Protest survey is a standard tool for scholars to understand protests. However, although protest survey methods are well established, the occurrence of spontaneous and leaderless protests has created new challenges for researchers. Not only do their unpredictable occurrences hinder planning, their fluidity also creates problems in obtaining representative samples. This article addresses these challenges based on our research during Hong Kong’s Anti-Extradition Law Amendment Bill Movement. We propose a mixed-mode sampling method combining face-to-face survey and smartphone-based online survey (onsite and post hoc), which can maximize sample sizes while ensuring representativeness in a cost-effective manner. Test results indicate that key variables from the survey modes are not statistically different in a consistent manner, except for age. Our findings show mixed-mode sampling can better capture protesters’ characteristics in contemporary protests and is replicable in other contexts.