https://morph3.blog/crawpy/example.html
https://morph3.blog/crawpy/example.txt

git clone https://github.com/morph3/crawpy
pip3 install -r requirements.txt 
or
python3 -m pip install -r requirements.txt

morph3 ➜ crawpy/ [main✗] λ python3 crawpy.py --help
usage: crawpy.py [-h] [-u URL] [-w WORDLIST] [-t THREADS] [-rc RECURSIVE_CODES] [-rp RECURSIVE_PATHS] [-rd RECURSIVE_DEPTH] [-e EXTENSIONS] [-to TIMEOUT] [-follow] [-ac] [-fc FILTER_CODE] [-fs FILTER_SIZE] [-fw FILTER_WORD] [-fl FILTER_LINE] [-k] [-m MAX_RETRY]
                 [-H HEADERS] [-o OUTPUT_FILE] [-gr] [-l URL_LIST] [-lt LIST_THREADS] [-s] [-X HTTP_METHOD] [-p PROXY_SERVER]

optional arguments:
  -h, --help            显示此帮助信息并退出
  -u URL, --url URL     URL
  -w WORDLIST, --wordlist WORDLIST
                        单词列表
  -t THREADS, --threads THREADS
                        信号量池的大小
  -rc RECURSIVE_CODES, --recursive-codes RECURSIVE_CODES
                        递归扫描的状态码，例如：301,302,307
  -rp RECURSIVE_PATHS, --recursive-paths RECURSIVE_PATHS
                        递归扫描的路径，请注意只有给定的递归路径会被初始扫描，例如：admin,support,js,backup
  -rd RECURSIVE_DEPTH, --recursive-depth RECURSIVE_DEPTH
                        递归扫描深度，例如：2
  -e EXTENSIONS, --extension EXTENSIONS
                        在末尾添加扩展名。用逗号分隔，例如：-x .php,.html,.txt
  -to TIMEOUT, --timeout TIMEOUT
                        超时，建议不要使用此选项，因为它现在会产生许多我未能解决的错误
  -follow, --follow-redirects
                        跟随重定向
  -ac, --auto-calibrate
                        自动校准过滤参数
  -fc FILTER_CODE, --filter-code FILTER_CODE
                        过滤状态码
  -fs FILTER_SIZE, --filter-size FILTER_SIZE
                        过滤大小
  -fw FILTER_WORD, --filter-word FILTER_WORD
                        过滤单词数
  -fl FILTER_LINE, --filter-line FILTER_LINE
                        过滤行数
  -k, --ignore-ssl      忽略不受信任的SSL证书
  -m MAX_RETRY, --max-retry MAX_RETRY
                        最大重试次数
  -H HEADERS, --headers HEADERS
                        请求头，可以多次设置该标志。例如：-H "X-Forwarded-For: 127.0.0.1", -H "Host: foobar"
  -o OUTPUT_FILE, --output OUTPUT_FILE
                        输出文件夹
  -gr, --generate-report
                        是否让crawpy生成报告，默认路径是crawpy/reports/<url>.txt
  -l URL_LIST, --list URL_LIST
                        输入一个URL列表作为输入，并通过多进程运行crawpy -l ./urls.txt
  -lt LIST_THREADS, --list-threads LIST_THREADS
                        当使用URL列表运行时，并行运行crawpy的线程数
  -s, --silent          让crawpy不产生输出
  -X HTTP_METHOD, --http-method HTTP_METHOD
                        HTTP请求方法
  -p PROXY_SERVER, --proxy PROXY_SERVER
                        代理服务器，例如：'http://127.0.0.1:8080'

python3 crawpy.py -u https://facebook.com/FUZZ -w ./common.txt  -k -ac  -e .php,.html
python3 crawpy.py -u https://google.com/FUZZ -w ./common.txt -k -fw 9,83 -rc 301,302 -rd 2 -ac
python3 crawpy.py -u https://morph3sec.com/FUZZ -w ./common.txt -e .php,.html -t 20 -ac -k
python3 crawpy.py -u https://google.com/FUZZ -w ./common.txt  -ac -gr
python3 crawpy.py -u https://google.com/FUZZ -w ./common.txt  -ac -gr -o /tmp/test.txt
sudo python3 crawpy.py -l urls.txt -lt 20 -gr -w ./common.txt -t 20 -o custom_reports -k -ac -s
python3 crawpy.py -u https://google.com/FUZZ -w ./common.txt -ac -gr -rd 1 -rc 302,301 -rp admin,backup,support -k