diff options
| -rw-r--r-- | .elpais.com.txt | 12 | ||||
| -rw-r--r-- | elpais.com.txt | 1 |
2 files changed, 12 insertions, 1 deletions
diff --git a/.elpais.com.txt b/.elpais.com.txt index 0e7eebc..d1ada71 100644 --- a/.elpais.com.txt +++ b/.elpais.com.txt @@ -1,13 +1,23 @@ title: //meta[@name='DC.title']/@content +title: //div[contains(@class, 'cabecera_noticia')]//h1 date: //meta[@name='DC.date']/@content +date: //meta[@name='date']/@content body: //div[@class='columna_texto'] body: //div[@id='cuerpo_noticia'] +body: //div[@class='estructura_2col_1zq']//div[@class='margen_n'] + prune: no strip_id_or_class: disposicion_vertical strip_id_or_class: ampliar_foto +strip_id_or_class: utilidades +strip_id_or_class: info_relacionada +strip_id_or_class: m-kiosko +strip_id_or_class: info_complementa strip: //div[starts-with(@id, 'sumario') and contains(., 'más información')] +strip: //div[@id='coment' or @id='foros_not'] +strip: //picture//source test_url: http://economia.elpais.com/economia/2012/02/07/actualidad/1328611790_342868.html -test_url: http://internacional.elpais.com/internacional/2012/02/07/actualidad/1328602145_448315.html
\ No newline at end of file +test_url: http://internacional.elpais.com/internacional/2012/02/07/actualidad/1328602145_448315.html diff --git a/elpais.com.txt b/elpais.com.txt index 7552afa..de8e8a4 100644 --- a/elpais.com.txt +++ b/elpais.com.txt @@ -17,6 +17,7 @@ strip_id_or_class: info_complementa strip: //div[starts-with(@id, 'sumario') and contains(., 'más información')] strip: //div[@id='coment' or @id='foros_not'] +strip: //picture//source test_url: http://elpais.com/elpais/2012/02/06/gente/1328526783_491687.html test_url: http://elpais.com/diario/2012/02/07/cultura/1328569202_850215.html |
