편집 기록

중고나라에서 상품가격을 크롤링하는 코딩입니다.

import urllib.request
import urllib.parse
import re
from bs4 import BeautifulSoup
import numpy as np
import pandas as pd
import sys
from flask import Flask, render_template, request
import tablib
import os

app = Flask(__name__)
@app.route("/")
def student(plusurl=None):
  return render_template('student.html',plusurl='Name')

def func_clawler(plusurl):
  if request.method == 'POST':
  #plusurl = input("검색어를 입력하세요:")
    page=3
    pageNum=1
    lastPage=int(page)*10-9
    num=1
    list1=list()
    while pageNum < lastPage +1:

      baseurl = "https://search.naver.com/search.naver?where=article&sm=tab_jum&query="
      suburl ="%20중고나라%20판매중%20"
      addurl ="&prdtype=0&t=0&st=rel&date_option=0&date_from=&date_to=&srchby=text&dup_remove=1&cafe_url=&without_cafe_url=&board=&sm=tab_pge&start="
      url =  baseurl+urllib.parse.quote_plus(suburl)+urllib.parse.quote_plus(plusurl)+addurl+str(pageNum)
      html = urllib.request.urlopen(url).read()
      soup = BeautifulSoup(html, "html.parser")
      my_price = soup.find_all(class_="cafe_item_price")

      for title in my_price:
        numbers = re.findall("\d+",title.text.replace(',',''))
        index=[]
        new_numbers=np.delete(numbers, index)
        real_numbers=int(new_numbers)
        num +=1
        list1.append(real_numbers)
        list1.sort()

      pageNum += 10
    for i in list1:
       print(int(i),end="원 ")
    articles = pd.DataFrame(list1, columns=['가격'])
    articles.to_csv('c:\project\priceextract\priceresults.csv',encoding='cp949')

    dataset = tablib.Dataset()
    with open(os.path.join(os.path.dirname(__file__),'c:\project\priceextract\priceresults.csv')) as f:
         dataset.csv = f.read()
    @app.route("/result" )
    def index():    
        return dataset.html  

    if __name__== "__main__":
       app.run()  

 func_clawler('Name')

위 코드를 실행하면 아래와 같은 결과로 막히네요.

This typically means that you attempted to use functionality that needed
an active HTTP request.  Consult the documentation on testing for
information about how to avoid this problem.

혹시 이 문제를 해결하는 방법을 아시면 공유 부탁드립니다.

중고나라에서 상품가격을 크롤링하는 코딩입니다. import urllib.request import urllib.parse import re from bs4 import BeautifulSoup import numpy as np import pandas as pd import sys from flask import Flask, render_template, request import tablib import os

app = Flask(name) @app.route("/") def student(plusurl=None): return render_template('student.html',plusurl='Name')

def func_clawler(plusurl): if request.method == 'POST': #plusurl = input("검색어를 입력하세요:") page=3 pageNum=1 lastPage=int(page)*10-9 num=1 list1=list() while pageNum < lastPage +1:

  baseurl = "https://search.naver.com/search.naver?where=article&sm=tab_jum&query="
  suburl ="%20중고나라%20판매중%20"
  addurl ="&prdtype=0&t=0&st=rel&date_option=0&date_from=&date_to=&srchby=text&dup_remove=1&cafe_url=&without_cafe_url=&board=&sm=tab_pge&start="
  url =  baseurl+urllib.parse.quote_plus(suburl)+urllib.parse.quote_plus(plusurl)+addurl+str(pageNum)
  html = urllib.request.urlopen(url).read()
  soup = BeautifulSoup(html, "html.parser")
  my_price = soup.find_all(class_="cafe_item_price")

  for title in my_price:
    numbers = re.findall("\d+",title.text.replace(',',''))
    index=[]
    new_numbers=np.delete(numbers, index)
    real_numbers=int(new_numbers)
    num +=1
    list1.append(real_numbers)
    list1.sort()

  pageNum += 10
for i in list1:
   print(int(i),end="원 ")
articles = pd.DataFrame(list1, columns=['가격'])
articles.to_csv('c:\project\priceextract\priceresults.csv',encoding='cp949')

dataset = tablib.Dataset()
with open(os.path.join(os.path.dirname(__file__),'c:\project\priceextract\priceresults.csv')) as f:
     dataset.csv = f.read()
@app.route("/result" )
def index():    
    return dataset.html  

if __name__== "__main__":
   app.run()  

func_clawler('Name')

위 코드를 실행하면 아래와 같은 결과로 막히네요. This typically means that you attempted to use functionality that needed an active HTTP request. Consult the documentation on testing for information about how to avoid this problem.

혹시 이 문제를 해결하는 방법을 아시면 공유 부탁드립니다.