Manual de usuario de calibre, Publicación 2.73.0
# should immediately be fired. I've seen it used to hold nothing at all but with
# 20 or so empty lines in it. Also to hold a single link to another article.
# Whatever it was designed to do it is not wanted by this recipe. Exact
# match only.
o_reg_exp = '^o$'
# Remove 'promotopbg' and 'promobottombg', link lists. Have decided to
# use two reg expressions to make removing this (and variants) robust.
promo_top_reg_exp = '^.*promotopbg.*$'
promo_bottom_reg_exp = '^.*promobottombg.*$'
# Remove 'nlp', provides heading for link lists. Requires an exact match due to
# risk of matching those letters in something needed, unless I see a variation
# of 'nlp' used at a later date.
nlp_reg_exp = '^nlp$'
# Remove 'mva', provides embedded floating content of various types. Variant 'mvb'
# has also now been seen. Requires an exact match of 'mva' or 'mvb' due to risk of
# matching those letters in something needed.
mva_or_mvb_reg_exp = '^mv[ab]$'
# Remove 'mvtb', seems to be page navigation tools, like 'blq-mast'.
mvtb_reg_exp = '^mvtb$'
# Remove 'blq-toplink', class to provide a link to the top of the page.
blq_toplink_reg_exp = '^.*blq[_ -]*top[_ -]*link.*$'
# Remove 'products and services' links, Eg. desktop tools, alerts, and so on.
# Eg. Class="servicev4 ukfs_services" - what a mess of a name. Have decided to
# use two reg expressions to make removing this (and variants) robust.
prods_services_01_reg_exp = '^.*servicev4.*$'
prods_services_02_reg_exp = '^.*ukfs[_ -]*services.*$'
# Remove -what I think is- some kind of navigation tools helper class, though I am
# not sure, it's called: 'blq-rst blq-new-nav'. What I do know is it pops up
# frequently and it is not wanted. Have decided to use two reg expressions to make
# removing this (and variants) robust.
blq_misc_01_reg_exp = '^.*blq[_ -]*rst.*$'
blq_misc_02_reg_exp = '^.*blq[_ -]*new[_ -]*nav.*$'
# Remove 'puffbox' - this may only appear inside 'storyextra', so it may not
# need removing - I have no clue what it does other than it contains links.
# Whatever it is - it is not part of the article and is not wanted.
puffbox_reg_exp = '^.*puffbox.*$'
# Remove 'sibtbg' and 'sibtbgf' - some kind of table formatting classes.
sibtbg_reg_exp = '^.*sibtbg.*$'
# Remove 'storyextra' - links to relevant articles and external sites.
storyextra_reg_exp = '^.*story[_ -]*extra.*$'
˓→
remove_tags = [dict(name='div', attrs={'class': re.compile(story_feature_reg_exp,
re.IGNORECASE)}),
dict(name='div', attrs={'class': re.compile(
share_help_reg_exp, re.IGNORECASE)}),
dict(name=