mirror of
https://github.com/webrecorder/pywb.git
synced 2025-03-21 19:12:10 +01:00
4f9310fe4d
add 'parse_comments' rule options for parsing comment contents via regex banner: simplify banner insertion check, only insert for top frame, and check for canon_url matching current href at top before redirecting to top replace em_ -> mp_ as default embedded mod
92 lines
2.7 KiB
YAML
92 lines
2.7 KiB
YAML
|
|
rules:
|
|
|
|
# twitter rules
|
|
#=================================================================
|
|
- url_prefix: 'com,twitter)/i/profiles/show/'
|
|
|
|
fuzzy_lookup: '/profiles/show/.*with_replies\?.*(max_id=[^&]+)'
|
|
|
|
|
|
# facebook rules
|
|
#=================================================================
|
|
# - url_prefix: 'com,facebook)/ajax/pagelet/generic.php/profiletimelinesectionpagelet'
|
|
- url_prefix: 'com,facebook)/ajax/pagelet/generic.php/'
|
|
|
|
fuzzy_lookup: 'com,facebook\)/.*[?&]data=(.*?(?:[&]|query_type[^,]+))'
|
|
|
|
- url_prefix: 'com,facebook)/ajax/ufi/'
|
|
|
|
fuzzy_lookup: '(ft_ent_identifier=[^&]+).*(lsd=[^&]+)'
|
|
|
|
# not actually needed, fuzzy match is used instead here
|
|
# canonicalize:
|
|
# match: 'com,facebook\)/.*[?&]data=([^&]+).*'
|
|
# replace: 'com,facebook)/ajax/pagelet/generic.php/profiletimelinesectionpagelet?data=\1'
|
|
|
|
|
|
- url_prefix: 'com,facebook)/'
|
|
rewrite:
|
|
js_regexs:
|
|
- match: 'Bootloader\.configurePage.*?;'
|
|
replace: '/* {0} */'
|
|
|
|
parse_comments: true
|
|
|
|
|
|
# flickr rules
|
|
#=================================================================
|
|
- url_prefix: ['com,yimg,l)/g/combo', 'com,yimg,s)/pw/combo', 'com,yahooapis,yui)/combo']
|
|
fuzzy_lookup: '([^/]+(?:\.css|\.js))'
|
|
|
|
|
|
- url_prefix: 'com,staticflickr,'
|
|
|
|
fuzzy_lookup:
|
|
match: '([0-9]+_[a-z0-9]+).*?.jpg'
|
|
replace: '/'
|
|
|
|
|
|
# google plus rules
|
|
#=================================================================
|
|
|
|
- url_prefix: 'com,google,plus)/_/stream/getactivities'
|
|
|
|
fuzzy_lookup: '(egk[^"]+).*(f.sid=[^&]+)'
|
|
|
|
- url_prefix: 'com,google,plus)/_/stream/squarestream'
|
|
|
|
fuzzy_lookup: '(cai[^"]+).*(f.sid=[^&]+)'
|
|
|
|
- url_prefix: 'com,google,plus)/_/communities/rt/landing'
|
|
|
|
fuzzy_lookup: 'com,google,plus\)/_/.*?.*\,(\d{13}\])&.*(f.sid=[^&]+).*'
|
|
|
|
|
|
- url_prefix: 'com,google,plus)/_/'
|
|
|
|
fuzzy_lookup: 'com,google,plus\)/_/.*?.*(f.sid=[^&]+)'
|
|
|
|
|
|
# testing rules -- not for valid domain
|
|
#=================================================================
|
|
# this rule block is a non-existent prefix merely for testing
|
|
- url_prefix: 'example,example,test)/'
|
|
|
|
canonicalize:
|
|
match: '(example,example,test\)/.*?)[?].*?(id=value).*'
|
|
replace: '\1?\2'
|
|
|
|
rewrite:
|
|
js_rewrite_location: False
|
|
|
|
|
|
# all domain rules -- fallback to this dataset
|
|
#=================================================================
|
|
# Applies to all urls -- should be last
|
|
- url_prefix: ''
|
|
fuzzy_lookup:
|
|
match: '(.*)[&?](?:_|uncache)=[\d]+[&]?'
|
|
filter: '=urlkey:{0}'
|
|
replace: '?'
|