diff options
| author | zinnober <cinnabarit@mailbox.org> | 2014-09-03 11:02:58 +0200 |
|---|---|---|
| committer | zinnober <cinnabarit@mailbox.org> | 2014-09-03 11:02:58 +0200 |
| commit | a390429e1979b0ddea24d7c9b846e027039990da (patch) | |
| tree | 8eda22fd17bc12447bf0aced5e77513e1e2c16a7 | |
| parent | c159266a63cd8145f6007076becb53305c1df84a (diff) | |
| download | ftr-site-config-a390429e1979b0ddea24d7c9b846e027039990da.tar.gz ftr-site-config-a390429e1979b0ddea24d7c9b846e027039990da.zip | |
Initial submit.
| -rw-r--r-- | tagesspiegel.de.txt | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/tagesspiegel.de.txt b/tagesspiegel.de.txt new file mode 100644 index 0000000..57e7d3d --- /dev/null +++ b/tagesspiegel.de.txt @@ -0,0 +1,60 @@ +# Author: zinnober +# Should work with "normal" articles as well as with image galleries + +prune: no + +# Title +title: //h1/span[@class='hcf-headline'] + +# Set author +author: //a[@rel='author'] + +# Set date +date: //span[@class='date hcf-atlas'] + +# Fetch full multipage articles +next_page_link: //a[contains(@class, 'hcf-forward')] + +# Content is here +body: //article +body: //div[contains(@class, 'hcf-screen')] + +# Remove tracking and ads +strip_id_or_class: hcf-ad +strip_id_or_class: hcf-autoload-ad +strip_id_or_class: hcf-content-ad + +# Tidy up before article +strip: //article/h1 +strip_id_or_class: hcf-atlas +strip_id_or_class: hcf-author +strip_id_or_class: date hcf-atlas +strip_id_or_class: date hcf-atlas + +# General cleanup +strip: //div[contains(@class, 'hcf-screen')]//h1 +strip: //div[@class='hcf-subpage-titles']//ul +strip_id_or_class: hcf-doctype-media +strip_id_or_class: hcf-inline-gallery +strip_id_or_class: hcf-doctype-video +strip_id_or_class: hcf-links +strip_id_or_class: hcf-mini-navi +strip_id_or_class: hcf-media-control +strip_id_or_class: hcf-hidden +replace_string(<span class="hcf-update">Update</span>): <strong>Update: </strong> + +# Fix pictures and captions +replace_string(<a class="hcf-doctype-gallery): <p class="hcf-doctype-gallery +replace_string(<a class="hcf-doctype-enlarge): <p class="hcf-doctype-enlarge +replace_string(<figcaption class="hcf-caption">): <br><small><em> +replace_string(</figcaption>): </em></small> + +# Fix image galleries +replace_string(<a class=" ajaxify): <p class="ajaxify +replace_string(<div class="hcf-caption"><div><p>): <small><em> + +# Try it yourself +test_url: http://www.tagesspiegel.de/berlin/bezirke/wedding/wedding-jetzt/auf-der-suche-nach-einem-stadtteil-wilder-weiter-wedding/8757156.html +test_url: http://www.tagesspiegel.de/berlin/olympia-in-berlin-der-flughafen-tegel-soll-das-olympische-dorf-werden/10645036.html +test_url: http://www.tagesspiegel.de/mediacenter/fotostrecken/berlin/bildergalerie-kreuzberger-der-woche/9305534.html + |