This paper addresses the challenge of automating data-driven condition assessments for concrete bridges, hindered by limited data availability. The developed method consists of (1) data integration and standardization, and (2) condition assessment modules. The first module captures, structures, and integrates bridge data from diverse sources, including inspection reports, using web scraping and rule-based data extraction. It standardizes inspection data through text mining and natural language processing. The second module employs Bayesian belief networks to assess bridge deck conditions, leveraging standardized data. The method was validated on a set of bridges in Québec, Canada, resulting in a structured, integrated data repository with standardized data from 2255 inspection reports. This repository supports the development of advanced asset management tools for this class of bridges. The method achieved 94.6% accuracy, 95.0% precision, 94.7% recall, and 94.1% F1 score, demonstrating its potential to help transportation agencies improve bridge data and asset management efficiency.