mirror of
				https://github.com/tiyn/stud.ip-crawler.git
				synced 2025-10-31 03:01:18 +01:00 
			
		
		
		
	bugfixes: included error message for large files - skipping them
This commit is contained in:
		
							
								
								
									
										33
									
								
								Dockerfile
									
									
									
									
									
										Normal file
									
								
							
							
						
						
									
										33
									
								
								Dockerfile
									
									
									
									
									
										Normal file
									
								
							| @@ -0,0 +1,33 @@ | ||||
| FROM python | ||||
|  | ||||
| LABEL maintainer "TiynGER <mail@martenkante.eu>" | ||||
|  | ||||
| ENV USER admin | ||||
|  | ||||
| ENV PSWD admin | ||||
|  | ||||
| ENV URL admin | ||||
|  | ||||
| ENV HOST mysql | ||||
|  | ||||
| ENV INTERVAL 86400 | ||||
|  | ||||
| ENV DB_USER root | ||||
|  | ||||
| ENV DB_PSWD root | ||||
|  | ||||
| ADD src /studip | ||||
|  | ||||
| WORKDIR /studip | ||||
|  | ||||
| RUN pip install -r requirements.txt | ||||
|  | ||||
| ADD docker-entry.sh . | ||||
|  | ||||
| RUN chmod +x docker-entry.sh | ||||
|  | ||||
| VOLUME /studip/data | ||||
|  | ||||
| WORKDIR /studip | ||||
|  | ||||
| CMD ["./docker-entry.sh"] | ||||
| @@ -1,29 +1,31 @@ | ||||
| version: "3.1" | ||||
| services: | ||||
|     studip: | ||||
|         image: tiynger/studip-crawler | ||||
|         image: studip:latest | ||||
|         restart: unless-stopped | ||||
|         environment: | ||||
|             USER: 'user' | ||||
|             PSWD: 'pswd' | ||||
|             URL: 'https://url.tld' | ||||
|             INTERVAL: 86400 | ||||
|             HOST: mysql | ||||
|             HOST: 'mysql' | ||||
|             DB_USER: root | ||||
|             DB_PSWD: root | ||||
|             DB_PSWD: 'pswddb' | ||||
|         volumes: | ||||
|             - studip_data:/studip/src/data | ||||
|             - studip:/studip/data | ||||
|         depends_on: | ||||
|             - mysql | ||||
| 
 | ||||
|     mysql: | ||||
|         image: mysql | ||||
|         image: mysql:5.6 | ||||
|         restart: unless-stopped | ||||
|         environment: | ||||
|             MYSQL_ROOT_PASSWORD: root | ||||
|             MYSQL_ROOT_PASSWORD: 'pswddb' | ||||
|         volumes: | ||||
|             - studip_db:/var/lib/mysql | ||||
|             - mysql:/var/lib/mysql | ||||
| 
 | ||||
| volumes: | ||||
|     studip_data: | ||||
|     studip: | ||||
|         driver: local | ||||
|     studip_db: | ||||
|     mysql: | ||||
|         driver: local | ||||
							
								
								
									
										3
									
								
								docker-entry.sh
									
									
									
									
									
										Executable file
									
								
							
							
						
						
									
										3
									
								
								docker-entry.sh
									
									
									
									
									
										Executable file
									
								
							| @@ -0,0 +1,3 @@ | ||||
| #!/bin/bash | ||||
|  | ||||
| while true; do python /studip/run.py -o /studip/data -u $USER -p $PSWD -s $URL --db_user $DB_USER --db_passwd $DB_PSWD --host $HOST && sleep $INTERVAL; done | ||||
| @@ -1,35 +0,0 @@ | ||||
| FROM python | ||||
|  | ||||
| LABEL maintainer "TiynGER <mail@martenkante.eu>" | ||||
|  | ||||
| ENV USER admin | ||||
|  | ||||
| ENV PSWD admin | ||||
|  | ||||
| ENV URL admin | ||||
|  | ||||
| ENV HOST mysql | ||||
|  | ||||
| ENV INTERVAL 86400 | ||||
|  | ||||
| ENV DB_USER root | ||||
|  | ||||
| ENV DB_PSWD root | ||||
|  | ||||
| RUN git clone https://github.com/tiyn/stud.ip-crawler /studip | ||||
|  | ||||
| WORKDIR /studip | ||||
|  | ||||
| RUN pip install -r src/requirements.txt | ||||
|  | ||||
| ADD run.sh . | ||||
|  | ||||
| RUN chmod +x run.sh | ||||
|  | ||||
| RUN chmod +x src/run.py | ||||
|  | ||||
| VOLUME /studip/src/data | ||||
|  | ||||
| WORKDIR /studip/src | ||||
|  | ||||
| CMD ["/studip/run.sh"] | ||||
| @@ -1,3 +0,0 @@ | ||||
| #!/bin/bash | ||||
|  | ||||
| while true; do python /studip/src/run.py -o /studip/src/data -u $USER -p $PSWD -s $URL --db_user $DB_USER --db_passwd $DB_PSWD --host $HOST && sleep $INTERVAL; done | ||||
| @@ -150,7 +150,7 @@ class Studip: | ||||
|                         doc_file.write(chunk) | ||||
|                 self.db.set_last_file_dl(str(doc), str(int(time.time()))) | ||||
|             except OSError: | ||||
|                 log.critical("Error while writing to the file " + doc_name) | ||||
|                 log.warning("Error while writing to the file " + doc_name) | ||||
|  | ||||
|     def get_subdirs(self, folder): | ||||
|         """Get all the subdirectories of a given folder. | ||||
|   | ||||
		Reference in New Issue
	
	Block a user