pywb/pywb/rules.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'

      fuzzy_lookup: 'com,facebook\)/.*[?&]data=(.*?(?:[&]|query_type[^,]+))'

# 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} */'


    # 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: '/'


    # 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: '?'