Detecting compatible layouts for content-based native ads
A plurality of pages associated with a website are crawled. Page information is generated for the plurality of pages. A plurality of locations that are compatible with a content template are determined based at least the page information for the plurality of pages. The content template is embedded in at least one of the plurality of locations.
1. A method, comprising:
crawling a plurality of pages associated with a website;
generating corresponding page information for the plurality of pages;
determining, based at least the page information, a plurality of potential locations that are compatible with a content template for one of the plurality of pages, wherein the content template is configured to be used to generate a content item, wherein the content template is configured to define one or more attributes associated with the content item; and
embedding the content template in at least one selected location of the plurality of potential locations that are compatible with the content template for the one of the plurality of pages, wherein the content item is displayed at the at least one selected location of the plurality of potential locations upon a page corresponding to the at least one selected location of the plurality of potential locations being loaded.
2. The method of claim 1 , further comprising providing a plurality of renderings of the content template at the plurality of potential locations that are compatible with the content template.
3. The method of claim 2 , further comprising receiving a selection of the at least one of the plurality of potential locations that are compatible with the content template.
4. The method of claim 3 , further comprising updating a placement group associated with the content template.
5. The method of claim 4 , wherein the placement group includes one or more locations at which the content template is to be placed.
6. The method of claim 1 , wherein the plurality of potential locations are determined to be compatible with the content template based in part on a corresponding structural layout.
7. The method of claim 1 , further comprising generating a selector based on portions of a page.
8. The method of claim 7 , wherein the selector is compared to the page information for the plurality of pages.
9. The method of claim 7 , wherein the selector is a cascading style sheets selector.
10. The method of claim 7 , wherein the selector is configured to identify elements of a page that are compatible with the content template.
11. The method of claim 1 , wherein the plurality of potential locations that are compatible with the content template are determined to be compatible with the content template based on a similarity score.
12. The method of claim 11 , wherein the similarity score is based on a cosine similarity.
13. The method of claim 1 , wherein the plurality of potential locations are determined to be compatible with the content template based on corresponding structural vectors.
14. The method of claim 13 , wherein the corresponding structural vectors are based on a term frequency-inverse document frequency value.
15. The method of claim 1 , further comprising monitoring the plurality of pages for one or more changes.
16. The method of claim 15 , further comprising detecting a change to at least a first page of the plurality of pages.
17. The method of claim 16 , further comprising determining that the content template is compatible with the detected change.
18. The method of claim 16 , further comprising determining that the content template is not compatible with the detected change.
19. A system, comprising:
a processor configured to:
crawl a plurality of pages associated with a web site;
generate corresponding page information for the plurality of pages;
determine, based at least the page information for the plurality of pages, a plurality of potential locations that are compatible with a content template for one of the plurality of pages, wherein the content template is configured to be used to generate a content item, wherein the content template is configured to define one or more attributes associated with the content item; and
embed the content template in at least one selected location of the plurality of potential locations that are compatible with the content template for the one of the plurality of pages, wherein the content item is displayed at the at least one selected location of the plurality of potential locations upon a page corresponding to the at least one selected location of the plurality of potential locations being loaded; and
a memory coupled to the processor and configured to provide the processor with instructions.
20. A computer program product, the computer program product being embodied on a non-transitory computer readable storage medium and comprising instructions for:
crawling a plurality of pages associated with a web site;
generating corresponding page information for the plurality of pages;
determining, based at least the page information for the plurality of pages, a plurality of potential locations that are compatible with a content template for one of the plurality of pages, wherein the content template is configured to be used to generate a content item, wherein the content template is configured to define one or more attributes associated with the content item; and
embedding the content template in at least one selected location of the plurality of potential locations that are compatible with the content template for one of the plurality of pages, wherein the content item is displayed at the at least one selected location of the plurality of potential locations upon a page corresponding to the at least one selected location of the plurality of potential locations being loaded.