Class: WebPageParser::BbcNewsPageParserV2

Inherits:

BaseRegexpParser

• Object
• BaseParser
• BaseRegexpParser
• WebPageParser::BbcNewsPageParserV2

Defined in:

lib/web-page-parser/parsers/bbc_news_page_parser.rb

Overview

BbcNewsPageParserV2 parses BBC News web pages

Direct Known Subclasses

BbcNewsPageParserV3

Constant Summary

TITLE_RE =

ORegexp.new('<meta name="Headline" content="(.*)"', 'i')

DATE_RE =

ORegexp.new('<meta name="OriginalPublicationDate" content="(.*)"', 'i')

CONTENT_RE =

ORegexp.new('S BO -->(.*?)<!-- E BO', 'm')

STRIP_BLOCKS_RE =

ORegexp.new('<(table|noscript|script|object|form)[^>]*>.*?</\1>', 'i')

STRIP_TAGS_RE =

ORegexp.new('</?(b|div|img|tr|td|br|font|span)[^>]*>','i')

STRIP_COMMENTS_RE =

ORegexp.new('<!--.*?-->')

STRIP_CAPTIONS_RE =

ORegexp.new('<!-- caption .+?<!-- END - caption -->')

WHITESPACE_RE =

ORegexp.new('[\t ]+')

PARA_RE =

Regexp.new('</?p[^>]*>', Regexp::IGNORECASE)

Constants inherited from BaseRegexpParser

WebPageParser::BaseRegexpParser::HTML_ENTITIES_DECODER, WebPageParser::BaseRegexpParser::KILL_CHARS_RE

Instance Attribute Summary

Attributes inherited from BaseParser

#url

Method Summary

Methods inherited from BaseRegexpParser

#content, #date, #decode_entities, #encode, #initialize, #page, #retrieve_page, #title

Methods inherited from BaseParser

#content, #date, #guid, #guid_from_url, #hash, #initialize, #page, #retrieve_page, #title

Constructor Details

This class inherits a constructor from WebPageParser::BaseRegexpParser