【发布时间】:2020-12-18 11:16:29
【问题描述】:
我正在尝试制作一个烧瓶 Web 应用程序,它可以下载整个网页并在 localhost 上呈现它以裁剪元素。请求模块从站点获取所有数据,除了它所说的一些数据
来源“http://127.0.0.1:5000”已被 CORS 策略阻止:请求的资源上不存在“Access-Control-Allow-Origin”标头。
以下是我为烧瓶应用程序编写的代码。我也尝试过flask_cros,但似乎没有帮助。
from flask_socketio import SocketIO, emit
from flask_session import Session
import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse
from flask_cors import CORS,cross_origin
app= Flask(__name__)
app.config["SECRET_KEY"] = os.getenv("SECRET_KEY")
app.config["CORS_HEADERS"]="Content-Type"
socketio=SocketIO(app)
session=Session(app)
cors = CORS(app)
dir= os.path.abspath(os.getcwd())
@app.route("/")
def index():
return render_template("index.html")
@app.route("/crop",methods=["POST"])
@cross_origin()
def crop():
if request.method=="POST":
outfile=open("result.txt","w")
outfile.write("<iframe>")
outfile.close()
dummy= open("templates/down.html",'w')
dummy.close()
global link
link = str(request.form.get("url"))
r= requests.get(link,allow_redirects=True,headers={"User-Agent":"Chrome/42.0.2311.135"})
if r.status_code==405:
return render_template("exception.html")
soup = BeautifulSoup(r.content,"html.parser")
outfile=open("links.html","w")
for a in soup.findAll("link",attrs={'href':True},rel="stylesheet"):
if a['href'][0:4]!="http":
dom= urlparse(link)
wurl=dom.scheme+"://"+dom.netloc
r1=requests.get(wurl+a['href'],headers={"User-Agent":"Chrome/42.0.2311.135"})
if r1.status_code==200:
a['href']= wurl + a['href']
print(a)
outfile.write(str(a))
else:
a['href']= link + a['href']
outfile.write(str(a))
else:
outfile.write(str(a))
outfile.close()
body= soup.prettify("utf-8")
with open("templates/down.html",'wb') as file:
file.write(body)
return render_template("base.html") ```
【问题讨论】:
标签: python flask web-scraping cors