diff options
Diffstat (limited to 'welt.de.txt')
| -rw-r--r-- | welt.de.txt | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/welt.de.txt b/welt.de.txt new file mode 100644 index 0000000..42e65e9 --- /dev/null +++ b/welt.de.txt @@ -0,0 +1,22 @@ +# set body +tidy: no +body: //div[contains(@class, 'articleContent')] + +# remove clutter +strip: //div[@class='advertising'] +strip: //div[@class='themenalarm'] +strip: //div[contains(@class, 'inTextTeaser')] + +# remove captions +strip: //span[@class='copyRight'] + +# remove photo galleries and extras +strip: //div[contains(@class, 'textGallery')] +strip: //div[contains(@class, 'videoGallery')] +strip: //div[contains(@class, 'imageGallery')] +strip: //div[contains(@class, 'openContent')] + +# remove comments +strip: //div[@id = 'writeComment'] + +test_url: http://www.welt.de/vermischtes/weltgeschehen/article11050589/27-Bergleute-in-neuseelaendischer-Mine-vermisst.html
\ No newline at end of file |