url |
^http://.+\.(riverfronttimes|sfweekly)\.com/ |
nextLink |
//a[@class='next'] |
pageElement |
//div[@class='archiveListing clearfix']|id('searchResults')/*[h4]|//div[contains(@id,'storyBody')]/*[not(@class='pageNumber' or @class='content_insert' or @class='storyPagination')] |
exampleUrl |
http://www.riverfronttimes.com/stlouis/ArticleArchives?section=2348800 http://www.sfweekly.com/sanfrancisco/gag-order-sex-workers-allege-mistreatment-at-kinkcom/Content?oid=2188021 http://www.sfweekly.com/sanfrancisco/ArticleArchives?categoryType=Blog |