Python, Mechanize - request disallowed by robots.txt even after set_handle_robots and add_headers

问题

I have made a web crawler which gets all links till the 1st level of page and from them it gets all link and text plus imagelinks and alt. here is whole code:

import urllib
import re
import time
from threading import Thread
import MySQLdb
import mechanize
import readability
from bs4 import BeautifulSoup
from readability.readability import Document
import urlparse

url = ["http://sparkbrowser.com"]

i=0

while i<len(url):

    counterArray = [0]

    levelLinks = []
    linkText = ["homepage"]
    levelLinks = []

    def scraper(root,steps):
        urls = [root]
        visited = [root]
        counter = 0
        while counter < steps:
            step_url = scrapeStep(urls)
            urls = []
            for u in step_url:
                if u not in visited:
                    urls.append(u)
                    visited.append(u)
                    counterArray.append(counter +1)
            counter +=1
        levelLinks.append(visited)
        return visited

    def scrapeStep(root):
        result_urls = []
        br = mechanize.Browser()
        br.set_handle_robots(False)
        br.set_handle_equiv(False)
        br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]

        for url in root:
            try:
                br.open(url)

                for link in br.links():
                    newurl = urlparse.urljoin(link.base_url, link.url)
                    result_urls.append(newurl)
                    #levelLinks.append(newurl)
            except:
                print "error"
        return result_urls


    scraperOut = scraper(url[i],1)

    for sl,ca in zip(scraperOut,counterArray):
        print "\n\n",sl," Level - ",ca,"\n"

        #Mechanize
        br = mechanize.Browser()
        page = br.open(sl)
        br.set_handle_robots(False)
        br.set_handle_equiv(False)
        br.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
        #BeautifulSoup
        htmlcontent = page.read()
        soup = BeautifulSoup(htmlcontent)


        for linkins in br.links(text_regex=re.compile('^((?!IMG).)*$')):
            newesturl = urlparse.urljoin(linkins.base_url, linkins.url)
            linkTxt = linkins.text
            print newesturl,linkTxt

        for linkwimg in soup.find_all('a', attrs={'href': re.compile("^http://")}):
            imgSource = linkwimg.find('img')
            if linkwimg.find('img',alt=True):
                imgLink = linkwimg['href']
                #imageLinks.append(imgLink)
                imgAlt = linkwimg.img['alt']
                #imageAlt.append(imgAlt)
                print imgLink,imgAlt
            elif linkwimg.find('img',alt=False):
                imgLink = linkwimg['href']
                #imageLinks.append(imgLink)
                imgAlt = ['No Alt']
                #imageAlt.append(imgAlt)
                print imgLink,imgAlt

    i+=1

Everything is working great until my crawler reaches one of facebook links which he can't read, but he gives me error

httperror_seek_wrapper: HTTP Error 403: request disallowed by robots.txt

for the line 68 which is: page = br.open(sl)

And I don't now why because as you can see, I've setted up mechanize set_handle_robots and add_headers options.

I don't know why is that but I noticed that I'm getting that error for facebook links, in this case facebook.com/sparkbrowser and google to.

Any help or advice is welcome.

cheers

回答1:

Ok, so the same problem appeared in this question:

Why is mechanize throwing a HTTP 403 error?

By sending all the request headers a normal browser would send, and accepting / sending back the cookies the server sends should resolve the issue.

来源：https://stackoverflow.com/questions/18096885/python-mechanize-request-disallowed-by-robots-txt-even-after-set-handle-robot