diff options
Diffstat (limited to 'bookforum.com.txt')
| -rw-r--r-- | bookforum.com.txt | 19 |
1 files changed, 19 insertions, 0 deletions
diff --git a/bookforum.com.txt b/bookforum.com.txt new file mode 100644 index 0000000..03b6003 --- /dev/null +++ b/bookforum.com.txt @@ -0,0 +1,19 @@ +#metadata +title://div[@class = 'Topper']/h1 +author://div[@class = 'Topper']/h3 +date://div[@class = 'Topper']/h6 +body://div[@class = 'Core'] + + + +# clean up +strip://div[@class = 'Topper']/h1 +strip://div[@class = 'Topper']/h3 +strip://div[@class = 'Topper']/h4 +strip://div[@class = 'Topper']/h5 +strip://div[@class = 'Topper']/h6 +strip://br[@clear = 'all'] +strip://div[@class = 'adCore'] +strip://div[@class = 'BookR'] +strip://div[@class = 'InfoBox'] +test_url: http://bookforum.com/inprint/018_04/8595
\ No newline at end of file |
