SYSTEMS AND METHODS FOR SCRAPING URLS BASED ON VIEWPORT VIEWS
Systems, methods, and non-transitory computer readable media are configured to receive a uniform resource locator. A time and one or more features associated with the uniform resource locator can be provided to a first machine learning model. A prediction relating to a quantity of views the uniform resource locator achieves by the time can be received from the first machine learning model.
1 . A computer-implemented method comprising:
determining, by a computing system, a quantity of views associated with a uniform resource locator for a first time;
determining, by the computing system, a predicted quantity of views associated with the uniform resource locator for a second time by a machine learning model based on one or more features associated with the uniform resource locator;
determining, by the computing system, a viewport view speed associated with the uniform resource locator based on the quantity of views associated with the uniform resource locator for the first time, the predicted quantity of views associated with the uniform resource locator for the second time, and a period of time between the first time and the second time; and
causing, by the computing system, the uniform resource locator to be scraped based on the viewport view speed.
2 . The computer-implemented method of claim 1 , further comprising:
providing, by the computing system, a prediction of whether the uniform resource locator will achieve a threshold viewport view speed between the first time and the second time.
3 . The computer-implemented method of claim 1 , wherein the uniform resource locator is caused to be scraped further based on the viewport view speed satisfying a threshold viewport view speed, wherein the threshold viewport view speed is based on a period of time to make a prediction of the contents referenced by the uniform resource locator.
4 . The computer-implemented method of claim 1 , wherein the determining the viewport view speed comprises:
determining a slope based on a difference between the predicted quantity of views associated with the uniform resource locator for the second time and the quantity of views associated with the uniform resource locator for the first time, and further based on the period of time between the first time and the second time.
5 . The computer-implemented method of claim 1 , wherein the first time is based on a first elapsed time since a provision of the uniform resource locator and the second time is based on a second elapsed time since the provision of the uniform resource locator.
6 . The computer-implemented method of claim 1 , wherein the one or more features associated with the uniform resource locator includes at least one of: an identifier for the uniform resource locator, a domain for the uniform resource locator, a text token for the uniform resource locator, historical data for a resource referenced by the uniform resource locator, or historical data for the domain for the uniform resource locator.
7 . The computer-implemented method of claim 1 , wherein the machine learning model is trained based on training data, wherein the training data includes feature data of a training uniform resource locator and a quantity of views for the training uniform resource locator associated with an elapsed time.
8 . The computer-implemented method of claim 1 , wherein the machine learning model is trained based on the uniform resource locator and an indication of whether a cold start state associated with the uniform resource locator ended prior to the uniform resource locator receiving a threshold quantity of views.
9 . The computer-implemented method of claim 1 , wherein the uniform resource locator references at least one of: a page, a profile, or a group provided by a system.
10 . The computer-implemented method of claim 1 , further comprising:
preventing, by the computing system, display of a resource referenced by the uniform resource locator based on the uniform resource locator being scraped.
11 . A system comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:
determining a quantity of views associated with a uniform resource locator for a first time;
determining a predicted quantity of views associated with the uniform resource locator for a second time by a machine learning model based on one or more features associated with the uniform resource locator;
determining a viewport view speed associated with the uniform resource locator based on the quantity of views associated with the uniform resource locator for the first time, the predicted quantity of views associated with the uniform resource locator for the second time, and a period of time between the first time and the second time; and
causing the uniform resource locator to be scraped based on the viewport view speed.
12 . The system of claim 11 , wherein the method further comprises:
providing a prediction of whether the uniform resource locator will achieve a threshold viewport view speed between the first time and the second time.
13 . The system of claim 11 , wherein the uniform resource locator is caused to be scraped further based on the viewport view speed satisfying a threshold viewport view speed, wherein the threshold viewport view speed is based on a period of time to make a prediction of the contents referenced by the uniform resource locator.
14 . The system of claim 11 , wherein the determining the viewport view speed comprises:
determining a slope based on a first difference between the predicted quantity of views associated with the uniform resource locator for the second time and the quantity of views associated with the uniform resource locator for the first time, and further based on the period of time.
15 . The system of claim 11 , wherein the first time is based on a first elapsed time since a provision of the uniform resource locator and the second time is based on a second elapsed time since the provision of the uniform resource locator.
16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least on processor of a computing system, cause the computing system to perform a method comprising:
determining a quantity of views associated with a uniform resource locator for a first time;
determining a predicted quantity of views associated with the uniform resource locator for a second time by a machine learning model based on one or more features associated with the uniform resource locator;
determining a viewport view speed associated with the uniform resource locator based on the quantity of views associated with the uniform resource locator for the first time, the predicted quantity of views associated with the uniform resource locator for the second time, and a period of time between the first time and the second time; and
causing the uniform resource locator to be scraped based on the viewport view speed.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein the method further comprises:
providing a prediction of whether the uniform resource locator will achieve a threshold viewport view speed between the first time and the second time.
18 . The non-transitory computer-readable storage medium of claim 16 , wherein the uniform resource locator is caused to be scraped further based on the viewport view speed satisfying a threshold viewport view speed, wherein the threshold viewport view speed is based on a period of time to make a prediction of the contents referenced by the uniform resource locator.
19 . The non-transitory computer-readable storage medium of claim 16 , wherein the determining the viewport view speed comprises:
determining a slope based on a first difference between the predicted quantity of views associated with the uniform resource locator for the second time and the quantity of views associated with the uniform resource locator for the first time, and further based on the period of time.
20 . The non-transitory computer-readable storage medium of claim 16 , wherein the first time is based on a first elapsed time since a provision of the uniform resource locator and the second time is based on a second elapsed time since the provision of the uniform resource locator.