mardi 4 août 2020

Reading content in website, not able to open

I'm using Python 2.7.9

I tried open and reading a website but I get errors like: 11001 getaddrsinfo OR no connection ... machine actively refused it

In fact when I try to open a website with the purpose of reading it I'm never able to open it. I believe the problem is a configuration of the system. With webdriver I can open a website but don't know how to read that content. Can you help please?

Here is the code I used, with different possibilities but always with the same errors.

    import socket
import os
os.environ['http_proxy'] = '127.0.0.1:8080'
import requests, re
import urllib2
#from urllib2 import urlopen 
from bs4 import BeautifulSoup as bs

from HTMLParser import HTMLParser
from six.moves import urllib
# as req

#from urllib.request import urlopen

def news ():

    url = "http://www.edureka.co/"
    #payload = {'q': 'shape of you'}
    #r = requests.get(url, params = payload)
##  socket.getaddrinfo('127.0.0.1', 8080)
##  r = requests.get(url)
##  soup = bs(r.text,"html.parser")

#   html = urlopen(url).read()

#   soup = BeautifulSoup(html)
#https://www.crummy.com/software/BeautifulSoup/bs4/doc/
    #webbrowser.register('chrome',  None,
    #webbrowser.BackgroundBrowser("C://Program Files (x86)//Google//Chrome//Application//chrome.exe"))
    
##  link = soup.find('a', {'href':re.compile('http://www.edureka.co/')})['href']
    #link = "http://www.edureka.co/"
    link = 'http://www.edureka.co/'
    print(link)
    #proxies = {'http': 'http://www.someproxy.com:3128'}
    #proxies = {'http': 'http://www.edureka.co/'}
    #f = urllib.urlopen(link, proxies={})
    #proxy_support = urllib2.ProxyHandler({'http': '127.0.0.1'})
### proxy_support = urllib2.ProxyHandler({})
### opener = urllib2.build_opener(proxy_support)
### urllib2.install_opener(opener)
### in_ = opener.open(link)
### in_.read()

##  result = urllib2.urlopen(link)
    #result = urllib.request.urlopen(link)
    #f = urllib2.Request('http://www.edureka.co/')


    socket.getaddrinfo('localhost', 8080)
    mysock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    mysock.connect(("www.edureka.co/", 80))
    #mysock.send('GET http://www.edureka.co/ HTTP/1.0\n\n')
##  f2 = urllib2.urlopen('http://www.edureka.co/')
##  my = f2.read()

    #HTMLParser.feed('http://www.edureka.co/')
    

    #import requests
    #s = requests.Session()
    #url = requests.form['http://www.edureka.co/']
##  r = req.get('http://www.edureka.co')
##  print(r.status_code)
    #req = requests.get('<a href="http://www.edureka.co/">http://www.edureka.co/</a>')

##  r.encoding # returns 'utf-8'
##  soup = BeautifulSoup(r.text, 'html.parser').get_text()

##  print(soup.prettify())



Aucun commentaire:

Enregistrer un commentaire