontzoom##h ,4#BODY##t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,12#H1#fb24#t , ,海蓝
news.southcn.com ,2#keywords##content ,12#SPAN#source#t#/来源[:|：]\s(.*)/ ,1#ScDetailContent##h ,12#SPAN#time#t ,1#ScDetailTitle##t , ,海蓝
money.msn.com.cn ,2#keywords##content ,12#SPAN#info#t#/来源[:|：]\s?([^\s　]*)/ ,12#DIV#endText#h ,12#SPAN#info#t ,1#h1title##t , ,海蓝
gb.cri.cn ,2#keywords##content ,12#DIV#signdate#t#/来源[:|：](.*?)[\s　]/ ,1#ccontent##h ,12#DIV#signdate#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,1#ctitle##t , ,海蓝
im.banyuetan.org ,2#keywords##content ,12#DIV#xinxi#t#/来源[:|：]([^\s]*)/ ,1#lblContent##h ,12#DIV#xinxi#t#/([\d]{4}[年|-][\d]{1,2}[月|-][\d]{1,2}日?\s?(?:[\d]{1,2}:[\d]{1,2})?)/ ,1#lblTitle##t , ,海蓝
www.dahe.cn ,4#H1##t ,1#msg##t#/来源[:|：](.*)/ ,1#main##h ,12#SPAN#sTime#t ,4#H1##t , ,海蓝
cq.cqnews.net ,2#keywords##content ,12#SPAN#font12 sx022 sx022b hg18 xhx#t#/来源[:|：]\s?([^\s　]*)/ ,1#main_text##h ,12#DIV#wrapper#t ,1#get_title##t , ,海蓝
www.fjsen.com ,2#keywords##content ,12#DIV#content#t#/来源[:|：]\s?([^\s　]*)/ ,1#new_message_id##h ,12#DIV#content#t ,1#new_subject_id##t , ,海蓝
news.cn.yahoo.com ,2#keywords##content ,12#DIV#title#h#/<a[^>]*>([^<]*)/ ,12#DIV#text fixclear#h ,12#DIV#title#t ,4#H1##t , ,海蓝
china.cnr.cn ,2#keywords##content ,12#DIV#lh26 txtcenter#t#/来源[:|：]\s?([^\s　]*)/ ,12#DIV#f12_5a5a5a sanji_left#h ,12#DIV#lh26 txtcenter#t ,12#DIV#hei f24 txtcenter lh26#t , ,海蓝
www.dzwww.com ,2#keywords##content ,12#DIV#top#t#/来源[:|：]\s?([^\s　]*)/ ,12#DIV#con#h ,12#DIV#top#t ,4#H1##t , ,海蓝
www.sq120.com ,12#SPAN#style2#t ,千客网 ,12#SPAN#style43#t ,4#BODY##t ,12#SPAN#style2#t , ,海蓝
www.fsh168.com ,2#keywords##content ,12#TR#tdbg_all#t#/来源[:|：]\s?([^\s　]*)/ ,1#ArticleBody##h#/(<p>[\d\D]*<\/p>)/i ,12#TR#tdbg_all#t ,4#title##innerText#/([^\[]*)/ , ,海蓝
www.fujian.gov.cn ,12#TD#fjyw_xldbt#t ,福建日报 ,1#printdiv##h ,1#printdiv##t ,12#TD#fjyw_xldbt#t ,12#TD#tgray14#t ,海蓝
www.court.gov.cn ,12#TD#detail_title#t ,最高人民法院网站 ,1#zoom##h ,12#TD#detail_time#t ,12#TD#detail_title#t , ,海蓝
www.gzrd.gov.cn ,4#title##innerText ,贵州新闻 ,1#Table1##h ,1#bt##t ,4#title##innerText , ,海蓝
www.chinalaw.gov.cn ,2#keywords##content ,国务院法制办公室 ,1#zoom##t ,12#DIV#t12#t ,12#DIV#mtitle#t , ,海蓝
www.ceming.cn ,2#keywords##content ,千客网 ,1#content##h#/(<p>[\d\D]*<\/p>)/i ,now ,4#H1##t , ,小青
www.fmprc.gov.cn ,4#title##innerText ,外交部网站 ,12#TD#nr13#h ,1#article##t ,4#title##innerText , ,海蓝
www.saic.gov.cn ,2#keywords##content ,12#DIV#zj_four_time#t#/来源[:|：] ([^\s　]*)/ ,1#zoom##h ,12#DIV#zj_four_time#t ,12#TD#blue_dzi#t , ,海蓝
www.daxishi.com ,12#DIV#keyword#t#/关键词：(.*)/ ,千客网 ,12#DIV#entry#h#/(<p>[\d\D]*<\/p>)/#a ,now ,4#H2##t , ,风水
www.cdb.org.cn ,2#keywords##content ,12#DIV#m_c#t#/来源[:|：]\s?([^\s　]*)/ ,12#DIV#Section0#h ,1#news_update##t ,12#P#p0#t , ,海蓝
cxzy.people.com.cn ,2#keywords##content ,1#p_origin##t#/来源[:|：]\s?([^\s　]*)/ ,1#p_content##h#/^([\d\D]*)<br>/img#script#a ,1#p_publishtime##t ,1#p_title##t , ,海蓝
www.dtsjfs.com ,2#keywords##content ,千客风水 ,12#DIV#info_nr#h ,now ,12#DIV#wz_title#t , ,风水
www.888fengshui.com.cn ,2#keywords##content ,千客风水 ,12#DIV#content#h ,now ,12#DIV#arttitle#t , ,风水
dangjian.people.com.cn ,2#keywords##content ,12#TD#ly_red#t#/来源[:|：]\s?([^\s　]*)/ ,1#zoom##h ,12#TD#ly_red#t ,4#H1##t , ,海蓝
ent.xinmin.cn ,2#keywords##content ,1#about##t#/来源[:|：]\s?([^\s　]*)/ ,1#article_info##h#/^([\d\D]*)<img/img ,1#about##t ,4#H1##t , ,海蓝
economy.caixun.com ,2#keywords##content ,千客财经 ,1#Zoom##h##a ,12#DIV#newstip cgray#t ,4#title##innerText#/^([\d\D]*)_/ , ,海蓝
www.chinatibetnews.com ,2#keywords##content ,1#nr_bj_id##t#/来源[:|：]\s?([^\s　]*)/ ,1#nr_size_id##h ,12#TD#title_12pt_red#t ,12#SPAN#tb_content_title#t , ,海蓝
wq.zfwlxt.com ,1#_ctl0_ContentPlaceHolder1_divSubject##t , ,1#_ctl0_ContentPlaceHolder1_divContent##h ,1#_ctl0_ContentPlaceHolder1_divDateLine##t ,1#_ctl0_ContentPlaceHolder1_divSubject##t , ,海蓝
blog.sina.com.cn ,2#keywords##content ,新浪博客 ,1#sina_keyword_ad_area2##h ,12#SPAN#time SG_txtc#t ,1#t_9604f50901011zzy##t , ,海蓝

==========结束=================================