From 26dc5a8f2f43cef6d8e71b70c7e82d1ed4f52247 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Fri, 15 Jan 2010 12:05:13 -0700 Subject: [PATCH] New recipe for MSNBC by Darko Miletic --- resources/images/msnbc.png | Bin 0 -> 3328 bytes resources/recipes/msnbc.recipe | 58 +++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) create mode 100644 resources/images/msnbc.png create mode 100644 resources/recipes/msnbc.recipe diff --git a/resources/images/msnbc.png b/resources/images/msnbc.png new file mode 100644 index 0000000000000000000000000000000000000000..be861438d9c0f544eb6756cc6c3ace2909eeb80f GIT binary patch literal 3328 zcmV+b4gd0qP)C zaJp>pbn?e(u|KMlIqbUbDYAe6*~JF{I1T_z8u`=V`AjhTzmg}^ zz+_H;ScX2TBIau7R6}JdJfH6RWO_cT#nq7Tf0n>*;x;g(LR5dCtt{zHff8TLr zrezriqfzUZhRJUL$WCSJOfsqJq|9@sEHHCTexUy=gD<{v)9}u=h0e*LfDw)qW2=`O zYq)mZ6T!x&$B3xg+dHf8#K;{xUhTZ~@Zr?7T+ZQG%q}ij+StDO;+CJ+CPLpOqT%1E z6Q2w7FthDsM;|!!jqm*V@Nf2qBvSx9GUKp`_*E-MW`1SUkHamqz74?WIy&^%PjA`t z#rF^Ng+vrk1&9zZ8H*M+=Dz%Am;5LkvF<0L?76a>asU1I!%wBm>`!~;T3Kdha&x(j z9e@9iUmtvWM~sRJ^8LY4 z3*^GUr)tEYq>W^nTx?0?H zhCu)b3||7vXOW&!E*$N;q^oCS&B>u0i&U<&j_+jv7#S__iJr_f0MT=0IddxJVP*o5 z0MG;=2w((2zp9ct4y$T8>ZQ*KLoGo?Q5eld7c8&G##=9vy?c(M?Y&-RCZP#g092Jl z#3&(y8y#1g92ZfODW|G^%-k;`lXgaPsu@UCZ`Q)-4bpq46`8?W1cJTPG;cr0n}23c zPo6NMVR16UWhdCvCm=9HK@n2|4fR}?jK~Ka22Ku*F?kMCDGL=ig+rD!CS$z-mhbKu zzU`f!(G^{zg~ar5VEFuGc<-{7*s~$qc*1pEx7uHGGF++ZE!yAlaN)&Ao16o0vF1lX zY|f&F^DeU1Z(bE$vMLo?Jfkq&y)Q^a>Zqz1G6!t)1l{CFB{aAmJ| z2#6?V&#uk3%&eX9%v*gAeQihg(!p#IZi%QG>w?C-TjnM{{mpAhEXYO(vzp##mx3vK-jYG)81`!abi@}J5 z;5veQ-VtH~045^wn2n(jRmEkO&kO&@zSQMk-`-^uMZtiWP(X=K=3M!^J$<#d$@ks8 zt|c9`_$PiiO<*Aab#TURDsFvzn)G&p0;MX|GIbjabuuWv@)XrBXkvR|6QCj$=T)Vg z0ggq5Z5sj0kZ{C;Y6~*^}jW26G%BD(N7wr;q_KL6IJF`S4(FfvVQ|>y^t8@(vP^R993p zC#4+uisPOKB|ioEty_@1dKK)&&EAG_Rw5=?P4!^gh8;9fn+OSr$^|S6h$@h5ipsLp z)8)xsC*X(*L(7FN7%y@mKpa(!79=c+fIpzs5Xw_9Hbep2UznApUXubrbSMR5a4+JQ zT_i9FP#SM)K?8P6qZqag%QB=c5rV-bNR)d35oFo2W}L`^Ur*)4E=RxOI5AL$B(X)1 zxNQtEVeE7e>gVMAebkT?s8*t04J9IC7=Y}53ALBZW3w?j&O!um$b^-wV`2lQ$y{F_ zX2YN|_89=85sMcsZRQt_q>+U(dr%|-Qw3(k0N8<|K4M{Mb7Vge4V(g@GK@rIh@uUT zS?j;N7aWDUUIY}V@HPRe5EumaNE;%Nj6_x}gqC6}P=G@=0*M-dH~hroA()m~>2)HC z`STm#L__%Z&NLFtm7eI?s=zg`iXbz-d)f58OJ+oWC?cs-AXLtPC%<7XTKi4w+B@30 zCOMu^^&&K`T{NEtb?ijlH5ZDn6$@K7jG7v#$4Zf?1=|`QOGFhbR?fio6Qk%GEsob# z)heiBNo`Obykf?C>s#x;0pN}5*=z#VRpmlBqqig9_bK~RpWhYS@W24iS|%uJ1xiY# zGy`C$!a1;m6H8~YwWuDd!Yayv`Z%nHdM-D)csz($)GDP>6peKeG|#Wc3+-vRdaCn9 z07I_e4`;>YpRb*BY{ROi*9@k$0RB`}S59~?q^f|rGcnTsmvZp?w@Z4P0cQ|oHi8=0 zOXRk@x$xS{D8BjMA|rzgs=$dsfTVha-g}Odx7>iP?>r%z7Y@#AfSstXj2MZ!5E>gI z_~2+7M1(7^oR7WzW7sp0h5znZyiClETDWt06V|ro@$9kxZ26mQZ~w_aVF-yp4OTa_ zV&nYl|D`#c{99)3Frk`6diS?w|6grzhj)1~Q;}jnmoCwC&S{7c{&cXQ#@XW$;* zS#pa=Jf=W?=dUF3h3mL)P9yT~_lVh0!zhg;LPQ)0FluUoa9lxiQw+cVk2p zVUHn-swe>1FgJnCt7=iSJ8;L_PxEU-?Z~MDq@b}Bev#?K{^4UAzty@aGPic_R~h+% z>!suInj>U_7Xqtq08xP9)dZMWQ~hiX?nTX|D_Bk9 zKtnBvr~)Anp{6DT09d-D3H=4&*S#aKy~-U^MXkxWcV!ayuB*fD{PVc8?NMwUI*1|( zELH>vFj-+U@Uzsr_9KUW@!9lP`eqZO?VB{UH4Hd@qO4?<2n;s`>E0q3*v|G<_rX|l zsT5w`!gBmwfK*@-yYD=U`pY-T$ro!mv|vsp`ej8k=Ohq|+PL7t^YGLCDP#qRGQk0` zwxtI5U0jb)q6c^G{vMtm>3|Id`Fq=~oI`BYVzHA+j}$6;(AX5kq6G~w5>Y(Y zodF1_u?*a^tPu}iU5hu}m+;4L{Q$qt9Dzlp9z_07V!|nK%*o>L@bPIT*fK%PP!}Nb z&mcJEPK5wCX}Deg$`pAG!FBh*nY)tnFZ>9a9soMu;-;IfffX-7$ZsBP-UR4R zmU@{Ohf`^cP(X8{ncZ;Ty9;L1F^Oz`5atC}qPXvMi8ooW8E4*-co2#J;iUOGI4 z&5P^t#OIok3B7{#yY9nd{kxHqEX=BK>s0?KaDf%ag^9WC#KytL z>w`y;WpF!??LlDnjjXj-0jeP8QwGA8Mibp`8}8osU)Yv8j3P={AFB>Dk#_^)3p}CJ zMFqIAet~=Y!W(}Tx8px2$8o^S2>^Fu;MI-Vzr7xX69I*AbpcJ#bH*m{bwV8tX^<@ zoYrYyvre_nH47i*n!ps*kME{>wRx@(noP%sC4T~;PayOOgg$}L|1X687f)=es{^ia z4FCWDC3HntbYx+4WjbSWWnpw>05UK!FfA}KEipAzF)}(ZGdeLhEigAaFfasz!$<%C z03~!qSaf7zbY(hiZ)9m^c>ppnF)%GKF)cAQR53L=H8(mkHZ3qWIxsL;>3zch0000< KMNUMnLSTZyXena= literal 0 HcmV?d00001 diff --git a/resources/recipes/msnbc.recipe b/resources/recipes/msnbc.recipe new file mode 100644 index 0000000000..6e2fc50aaa --- /dev/null +++ b/resources/recipes/msnbc.recipe @@ -0,0 +1,58 @@ +__license__ = 'GPL v3' +__copyright__ = '2010, Darko Miletic ' +''' +msnbc.msn.com +''' + +import re +from calibre.web.feeds.recipes import BasicNewsRecipe + +class MsNBC(BasicNewsRecipe): + title = 'msnbc.com' + __author__ = 'Darko Miletic' + description = 'A Fuller Spectrum of News' + oldest_article = 2 + max_articles_per_feed = 100 + no_stylesheets = True + use_embedded_content = False + encoding = 'utf8' + publisher = 'msnbc.com' + category = 'news, USA, world' + language = 'en' + extra_css = ' body{ font-family: sans-serif } .head{font-family: serif; font-size: xx-large; font-weight: bold; color: #CC0000} .abstract{font-weight: bold} .source{font-size: small} .updateTime{font-size: small} ' + + conversion_options = { + 'comments' : description + ,'tags' : category + ,'language' : language + ,'publisher': publisher + } + + preprocess_regexps = [ + (re.compile(r'', re.DOTALL|re.IGNORECASE),lambda match: '') + ,(re.compile(r'
', re.DOTALL|re.IGNORECASE),lambda match: '
'), + ] + + remove_tags_before = dict(name='div', attrs={'class':'head'}) + remove_tags_after = dict(name='div', attrs={'class':'copyright'}) + remove_tags = [dict(name=['iframe','object','link','script','form'])] + + feeds = [ + (u'US News' , u'http://rss.msnbc.msn.com/id/3032524/device/rss/rss.xml' ) + ,(u'World News' , u'http://rss.msnbc.msn.com/id/3032506/device/rss/rss.xml' ) + ,(u'Politics' , u'http://rss.msnbc.msn.com/id/3032552/device/rss/rss.xml' ) + ,(u'Business' , u'http://rss.msnbc.msn.com/id/3032071/device/rss/rss.xml' ) + ,(u'Sports' , u'http://rss.nbcsports.msnbc.com/id/3032112/device/rss/rss.xml') + ,(u'Entertainment' , u'http://rss.msnbc.msn.com/id/3032083/device/rss/rss.xml' ) + ,(u'Health' , u'http://rss.msnbc.msn.com/id/3088327/device/rss/rss.xml' ) + ,(u'Tech & Science', u'http://rss.msnbc.msn.com/id/3032117/device/rss/rss.xml' ) + ] + + def print_version(self, url): + return url + 'print/1/displaymode/1098/' + + def preprocess_html(self, soup): + for item in soup.head.findAll('div'): + item.extract() + return soup +