Subversion Repositories SmartDukaan

from BeautifulSoup import BeautifulSoup

import mechanize

import sys

import cookielib

from time import sleep

def getBrowserObject():

    br = mechanize.Browser(factory=mechanize.RobustFactory())

    cj = cookielib.LWPCookieJar()

    br.set_cookiejar(cj)

    br.set_handle_equiv(True)

    br.set_handle_redirect(True)

    br.set_handle_referer(True)

    br.set_handle_robots(False)

    br.set_debug_http(False)

    br.set_debug_redirects(False)

    br.set_debug_responses(False)

    br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=1)

    br.addheaders = [('User-agent','Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11'),

                     ('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'),

                     ('Accept-Encoding', 'gzip,deflate,sdch'),                  

                     ('Accept-Language', 'en-US,en;q=0.8'),                     

                     ('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.3')]

    return br

def login(url):

    br = getBrowserObject()

    br.open(url)

    response = br.open(url)

    ungzipResponse(response, br)

    #html = response.read()

    #print html

    br.select_form(name="signinWidget")

    br.form['username'] = "amit.gupta@shop2020.in"

    br.form['password'] = "shop2020"

    response = br.submit()

    print "********************"

    print "Attempting to Login"

    print "********************"

    #ungzipResponse(response, br)

    return br

def requestReport(br,reportUrl):

    print "********************"

    print "Requesting Product Report"

    print "********************"

    br.open(reportUrl)

    return br

def checkStatus(br,statusUrl):

    response = br.open(statusUrl)

    ungzipResponse(response, br)

    page = response.read()

    return br, page

def getReportBatchId(br,page):

    print "********************"

    print "Fetching Batch Id for request"

    print "********************"

    soup = BeautifulSoup(page,convertEntities=BeautifulSoup.HTML_ENTITIES)

    table_rows = soup.find("tr" , {"class" : "list-row-even"})

    batchId = table_rows.findAll("td")

    return br , batchId[1].text

def downloadReport(br,batchId,statusUrl):

    print "********************"

    print "Check request status"

    print "********************"

    response = br.open(statusUrl)

    ungzipResponse(response, br)

    page = response.read()

    soup = BeautifulSoup(page,convertEntities=BeautifulSoup.HTML_ENTITIES)

    table_rows_even = soup.findAll("tr" , {"class" : "list-row-even"})

    table_rows_odd = soup.findAll("tr" , {"class" : "list-row-odd"})

    for tr in table_rows_even:

        row = tr.findAll("td")

        if row[1].text==batchId and row[4].text=='Ready':

            return br , row[5].find("a", {"class" : "buttonImage"})

    for tr in table_rows_odd:

        row = tr.findAll("td")

        if row[1].text==batchId and row[4].text=='Ready':

            return br , row[5].find("a", {"class" : "buttonImage"})

    return br,None

def fetchFile(link,br,batchId):

    print "********************"

    print "Writing file to disk"

    print "********************"

    response = br.open(link)

    print br.response().info()

    print br.response().read

    ungzipResponse(response,br)

    output = open(batchId+'.txt','wb')

    output.write(br.response().get_data())

    output.close()

def ungzipResponse(r,b):

    headers = r.info()

    if headers['Content-Encoding']=='gzip':

        import gzip

        print "********************"

        print "Deflating gzip response"

        print "********************"

        gz = gzip.GzipFile(fileobj=r, mode='rb')

        html = gz.read()

        gz.close()

        headers["Content-type"] = "text/html; charset=utf-8"

        r.set_data( html )

        b.set_response(r)

def main():

    print "Opening Seller Central login page"

    login_url = "https://sellercentral.amazon.in/gp/homepage.html"

    br = login(login_url)

    report_url = "https://sellercentral.amazon.in/gp/upload-download-utils/requestReport.html?ie=UTF8&type=nemoProductReports"

    br = requestReport(br,report_url)

    status_url="https://sellercentral.amazon.in/gp/upload-download-utils/reportStatusData.html"

    br, page = checkStatus(br,status_url)

    br, batchId = getReportBatchId(br,page)

    print "*********************************"

    print "Batch Id for request is ",batchId

    print "*********************************"

    ready = False

    retryCount = 0

    while not ready:

        if retryCount == 6:

            print "File not available for download after multiple retries"

            sys.exit(1)

        br, download_link = downloadReport(br,batchId,status_url)

        if download_link is not None:

            ready= True

            continue

        print "File not ready for download yet.Will try again after 10 minutes."

        retryCount+=1

        sleep(600)

    fetchFile(download_link['href'],br,batchId)

if __name__ == "__main__":

    main()