Subversion Repositories SmartDukaan

Rev

Rev 14175 | Rev 14541 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 14175 Rev 14176
Line 1... Line 1...
1
import urllib2
1
import urllib2
2
from BeautifulSoup import BeautifulSoup
2
from BeautifulSoup import BeautifulSoup
3
import re
3
import re
4
from sys import exit
4
from sys import exit
5
 
5
 
-
 
6
headers = { 
-
 
7
           'User-agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
-
 
8
            'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',      
-
 
9
            'Accept-Language' : 'en-US,en;q=0.8',                     
-
 
10
            'Accept-Charset' : 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
-
 
11
            'Cookie':'T=TI141257426738726661427143281839817329423126740566618323641725716448; __sonar=7237334677420142002; __gads=ID=c8b82101a0e4f451:T=1412574724:S=ALNI_MbPMbEOZj2nAGjM54z8ZHFMqwTOTQ; FK-CMP-DATA=; SN=2.VI11FB3FB6ED9D4693A796AB8C965B3417.SI802C325AC43444858830E870C4FD3324.VS141257426735693951472.1412576209; VID=2.VI11FB3FB6ED9D4693A796AB8C965B3417.1412576209.VS141257426735693951472; NSID=2.SI802C325AC43444858830E870C4FD3324.1412576209.VI11FB3FB6ED9D4693A796AB8C965B3417; __utma=19769839.709301254.1412574234.1412574234.1412574234.1; __utmb=19769839.23.10.1412574234; __utmc=19769839; __utmz=19769839.1412574234.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); s_cc=true; gpv_pn=SellerListing%3AMobile%3AMicromax%20Canvas%20Fire%20A093; gpv_pn_t=no%20value; s_sq=%5B%5BB%5D%5D; s_ppv=36',
-
 
12
            'Host':'www.flipkart.com'
-
 
13
        }
-
 
14
 
6
class FlipkartScraper:
15
class FlipkartScraper:
7
    def __init__(self):
16
    def __init__(self):
8
        self.count_trials = 0
17
        self.count_trials = 0
9
        self.redirectCount = 0
18
        self.redirectCount = 0
10
    
19
    
11
    def read(self, url):
20
    def read(self, url):
12
        request = urllib2.Request(url)
-
 
13
        request.add_header('Accept','text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')
-
 
14
        request.add_header('Accept-Language','en-US,en;q=0.8,hi;q=0.6')
-
 
15
        request.add_header('Connection','keep-alive')
-
 
16
        request.add_header('Cookie','T=TI141257426738726661427143281839817329423126740566618323641725716448; __sonar=7237334677420142002; __gads=ID=c8b82101a0e4f451:T=1412574724:S=ALNI_MbPMbEOZj2nAGjM54z8ZHFMqwTOTQ; FK-CMP-DATA=; SN=2.VI11FB3FB6ED9D4693A796AB8C965B3417.SI802C325AC43444858830E870C4FD3324.VS141257426735693951472.1412576209; VID=2.VI11FB3FB6ED9D4693A796AB8C965B3417.1412576209.VS141257426735693951472; NSID=2.SI802C325AC43444858830E870C4FD3324.1412576209.VI11FB3FB6ED9D4693A796AB8C965B3417; __utma=19769839.709301254.1412574234.1412574234.1412574234.1; __utmb=19769839.23.10.1412574234; __utmc=19769839; __utmz=19769839.1412574234.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); s_cc=true; gpv_pn=SellerListing%3AMobile%3AMicromax%20Canvas%20Fire%20A093; gpv_pn_t=no%20value; s_sq=%5B%5BB%5D%5D; s_ppv=36')
21
        request = urllib2.Request(url,headers=headers)
17
        request.add_header('Cache-Control','max-age=0')
-
 
18
        request.add_header('Host','www.flipkart.com')
-
 
19
        request.add_header('User-Agent','Mozilla/5.0 (X11; Linux i686) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.120 Safari/537.36')
-
 
20
        response_data = ""
22
        response_data = ""
21
        redirect_url = ""
-
 
22
        try:
23
        try:
23
            response = urllib2.urlopen(request)
24
            response = urllib2.urlopen(request)
24
            response_data = response.read()
25
            response_data = response.read()
25
            response.close()
26
            response.close()
26
            print "Fetched response from flipkart for %s" %(url)
27
            print "Fetched response from flipkart for %s" %(url)
27
            redirect_url = response.url
-
 
28
 
28
 
29
        except Exception as e:
29
        except Exception as e:
30
            print 'ERROR: ', e
30
            print 'ERROR: ', e
31
            print 'Retrying'
31
            print 'Retrying'
32
            self.count_trials += 1
32
            self.count_trials += 1