安装环境:
pip install requests pip install lxml pip install fire
使用命令:
python fofa.py -s="爬取的txt" -o="结果输出文件" -c="你的cookie"
注意:-o输入文件名即可,程序自动加入.txt后缀
FOFA网页爬取源代码:
import requests,time,base64,fire
from lxml import etree
def fofasc(s,o,c):
try:
qbase64 = (base64.b64encode(s.encode(‘utf-8‘))).decode(‘utf-8‘)
cookies = {
"_fofapro_ars_session": c
}
headers = {
‘User-Agent‘: ‘Mozilla/5.0 (Linux; Android 7.1.2; PCRT00 Build/N2G48H; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/66.0.3359.158 Safari/537.36 fanwe_app_sdk sdk_type/android sdk_version_name/4.0.1 sdk_version/2020042901 screen_width/720 screen_height/1280‘,
}
for i in range(1,1000):
url = "https://www.fofa.so/result?qbase64="+qbase64+"&full=true&page="+str(i)+‘&per_page=20‘
r = requests.get(url, headers=headers, cookies=cookies)
soup = etree.HTML(r.text)
result = soup.xpath(‘//*[@id="ajax_content"]/div/div[1]/div[1]/a[@target="_blank"]/@href‘)
if result != []:
for rs in result:
print(rs)
with open(o,mode="a+") as f:
f.write(rs+"\n")
else:
print("已经获取不到任何数据,爬取完毕!")
break
print("爬取完成:第%s页"%i)
time.sleep(5)
except KeyboardInterrupt:
print(‘用户退出‘)
def batch(s,c,o):
with open(s,"r+",encoding="utf-8") as f:
name = 1
for i in f:
i = i.strip("\n")
fofasc(s=i, o=(o+str(name) + ".txt"), c=c)
name += 1
if __name__ == ‘__main__‘:
fire.Fire(batch)