Webpage data processing method and device, computer equipment and storage medium
阅读说明：本技术 网页数据处理方法、装置、计算机设备和存储介质 (Webpage data processing method and device, computer equipment and storage medium ) 是由 梅锦振华 于 2019-09-09 设计创作，主要内容包括：本申请涉及一种网页数据处理方法、装置、计算机设备和存储介质。所述方法包括：获取网页行为数据,根据预设规则检测网页行为数据中是否存在异常行为数据；当网页行为数据中存在异常行为数据时,获取异常行为数据对应的网页访问数据；根据网页访问数据提取访问特征,将访问特征输入到已训练的爬虫识别模型中,得到爬虫识别结果；当爬虫识别结果是网页访问数据为爬虫访问数据时,得到网页访问数据中的爬虫标识,根据爬虫标识从网页行为数据中得到对应的爬虫网页行为数据；根据爬虫网页行为数据和网页行为数据得到目标网页行为数据。采用本方法能够提高得到目标网页行为数据的准确性。(The application relates to a webpage data processing method, a webpage data processing device, a computer device and a storage medium. The method comprises the following steps: acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule; when abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data; extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result; when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification; and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data. By adopting the method, the accuracy of obtaining the target webpage behavior data can be improved.)
1. A method of web page data processing, the method comprising:
acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule;
when the abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data;
extracting access characteristics according to the webpage access data, and inputting the access characteristics into a trained crawler recognition model to obtain a crawler recognition result;
when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification;
and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
2. The method according to claim 1, wherein the acquiring the webpage behavior data and detecting whether abnormal behavior data exists in the webpage behavior data according to a preset rule comprises:
acquiring first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and acquiring incremental behavior data according to the first webpage behavior data and the second webpage behavior data;
and when the incremental behavior data exceeds preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
3. The method according to claim 1, wherein the acquiring the webpage behavior data and detecting whether abnormal behavior data exists in the webpage behavior data according to a preset rule comprises:
acquiring webpage behavior data of each historical time period, and calculating to obtain a historical data growth rate according to the webpage behavior data of each historical time period;
acquiring webpage behavior data of a target time period, calculating to obtain a target data growth rate according to the webpage behavior data of the target time period, and comparing the target data growth rate with the historical data growth rate;
and when the target data growth rate exceeds the historical data growth rate, the webpage behavior data of the target time period are abnormal behavior data.
4. The method of claim 1, after obtaining target web page behavior data from the crawler web page behavior data and the web page behavior data, further comprising:
storing the crawler identification and webpage access data corresponding to the crawler identification into a preset blacklist database in an associated manner;
when the web page behavior data has abnormal behavior data, after acquiring the web page access data corresponding to the abnormal behavior data, the method further includes:
obtaining an access identifier in the webpage access data, and searching the access identifier in the preset blacklist database;
and when the access identifier exists in the preset blacklist database, obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the access identifier.
5. The method of claim 1, wherein the step of generating the trained crawler recognition model comprises:
acquiring historical crawler access data and historical target access data, extracting historical crawler access characteristics and historical crawler tags according to the historical crawler access data, and extracting the historical target access characteristics and the historical target tags according to the historical target access data;
and taking the historical crawler access characteristics and the historical target access characteristics as the input of a recurrent neural network, taking the historical crawler labels and the historical target labels as the labels of the recurrent neural network for training, and obtaining the trained crawler recognition model when preset conditions are met.
6. The method of claim 1, after obtaining target web page behavior data from the crawler web page behavior data and the web page behavior data, further comprising:
obtaining a crawler click behavior coordinate point and a target click behavior coordinate point according to the crawler webpage behavior data and the target webpage behavior data;
and generating a webpage click behavior display graph according to the crawler click behavior coordinate points and the target click behavior coordinate points, and sending the webpage behavior display graph to a management terminal for display.
7. A web page data processing apparatus, characterized in that the apparatus comprises:
the detection module is used for acquiring webpage behavior data and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule;
the access data acquisition module is used for acquiring webpage access data corresponding to the abnormal behavior data when the abnormal behavior data exists in the webpage behavior data;
the identification module is used for extracting access characteristics according to the webpage access data and inputting the access characteristics into a trained crawler identification model to obtain a crawler identification result;
a behavior data obtaining module, configured to obtain a crawler identifier in the web page access data when the crawler identification result indicates that the web page access data is crawler access data, and obtain corresponding crawler web page behavior data from the web page behavior data according to the crawler identifier;
and the target data obtaining module is used for obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
8. The apparatus according to claim 7, wherein the detection module is further configured to obtain first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and obtain incremental behavior data according to the first webpage behavior data and the second webpage behavior data; and when the incremental behavior data exceeds preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Technical Field
The present application relates to the field of internet technologies, and in particular, to a method and an apparatus for processing web page data, a computer device, and a storage medium.
Background
With the development of the internet technology, better internet service is provided for users by mining behavior data of the users in the web pages in the process of browsing the web pages by the users through the internet. However, with the development of crawler technology, web crawlers are increasingly inundated, and when the web crawlers are crawling internet data, user behaviors are simulated, for example, a user is simulated to log in, and data is crawled after the log-in. Thereby leading to inaccurate mined webpage behavior data.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, and a storage medium for processing webpage data, which can improve the accuracy of obtaining webpage behavior data.
A method of web page data processing, the method comprising:
acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule;
when abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data;
extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result;
when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification;
and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
In one embodiment, acquiring webpage behavior data, and detecting whether abnormal behavior data exists in the webpage behavior data according to a preset rule includes:
acquiring first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and acquiring incremental behavior data according to the first webpage behavior data and the second webpage behavior data;
and when the incremental behavior data exceeds the preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
In one embodiment, acquiring webpage behavior data, and detecting whether abnormal behavior data exists in the webpage behavior data according to a preset rule includes:
acquiring webpage behavior data of each historical time period, and calculating to obtain a historical data growth rate according to the webpage behavior data of each historical time period;
acquiring webpage behavior data of a target time period, calculating to obtain a target data growth rate according to the webpage behavior data of the target time period, and comparing the target data growth rate with the historical data growth rate;
and when the target data growth rate exceeds the historical data growth rate, the webpage behavior data of the target time period is abnormal behavior data.
In one embodiment, after obtaining the target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data, the method further includes:
storing the crawler identification and webpage access data corresponding to the crawler identification in a preset blacklist database in an associated manner;
when the web page behavior data has abnormal behavior data, after acquiring the web page access data corresponding to the abnormal behavior data, the method further includes:
acquiring an access identifier in the webpage access data, and searching the access identifier in a preset blacklist database;
and when the access identifier exists in the preset blacklist database, obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the access identifier.
In one embodiment, the step of generating the trained crawler recognition model comprises:
acquiring historical crawler access data and historical target access data, extracting historical crawler access characteristics and historical crawler tags according to the historical crawler access data, and extracting the historical target access characteristics and the historical target tags according to the historical target access data;
and taking the historical crawler access characteristics and the historical target access characteristics as the input of a recurrent neural network, taking the historical crawler labels and the historical target labels as the labels of the recurrent neural network for training, and obtaining a trained crawler recognition model when preset conditions are met.
In one embodiment, after obtaining the target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data, the method further includes:
obtaining a crawler click behavior coordinate point and a target click behavior coordinate point according to the crawler webpage behavior data and the target webpage behavior data;
and generating a webpage click behavior display graph according to the crawler click behavior coordinate points and the target click behavior coordinate points, and sending the webpage behavior display graph to the management terminal for display.
A web page data processing apparatus, the apparatus comprising:
the detection module is used for acquiring the webpage behavior data and detecting whether the webpage behavior data have abnormal behavior data according to a preset rule;
the access data acquisition module is used for acquiring webpage access data corresponding to the abnormal behavior data when the abnormal behavior data exists in the webpage behavior data;
the identification module is used for extracting access characteristics according to the webpage access data and inputting the access characteristics into the trained crawler identification model to obtain a crawler identification result;
the behavior data obtaining module is used for obtaining a crawler identifier in the webpage access data when the crawler identification result indicates that the webpage access data are crawler access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identifier;
and the target data obtaining module is used for obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
In one embodiment, the detection module is further configured to obtain first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and obtain incremental behavior data according to the first webpage behavior data and the second webpage behavior data; and when the incremental behavior data exceeds the preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule;
when abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data;
extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result;
when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification;
and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule;
when abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data;
extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result;
when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification;
and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
According to the webpage data processing method, the device, the computer equipment and the storage medium, whether abnormal behavior data exist in the webpage behavior data is detected through the preset rule, when the abnormal behavior data exist, the crawler webpage behavior data in the abnormal behavior data are identified through the crawler identification model, the crawler webpage behavior data can be accurately obtained, then the target webpage behavior data are obtained according to the crawler webpage behavior data, and the accuracy of the obtained target webpage behavior data is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary scenario for implementing a method for processing web page data;
FIG. 2 is a flowchart illustrating a method for processing web page data according to an embodiment;
FIG. 3 is a schematic flow chart illustrating obtaining abnormal behavior data in one embodiment;
FIG. 4 is a schematic flow chart illustrating the process of obtaining abnormal behavior data according to another embodiment;
FIG. 5 is a schematic flow chart diagram illustrating obtaining crawler web page behavior data in one embodiment;
FIG. 6 is a schematic flow diagram of training a crawler recognition model in one embodiment;
FIG. 7 is a flowchart illustrating the generation of a webpage click behavior presentation diagram in one embodiment;
FIG. 8 is a block diagram showing the structure of a web page data processing apparatus according to an embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The webpage data processing method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the
In one embodiment, as shown in fig. 2, a method for processing web page data is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
s202, acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule.
The web page behavior data refers to statistical data of web page behaviors generated after the web page is accessed, for example, PV (page view, page click rate) of the web page, page retention time, and the like, and the web page behavior data includes not only behavior data of a user but also behavior data of a crawler.
Specifically, the server acquires the webpage behavior data from the webpage terminal, and detects whether abnormal behavior data exists in the webpage behavior data according to a preset rule in the server.
And S204, when the abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data.
The abnormal behavior data refers to data different from the normal behavior data, for example, the web page click behavior data increases more than the normal growth speed in a period of time, and the like. The web page access data refers to access log information generated when a web page is accessed. Such as access identification, access time, page response time, etc.
Specifically, when the webpage behavior data has abnormal behavior data, the server acquires webpage access data corresponding to the abnormal behavior data. For example, the web page access data may be obtained from an access log stored in the server, or a monitoring script may be set in the front-end web page, where the monitoring script is used to obtain an access identifier, access time, and corresponding time of the page of the front-end visitor and send the access identifier, access time, and corresponding time of the page to the server to be stored as the access log.
And S206, extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result.
The access feature is used to identify whether the accessed webpage is a crawler or a user, and may include an access identification feature, an access time feature, a page dwell time feature, and the like. The crawler identification result refers to an identification result of the access characteristic, and can be a webpage accessed by the crawler or a webpage accessed by the user.
Specifically, the server extracts access features according to the webpage access data, digitalizes the access features to obtain access feature vectors, and inputs the access feature vectors into a trained crawler recognition model for recognition to obtain a crawler recognition result. For example, the access identifier feature is 1, the access time feature is within 1 hour, the access times feature is 15 times, and the page dwell time feature is 30s, so that an access feature vector is (1,1,15, 30).
And S208, when the webpage access data are the crawler access data as a crawler identification result, obtaining a crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification.
Wherein, the crawler identification is used for uniquely identifying the crawler. The name of the crawler may be used, and the IP (Internet Protocol Address) Address of the crawler may be used.
Specifically, when the crawler identification result indicates that the webpage access data is the crawler access data, that is, the crawler causes the webpage to generate abnormal behavior data, which indicates that the access request of the crawler exists, at this time, the access identifier is obtained from the webpage access data, and the access identifier is used as the crawler identifier. And obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification. For example, the click rate of the crawler can be obtained from the webpage click behavior data according to the crawler identification. And when the crawler identification result indicates that the webpage access data are normal access data, the access request of the crawler does not exist in the access request, and the processing is not carried out.
And S210, obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
The target webpage behavior data refers to behavior data of an accessed webpage after behavior data generated when a crawler accesses the webpage are removed.
Specifically, the server calculates target webpage behavior data according to the obtained crawler webpage behavior data and all webpage behavior data. For example, the web page click rate of the user is obtained according to the crawler click rate and all the web page click behavior data.
In the embodiment, whether the abnormal behavior data exist in the webpage behavior data is detected through the preset rule, when the abnormal behavior data exist, the crawler webpage behavior data in the abnormal behavior data are identified through the crawler identification model, the crawler webpage behavior data can be accurately obtained, then the target webpage behavior data are obtained according to the crawler webpage behavior data, and the accuracy of the obtained target webpage behavior data is improved.
In one embodiment, as shown in fig. 3, the step S202 of acquiring the webpage behavior data and detecting whether there is abnormal behavior data in the webpage behavior data according to the preset rule includes the steps of:
s202, acquiring first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and acquiring incremental behavior data according to the first webpage behavior data and the second webpage behavior data.
The time period is a preset time interval, and the first time period and the second time period are two continuous time periods. For example, each day may be divided into 12 time periods, one hour is a time period, the first webpage behavior data refers to the webpage behavior data obtained in the first time period, and the second webpage behavior data refers to the webpage behavior data obtained in the second time period. For example, the webpage behavior data of the time interval from 12 to 13 is acquired as the first webpage behavior data, and the webpage behavior data of the time interval from 13 to 14 is acquired as the second webpage behavior data. Incremental behavior data refers to added web page behavior data. For example, the number of user clicks from 12 to 13 is 100, the number of user clicks from 13 to 14 is 120, and the incremental clicks obtained in this case are 20.
Specifically, the server obtains first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and obtains incremental behavior data according to the first webpage behavior data and the second webpage behavior data.
And S204, when the incremental behavior data exceeds the preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
The preset incremental behavior data refers to behavior data which is preset to be increased when the normal state is achieved, and may be a value or an interval. For example, the set incremental clicks may be 10 times, or 10 to 15 times.
Specifically, the server compares the obtained incremental behavior data with preset incremental behavior data, and when the incremental behavior data exceeds the preset incremental behavior data, obtains second webpage behavior data corresponding to a second time period as abnormal behavior data. Namely, the second webpage behavior data generated in the second time period comprises webpage behavior data generated by the crawler. And when the incremental behavior data does not exceed the preset incremental behavior data, indicating that the corresponding second webpage behavior data in the second time period is normal behavior data. I.e., web page behavior data generated when a user accesses a web page.
In the embodiment, by acquiring the first webpage behavior data corresponding to the first time period and the second webpage behavior data corresponding to the second time period, the incremental behavior data is obtained according to the first webpage behavior data and the second webpage behavior data, and whether abnormal behavior data exists or not is judged according to the obtained incremental behavior data, so that the accuracy of obtaining the abnormal behavior data is improved.
In one embodiment, as shown in fig. 4, the step S202 of acquiring the webpage behavior data and detecting whether there is abnormal behavior data in the webpage behavior data according to the preset rule includes the steps of:
s402, acquiring the webpage behavior data of each historical time period, and calculating the historical data growth rate according to the webpage behavior data of each historical time period.
The historical time period refers to a time period of a date before the current date. Such as yesterday's period, the previous day's period, i.e. the period corresponding to the date before today. The historical data growth rate refers to the growth rate of the webpage behavior data in the historical time period.
Specifically, the server acquires the webpage behavior data of each historical time period, and calculates the historical data growth rate according to the webpage behavior data of each historical time period. For example, today is 10 months and 1 day, each historical time period may be a time period obtained by dividing each day of 9 months, that is, there may be 24 time periods each day. And acquiring webpage click behavior data of each time period in 9 months, and calculating the growth rate of historical click data according to the webpage click behavior data of each time period in 9 months.
S404, acquiring webpage behavior data of a target time period, calculating to obtain a target data growth rate according to the webpage behavior data of the target time period, and comparing the target data growth rate with the historical data growth rate.
The target time period refers to a time period obtained by dividing according to the current time, for example, the current time point is 10 months, 1 day and 12 points, the target time period may be a time period obtained by dividing 10 months, 1 day and 0 point to 12 points, and 1 hour may be divided as 1 target time period to obtain 12 target time periods. The target data growth rate is the growth rate of the web page behavior data at the current time.
Specifically, the server acquires webpage behavior data in each target time period, calculates a target data growth rate according to the webpage behavior data in each target time period, and compares the target data growth rate with the historical data growth rate.
S406, when the target data growth rate exceeds the historical data growth rate, the webpage behavior data in the target time period is abnormal behavior data.
Specifically, when the target data growth rate exceeds the historical data growth rate, the server takes the webpage behavior data in the target time period as abnormal behavior data. And when the target data growth rate does not exceed the historical data growth rate, the server takes the webpage behavior data in the target time period as normal behavior data. In one embodiment, when the target data growth rate is within the growth rate range obtained from the historical data growth rate, the server takes the webpage behavior data in the target time period as normal behavior data, and when the target data growth rate is outside the growth rate range obtained from the historical data growth rate, the server takes the webpage behavior data in the target time period as abnormal behavior data.
In the embodiment, the historical data growth rate is obtained by calculation according to the historical webpage behavior data, the historical data growth rate is compared with the current webpage behavior data growth rate, and the abnormal behavior data is obtained according to the comparison result. Namely, the abnormal behavior data is judged according to the increment rate of the historical data, and the accuracy of obtaining the abnormal behavior data is improved.
In one embodiment, after step S210, that is, after obtaining the target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data, the method further includes the steps of:
and storing the crawler identification and the webpage access data corresponding to the crawler identification in a preset blacklist database in an associated manner.
The preset blacklist database is used for storing relevant information of the crawler, including crawler identification, crawler behavior data, crawler access data and the like.
Specifically, the server stores the crawler identification and the webpage access data corresponding to the crawler identification in a preset blacklist database in an associated manner, so that subsequent management and viewing are facilitated. Meanwhile, target webpage behavior data can also be stored in the database, so that subsequent management is facilitated.
As shown in fig. 5, after step S204, that is, after acquiring the web page access data corresponding to the abnormal behavior data when the abnormal behavior data exists in the web page behavior data, the method further includes the steps of:
s502, obtaining the access identifier in the webpage access data, and searching the access identifier in a preset blacklist database.
Specifically, the server obtains an access identifier in the webpage access data, and searches the access identifier in a preset blacklist database.
S504, when the access identifier exists in the preset blacklist database, the corresponding crawler webpage behavior data is obtained from the webpage behavior data according to the access identifier.
Specifically, when the access identifier exists in the preset blacklist database, the access identifier can be found in the preset blacklist database, which indicates that the access identifier is an access identifier of a crawler. At the moment, the webpage behavior data corresponding to the access identifier is searched from the webpage behavior data according to the access identifier, and the webpage behavior data of the crawler are obtained. And then, acquiring the real webpage behavior data according to the webpage behavior data and the webpage behavior data of the crawler.
In the above embodiment, that is, when the corresponding access identifier is found in the preset blacklist database, the corresponding crawler webpage behavior data is obtained from the webpage behavior data according to the access identifier, so that the efficiency of obtaining the crawler webpage behavior data can be submitted, and the efficiency of obtaining the target webpage behavior data is improved.
In one embodiment, as shown in FIG. 6, the step of generating the trained crawler recognition model comprises the steps of:
s602, obtaining historical crawler access data and historical target access data, extracting historical crawler access characteristics and historical crawler tags according to the historical crawler access data, and extracting the historical target access characteristics and the historical target tags according to the historical target access data.
The historical crawler access data refers to access data recorded when the historical crawler accesses a webpage. The historical target access data refers to access data recorded when the webpage is oriented by a historical normal user. The historical crawler tag is a tag obtained according to crawler azimuth data, and the historical target tag is a target tag obtained according to historical target access data.
Specifically, the server acquires historical crawler access data and historical target access data, extracts historical crawler access features and historical crawler tags according to the historical crawler access data, and extracts the historical target access features and the historical target tags according to the historical target access data.
S604, taking the historical crawler access characteristics and the historical target access characteristics as the input of the recurrent neural network, taking the historical crawler labels and the historical target labels as the labels of the recurrent neural network for training, and obtaining a trained crawler recognition model when preset conditions are met.
The recurrent neural network is a recurrent neural network in which sequence data is input, recursion (recursion) is performed in the evolution direction of the sequence, and all nodes (recurrent units) are connected in a chain manner. For example, it may be an LSTM (Long Short-Term Memory) neural network. LSTM is a long-short term memory network, a time-cycled neural network. The preset condition is a preset condition for finishing training, and may be that the training reaches a preset iteration number or a calculation error reaches a preset threshold. In training, the activation function used is an S-type activation function, and the error is calculated by a cross entropy function.
Specifically, the service takes the historical crawler access characteristics and the historical target access characteristics as the input of the recurrent neural network, trains the historical crawler labels and the historical target labels as the labels of the recurrent neural network, and finishes training when the training reaches the preset iteration times or the calculation error reaches the preset threshold value, so as to obtain the trained crawler recognition model.
In the embodiment, the crawler recognition model is obtained by training the historical crawler access data and the historical target access data by using a recurrent neural network algorithm, then the trained crawler recognition model is deployed into the server, and the server can directly use the crawler recognition model, so that the crawler recognition efficiency is improved.
In one embodiment, as shown in fig. 7, after step S210, that is, after obtaining the target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data, the method further includes:
s702, obtaining a crawler click behavior coordinate point and a target click behavior coordinate point according to the crawler webpage behavior data and the target webpage behavior data.
The crawler clicking behavior coordinate point is a coordinate of a clicking position in a webpage when the crawler clicks the webpage, and the target clicking behavior coordinate point is a coordinate of the clicking position in the webpage when a user clicks the webpage.
Specifically, each crawler click behavior coordinate point is obtained according to the crawler webpage behavior data, and each target click behavior coordinate point is obtained according to the target webpage behavior data. For example, each time a user clicks a web page, the click position in the web page is recorded, and a coordinate point corresponding to each click is obtained.
S704, generating a webpage click behavior display graph according to the crawler click behavior coordinate points and the target click behavior coordinate points, and sending the webpage behavior display graph to a management terminal for display.
The webpage click behavior display graph is used for visually displaying the crawler click behavior coordinate points and the target click behavior coordinate points. For example, a simulated webpage may be generated, and the positions of coordinate points are marked in the simulated webpage by using marks of different colors, so as to obtain a click behavior display diagram.
Specifically, the server generates a webpage click behavior display graph according to the crawler click behavior coordinate point and the target click behavior coordinate point, and sends the webpage behavior display graph to the management terminal for display, so that the management terminal can conveniently check and analyze the webpage behavior display graph.
It should be understood that although the various steps in the flow charts of fig. 2-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-7 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, there is provided a web page data processing apparatus 800 including: a detection module 802, an access data obtaining module 804, a recognition module 806, a behavior data obtaining module 808, and a target data obtaining module 810, wherein:
the detection module 802 is configured to obtain webpage behavior data, and detect whether abnormal behavior data exists in the webpage behavior data according to a preset rule;
the access data acquisition module 804 is configured to acquire, when abnormal behavior data exists in the webpage behavior data, webpage access data corresponding to the abnormal behavior data;
the identification module 806 is configured to extract access characteristics according to the web page access data, and input the access characteristics into the trained crawler identification model to obtain a crawler identification result;
a behavior data obtaining module 808, configured to obtain a crawler identifier in the web access data when the crawler identification result indicates that the web access data is the crawler access data, and obtain corresponding crawler web behavior data from the web behavior data according to the crawler identifier;
and a target data obtaining module 810, configured to obtain target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
In one embodiment, the detection module 802 is further configured to obtain first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and obtain incremental behavior data according to the first webpage behavior data and the second webpage behavior data; and when the incremental behavior data exceeds the preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
In one embodiment, the detection module 802 is further configured to obtain webpage behavior data of each historical time period, and calculate a historical data growth rate according to the webpage behavior data of each historical time period; acquiring webpage behavior data of a target time period, calculating to obtain a target data growth rate according to the webpage behavior data of the target time period, and comparing the target data growth rate with the historical data growth rate; and when the target data growth rate exceeds the historical data growth rate, the webpage behavior data of the target time period is abnormal behavior data.
In one embodiment, the web page data processing apparatus 800 further includes:
the storage module is used for storing the crawler identification and the webpage access data corresponding to the crawler identification into a preset blacklist database in an associated manner;
the web page data processing apparatus 800 further includes:
the searching module is used for acquiring the access identifier in the webpage access data and searching the access identifier in a preset blacklist database; and when the access identifier exists in the preset blacklist database, obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the access identifier.
In one embodiment, the web page data processing apparatus 800 further includes:
the extraction module is used for acquiring historical crawler access data and historical target access data, extracting historical crawler access characteristics and historical crawler tags according to the historical crawler access data, and extracting the historical target access characteristics and the historical target tags according to the historical target access data;
and the training module is used for taking the historical crawler access characteristics and the historical target access characteristics as the input of the recurrent neural network, taking the historical crawler labels and the historical target labels as the labels of the recurrent neural network for training, and obtaining a trained crawler recognition model when preset conditions are met.
In one embodiment, the web page data processing apparatus 800 further includes:
the display module is used for obtaining a crawler click behavior coordinate point and a target click behavior coordinate point according to the crawler webpage behavior data and the target webpage behavior data; and generating a webpage click behavior display graph according to the crawler click behavior coordinate points and the target click behavior coordinate points, and sending the webpage behavior display graph to the management terminal for display.
For specific limitations of the web page data processing apparatus, reference may be made to the above limitations of the web page data processing method, which are not described herein again. The modules in the web page data processing device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing webpage behavior data and webpage access data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a web page data processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, there is provided a computer device comprising a memory storing a computer program and a processor implementing the following steps when the processor executes the computer program: acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule; when abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data; extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result; when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification; and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and acquiring incremental behavior data according to the first webpage behavior data and the second webpage behavior data; and when the incremental behavior data exceeds the preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring webpage behavior data of each historical time period, and calculating to obtain a historical data growth rate according to the webpage behavior data of each historical time period; acquiring webpage behavior data of a target time period, calculating to obtain a target data growth rate according to the webpage behavior data of the target time period, and comparing the target data growth rate with the historical data growth rate; and when the target data growth rate exceeds the historical data growth rate, the webpage behavior data of the target time period is abnormal behavior data.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and storing the crawler identification and the webpage access data corresponding to the crawler identification in a preset blacklist database in an associated manner. The processor when executing the computer program further realizes the following steps: acquiring an access identifier in the webpage access data, and searching the access identifier in a preset blacklist database; and when the access identifier exists in the preset blacklist database, obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the access identifier.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring historical crawler access data and historical target access data, extracting historical crawler access characteristics and historical crawler tags according to the historical crawler access data, and extracting the historical target access characteristics and the historical target tags according to the historical target access data; and taking the historical crawler access characteristics and the historical target access characteristics as the input of a recurrent neural network, taking the historical crawler labels and the historical target labels as the labels of the recurrent neural network for training, and obtaining a trained crawler recognition model when preset conditions are met.
In one embodiment, the processor, when executing the computer program, further performs the steps of: obtaining a crawler click behavior coordinate point and a target click behavior coordinate point according to the crawler webpage behavior data and the target webpage behavior data; and generating a webpage click behavior display graph according to the crawler click behavior coordinate points and the target click behavior coordinate points, and sending the webpage behavior display graph to the management terminal for display.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring webpage behavior data, and detecting whether abnormal behavior data exist in the webpage behavior data according to a preset rule; when abnormal behavior data exists in the webpage behavior data, acquiring webpage access data corresponding to the abnormal behavior data; extracting access characteristics according to the webpage access data, and inputting the access characteristics into the trained crawler recognition model to obtain a crawler recognition result; when the crawler identification result is that the webpage access data are crawler access data, obtaining crawler identification in the webpage access data, and obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the crawler identification; and obtaining target webpage behavior data according to the crawler webpage behavior data and the webpage behavior data.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring first webpage behavior data corresponding to a first time period and second webpage behavior data corresponding to a second time period, and acquiring incremental behavior data according to the first webpage behavior data and the second webpage behavior data; and when the incremental behavior data exceeds the preset incremental behavior data, the second webpage behavior data corresponding to the second time period is abnormal behavior data.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring webpage behavior data of each historical time period, and calculating to obtain a historical data growth rate according to the webpage behavior data of each historical time period; acquiring webpage behavior data of a target time period, calculating to obtain a target data growth rate according to the webpage behavior data of the target time period, and comparing the target data growth rate with the historical data growth rate; and when the target data growth rate exceeds the historical data growth rate, the webpage behavior data of the target time period is abnormal behavior data.
In one embodiment, the computer program when executed by the processor further performs the steps of: and storing the crawler identification and the webpage access data corresponding to the crawler identification in a preset blacklist database in an associated manner. The computer program when executed by the processor further realizes the steps of: acquiring an access identifier in the webpage access data, and searching the access identifier in a preset blacklist database; and when the access identifier exists in the preset blacklist database, obtaining corresponding crawler webpage behavior data from the webpage behavior data according to the access identifier.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical crawler access data and historical target access data, extracting historical crawler access characteristics and historical crawler tags according to the historical crawler access data, and extracting the historical target access characteristics and the historical target tags according to the historical target access data; and taking the historical crawler access characteristics and the historical target access characteristics as the input of a recurrent neural network, taking the historical crawler labels and the historical target labels as the labels of the recurrent neural network for training, and obtaining a trained crawler recognition model when preset conditions are met.
In one embodiment, the computer program when executed by the processor further performs the steps of: obtaining a crawler click behavior coordinate point and a target click behavior coordinate point according to the crawler webpage behavior data and the target webpage behavior data; and generating a webpage click behavior display graph according to the crawler click behavior coordinate points and the target click behavior coordinate points, and sending the webpage behavior display graph to the management terminal for display.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
- 上一篇：一种医用注射器针头装配设备
- 下一篇：一种基于中间人的互联网数据采集方法及系统