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/'

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

    - url_prefix: 'com,facebook)/ajax/ufi/'

      fuzzy_lookup:
          - ft_ent_identifier
          - lsd

    - url_prefix: 'com,facebook)/ajax/chat/hovercard/sidebar.php'

      fuzzy_lookup:
          - ids[0]

    - url_prefix: 'com,facebook)/login.php'

      fuzzy_lookup:
          - email
          - lgnrnd
          - lsd

    # fallback for all /ajax/
    - url_prefix: 'com,facebook)/ajax/'

      fuzzy_lookup: '([?&][^_]\w+=[^&]+)+'

    - url_prefix: 'com,facebook)/'
      rewrite:
        js_regexs:
            - match: 'Bootloader\.configurePage.*?;'
              replace: '/* {0} */'

        parse_comments: true

    - url_prefix: 'com,facebook'
      rewrite:
          cookie_scope: root


    # instagram rules
    #=================================================================
    - url_prefix: 'net,cloudfront,'

      rewrite:
          js_regexs:
              - match: '\burl\((//[^)]+)\)'
                rewrite: true
                group: 1

    - url_prefix: 'com,instagram)/p/'

      fuzzy_lookup: '()'


     # 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=[^&]+)'
      fuzzy_lookup: 'f.req=.*\]\]\]\,\"([^"]+).*(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=[^&]+)'


    # vimeo rules
    #=================================================================

    - url_prefix: 'com,vimeo,av)/'

      # only use non query part of url, ignore query
      fuzzy_lookup: '()'

    - url_prefix: 'com,vimeocdn,'

      fuzzy_lookup: '()'

    - url_prefix: 'metadata)/player.vimeo.com/'

      fuzzy_lookup:
          match: '()'
          replace: '&'

    - url_prefix: 'com,vimeo,player)/log/'

      fuzzy_lookup:
          - id
          - ownerId
          - videoFileId
          - signature


    # youtube rules
    #=================================================================

    - url_prefix: 'com,youtube)/get_video_info'

      fuzzy_lookup:
          - video_id
          - html5

    - url_prefix: 'com,youtube,s)/api/stats/qoe'

      fuzzy_lookup:
          - docid

    - url_prefix: 'com,youtube,s)/api/stats/watch'

      fuzzy_lookup:
          - docid

    - url_prefix: 'com,youtube,c'

      fuzzy_lookup: 'com,youtube,c.*/videogoodput.*(id=[^&]+)'

    - url_prefix: 'com,googlevideo,'

      fuzzy_lookup:
          match: 'com,googlevideo.*/videoplayback.*(id=[^&]+).*(itag=[^&]+).*(mime=[^&]+)'
          filter:
              - '~urlkey:{0}'
              - '!mimetype:text/plain'

          type: 'domain'

    # comments support
    - url_prefix: 'com,googleapis,plus)/u/0/_/widget/render/comments'

      rewrite:
          js_rewrite_location: location

      fuzzy_lookup:
          - href
          - stream_id
          - substream_id

    - url_prefix: 'com,ytimg,s)/yts/jsbin/'

      rewrite:
          js_rewrite_location: location


    # testing rules -- not for valid domain
    #=================================================================
    # this rule block is a non-existent prefix merely for testing
    - url_prefix: 'example,example,test,loconly)/'

      rewrite:
        js_rewrite_location: location

    - url_prefix: 'example,example,test)/'

      canonicalize:
        match: '(example,example,test\)/.*?)[?].*?(id=value).*'
        replace: '\1?\2'

      fuzzy_lookup:
          - param1
          - id

      rewrite:
        js_rewrite_location: urls


      # 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: '?'