updated specific configuration for parsing

This commit is contained in:
Nicolas Lœuillet
2014-07-13 10:15:40 +02:00
parent 58dbe10388
commit 4e067ceabd
952 changed files with 7585 additions and 5682 deletions

36
inc/3rdparty/site_config/standard/amazon.com.txt vendored Normal file → Executable file
View File

@ -1,19 +1,19 @@
title: //span[@id = 'btAsinTitle']
body: (//*[@id='prodImageCell']//a)[1] | //div[@id = 'ps-content'] | //span[@id='actualPriceValue'] | //h2[.='Product Details']/following-sibling::div | //div[@class='h2' and .='Product Description']/following-sibling::div
#strip_id_or_class: quantityDropdownDiv
#strip_id_or_class: addToCartSpan
#strip_id_or_class: oneClickDiv
strip_id_or_class: nocontent
strip_id_or_class: masDynamicConten
strip_id_or_class: dynamic-content
prune: no
find_string: <span id="actualPriceValue">
replace_string: <span id="actualPriceValue"><br />Price:
strip_id_or_class: collapsePS
strip_id_or_class: expandPS
strip_id_or_class: psPlaceHolde
strip: //li[contains(., 'update product info') or contains(., 'give feedback on images')]
title: //span[@id = 'btAsinTitle']
body: (//*[@id='prodImageCell']//a)[1] | //div[@id = 'ps-content'] | //span[@id='actualPriceValue'] | //h2[.='Product Details']/following-sibling::div | //div[@class='h2' and .='Product Description']/following-sibling::div
#strip_id_or_class: quantityDropdownDiv
#strip_id_or_class: addToCartSpan
#strip_id_or_class: oneClickDiv
strip_id_or_class: nocontent
strip_id_or_class: masDynamicConten
strip_id_or_class: dynamic-content
prune: no
find_string: <span id="actualPriceValue">
replace_string: <span id="actualPriceValue"><br />Price:
strip_id_or_class: collapsePS
strip_id_or_class: expandPS
strip_id_or_class: psPlaceHolde
strip: //li[contains(., 'update product info') or contains(., 'give feedback on images')]
test_url: http://www.amazon.com/Common-Sense-Forestry-Living-Mother/dp/1931498210/