Selenium-Script / app.py
Container's picture
Update app.py
247ee08 verified
raw
history blame
1.91 kB
from seleniumwire import webdriver
from selenium.webdriver.chrome.options import Options
from fastapi import FastAPI, Request
import uvicorn
import time
import json
from urllib.parse import unquote
app = FastAPI()
@app.get("/")
def main():
return {"code": 200,"msg":"Success"}
@app.get("/chrome")
def chrome(url:str=None,wait:int=5,header:str=None,cookie:str=None):
# 必须有目标url
if type(url) == str:
target_url = unquote(url)
else:
return {"code": 500,"msg":"No target URL"}
# 等待时间必须在 0 到 30 之间
if wait_time in range(0, 31):
wait_time = wait
else:
return {"code": 500,"msg":"The waiting time must be between 0 and 30"}
header_array = {}
# header可以覆写,但必须传入json
try:
if type(header) == str:
header_array.update(json.loads(unquote(header)))
except Exception as e:
return {"code": 500,"msg":"The header field is not JSON"}
# 如果输入了cookie
if type(cookie) == str:
header_array.update({"cookie":unquote(cookie)})
options = Options()
options.add_argument('--headless')
driver = webdriver.Chrome(options=options)
driver.header_overrides = header_array
driver.get(target_url)
print(driver.page_source)
time.sleep(wait_time)
# 获取当前URL
current_url = driver.current_url
# 获取页面源代码
page_source = driver.page_source
# 获取cookie
cookies = driver.get_cookies()
# 是否有跳转过
is_jump = (target_url != current_url)
data = {
"url": current_url,
"page_source": page_source,
"cookies": cookies,
"is_jump": is_jump
}
driver.quit()
return {"code": 200,"data":data}
if __name__ == '__main__':
uvicorn.run(app='app:app', host="0.0.0.0", port=7860)