1 views collected around this technical thread.
This article explains how to scrape tens of thousands of images from Sogou by analyzing the request URLs, extracting image URLs from JSON responses, and implementing a multithreaded Java downloader that stores the pictures locally.
This tutorial explains how to crawl thousands of images from Sogou using Java, detailing the request URL analysis, parameter extraction, multithreaded downloading logic, and providing complete source code for the image processor, pipeline, and HTTP utility classes.
This article explains how to programmatically fetch and save thousands of images from Sogou by analyzing the XHR request parameters, constructing the appropriate URL, extracting image URLs from the JSON response, and using a multithreaded Java downloader with custom HTTP utilities.
This article demonstrates how to build a Java-based web crawler that fetches image URLs from Sogou Image Search, parses the JSON response, and downloads thousands of pictures to a local directory using multithreaded processing and custom HTTP utilities.
This article summarizes Sogou's information‑feed recommendation system, covering the architecture from data collection and NLP processing to recall, ranking, and feedback, and detailing the classification, tagging, keyword extraction, and various recall and ranking models such as FastText, TextCNN, collaborative filtering, and wide‑and‑deep learning.
This article outlines Sogou's infrastructure evolution under rapid business iteration, detailing stages of compute and storage horizontal scaling, serviceization, and stream computing, while sharing the practices, principles, lessons learned, and reflections that guided the platform's architectural transformation.