Content creation from extracted content

A system comprising:

• a memory;
• and
• at least one processor, connected with the memory, executing a process comprising:
• receiving input information for content creation, wherein the input information comprising a link to a landing page and keyword information,
• evaluating the landing page and extracting content including at least one of image data and text data from the landing page,
• analyzing properties of the content extracted,
• ranking the content extracted based on the analyzed properties of the content and application of at least two ranking algorithms, wherein a first ranking algorithm applied ranks the content extracted based on relevance to the landing page and a second ranking algorithm applied ranks the content extracted based on relevance to the keyword information,
• filtering the ranked content to remove content or portions of content that are determined to be unappealing based on applying filtering rules to the ranked content, and
• creating at least one abstract from the filtered and ranked content.

A computer-readable storage device containing instructions, that when executed on at least one processor, causing the processor to execute a process comprising:

• receiving input information for content creation, wherein the input information comprising a link to a landing page and keyword information;
• evaluating the landing page and automatically extracting content including image data and text data from the landing page using machine learning algorithms;
• analyzing properties of the content extracted;
• ranking the image data and the text data extracted based on the analyzed properties of the content and application of at least two ranking algorithms, wherein a first ranking algorithm applied ranks content extracted based on relevance to the landing page and a second ranking algorithm applied ranks the content extracted based on relevance to the keyword information;
• filtering the ranked content to remove content or portions of content that are determined to be unappealing based on applying filtering rules to the ranked content, wherein the filtering comprising updating ranking of ranked image data and ranked text data based on application of the filtering rules that evaluate at least one of relevance to how dominant content is to the landing page, relevance to the keyword information, and relevance determined from user response data;
• and
• creating at least one rich format abstract from the filtered and ranked content, wherein the creating arranges and aggregates filtered image data and filtered text data to create the at least one rich format abstract.