Surgical instrument segmentation plays an important role in robotic autonomous surgical navigation systems as it can accurately locate surgical instruments and estimate their posture, which helps surgeons understand the position and orientation of the instruments. However, there are still some problems affecting segmentation accuracy, like insufficient attention to the edges and center of surgical instruments, insufficient usage of low-level feature details, etc. To address these issues, a lightweight network for surgical instrument segmentation in gastrointestinal (GI) endoscopy (GESur_Net) is proposed. The pixel data aggregation (PDA) mechanism is proposed to analyze the pixel value distribution in the feature map to obtain the importance of each feature channel. The skip connection attention (SK_A) block is proposed to enhance the attention on critical regions of the surgical instruments. The global guidance attention (GGA) block is proposed to fuse high-level semantic information with low-level detailed features, enabling the acquisition of both fine-grained resolution and global semantic information. In addition, we constructed a new dataset, the Gastrointestinal Endoscopic Instrument (GEI) dataset, hoping to provide valuable resources for future research. Extensive experiments conducted on our presented GEI dataset and the Kvasir-instrument dataset demonstrate that the proposed GESur_Net increases the segmentation accuracy and outperforms state-of-the-art segmentation models.