Subversion Repositories SmartDukaan

Rev

Rev 14542 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 14542 Rev 14745
Line 1... Line -...
1
import urllib2
-
 
2
from BeautifulSoup import BeautifulSoup
1
from BeautifulSoup import BeautifulSoup
3
import re
2
import re
4
from sys import exit
3
from sys import exit
-
 
4
from dtr.utils.utils import fetchResponseUsingProxy
5
 
5
 
6
headers = { 
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',
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',      
8
            'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',      
9
            'Accept-Language' : 'en-US,en;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',
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',
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'
12
            'Host':'www.flipkart.com',
-
 
13
            'Accept-Encoding' : 'gzip,deflate,sdch'
13
        }
14
        }
14
 
15
 
15
class FlipkartScraper:
16
class FlipkartScraper:
16
    def __init__(self):
17
    def __init__(self):
17
        self.count_trials = 0
18
        self.count_trials = 0
18
        self.redirectCount = 0
19
        self.redirectCount = 0
19
    
20
    
20
    def read(self, url):
21
    def read(self, url):
21
        try:
22
        try:
22
            proxy = urllib2.ProxyHandler({'http': 'http://192.161.163.60:8800'})
-
 
23
            opener = urllib2.build_opener(proxy)
-
 
24
            urllib2.install_opener(opener)
23
            """quick fix,need to add it conf""" 
25
            response = urllib2.urlopen(url)
-
 
26
            response_data = response.read()
-
 
27
            response.close()
-
 
28
#        try:
24
            
29
#            response = urllib2.urlopen(request)
-
 
30
#            response_data = response.read()
25
            response_data = fetchResponseUsingProxy(url, headers)
31
#            response.close()
26
            
32
#            print "Fetched response from flipkart for %s" %(url)
-
 
33
 
-
 
34
        except Exception as e:
27
        except Exception as e:
35
            print 'ERROR: ', e
28
            print 'ERROR: ', e
36
            print 'Retrying'
29
            print 'Retrying'
37
            self.count_trials += 1
30
            self.count_trials += 1
38
 
31