diff options
Diffstat (limited to 'tagesschau.de.txt')
| -rw-r--r-- | tagesschau.de.txt | 23 |
1 files changed, 23 insertions, 0 deletions
diff --git a/tagesschau.de.txt b/tagesschau.de.txt new file mode 100644 index 0000000..be76cd0 --- /dev/null +++ b/tagesschau.de.txt @@ -0,0 +1,23 @@ +title://h1[1] + +author: substring-after(//em, 'Von ') +author:string('tagesschau.de') + +date:substring-after(//div[@class='standDatum'], 'Stand: ') + +body://div[contains(@class, 'article')] | //div[contains(@class, 'centerCol')] + +strip://h1[1] +strip: //div[contains(@class, 'directLinks')] +strip: //div[contains(@class, 'zitatBox')] +strip: //div[contains(@class, 'teaserBox metaBlock')] +strip: //*[contains(@class, 'inv')] +strip: //span[@class='imgSubline'] +strip: //*[contains(@class, 'topline')][1] +strip: //div[@id='rightCol'][1] +strip: //div[@id="footer"][1] +strip: //div[@class="fPlayer"] +strip: //div[@id='seitenanfang'] +strip: //div[@class='standDatum'] +strip: //em +test_url: http://www.tagesschau.de/ausland/wahlkampffrankreich102.html
\ No newline at end of file |