#!/usr/bin/env python

from scrapy.spiders import CrawlSpider
from scrapy.http import FormRequest
from scrapy.http.request import Request
from loginform import fill_login_form
import logging

logger = logging.getLogger('Zauba')

class zauba(CrawlSpider):
    name = 'Zauba'
    login_url = 'https://www.zauba.com/user'
    login_user = 'scrapybot1@gmail.com'
    login_password = 'scrapybot1'
    logger.info('zauba')
    start_urls = ['https://www.zauba.com/import-gold/p-1-hs-code.html']

def start_requests(self):
    logger.info('start_request')
    # let's start by sending a first request to login page
    yield scrapy.Request(self.login_url, callback = self.parse_login)

def parse_login(self, response):
    logger.warning('parse_login')
    # got the login page, let's fill the login form...
    data, url, method = fill_login_form(response.url, response.body,
                                        self.login_user, self.login_password)

    # ... and send a request with our login data
    return FormRequest(url, formdata=dict(data),
                       method=method, callback=self.start_crawl)

def start_crawl(self, response):
    logger.warning('start_crawl')
    # OK, we're in, let's start crawling the protected pages
    for url in self.start_urls:
        yield scrapy.Request(url, callback=self.parse)

def parse(self, response):
    logger.info('parse')
    text = response.xpath('//div[@id="block-system-main"]/div[@class="content"]/div[@style="width:920px; margin-bottom:12px;"]/span/text()').extract_first()
    total_entries = int(text.split()[0].replace(',', ''))
    total_pages = int(math.ceil((total_entries*1.0)/30))
    logger.warning('***************    :   ' + total_pages)
    print('***************    :   ' + total_pages)
    for page in xrange(1, (total_pages + 1)):
        url = 'https://www.zauba.com/import-gold/p-' + page +'-hs-code.html'
        log.msg('url%d  :  %s' % (pages,url))
        yield scrapy.Request(url, callback=self.extract_entries)


def extract_entries(self, response):
    logger.warning('extract_entries')
    row_trs = response.xpath('//div[@id="block-system-main"]/div[@class="content"]/div/table/tr')
    for row_tr in row_trs[1:]:
        row_content = row_tr.xpath('.//td/text()').extract()
        if (row_content.__len__() == 9):
            print row_content
            yield {
                'date' : row_content[0].replace(' ', ''),
                'hs_code' : int(row_content[1]),
                'description' : row_content[2],
                'origin_country' : row_content[3],
                'port_of_discharge' : row_content[4],
                'unit' : row_content[5],
                'quantity' : int(row_content[6].replace(',', '')),
                'value_inr' : int(row_content[7].replace(',', '')),
                'per_unit_inr' : int(row_content[8].replace(',', '')),
            }

#!/usr/bin/env python

import sys
from argparse import ArgumentParser
from collections import defaultdict
from lxml import html

__version__ = '1.0'  # also update setup.py


def _form_score(form):
    score = 0

    # In case of user/pass or user/pass/remember-me

    if len(form.inputs.keys()) in (2, 3):
        score += 10

    typecount = defaultdict(int)
    for x in form.inputs:
        type_ = (x.type if isinstance(x, html.InputElement) else 'other'
                 )
        typecount[type_] += 1

    if typecount['text'] > 1:
        score += 10
    if not typecount['text']:
        score -= 10

    if typecount['password'] == 1:
        score += 10
    if not typecount['password']:
        score -= 10

    if typecount['checkbox'] > 1:
        score -= 10
    if typecount['radio']:
        score -= 10

    return score


def _pick_form(forms):
    """Return the form most likely to be a login form"""

    return sorted(forms, key=_form_score, reverse=True)[0]


def _pick_fields(form):
    """Return the most likely field names for username and password"""

    userfield = passfield = emailfield = None
    for x in form.inputs:
        if not isinstance(x, html.InputElement):
            continue

        type_ = x.type
        if type_ == 'password' and passfield is None:
            passfield = x.name
        elif type_ == 'text' and userfield is None:
            userfield = x.name
        elif type_ == 'email' and emailfield is None:
            emailfield = x.name

    return (userfield or emailfield, passfield)


def submit_value(form):
    """Returns the value for the submit input, if any"""

    for x in form.inputs:
        if x.type == 'submit' and x.name:
            return [(x.name, x.value)]
    else:
        return []


def fill_login_form(
    url,
    body,
    username,
    password,
    ):
    doc = html.document_fromstring(body, base_url=url)
    form = _pick_form(doc.xpath('//form'))
    (userfield, passfield) = _pick_fields(form)
    form.fields[userfield] = username
    form.fields[passfield] = password
    form_values = form.form_values() + submit_value(form)
    return (form_values, form.action or form.base_url, form.method)


def main():
    ap = ArgumentParser()
    ap.add_argument('-u', '--username', default='username')
    ap.add_argument('-p', '--password', default='secret')
    ap.add_argument('url')
    args = ap.parse_args()

    try:
        import requests
    except ImportError:
        print 'requests library is required to use loginform as a tool'

    r = requests.get(args.url)
    (values, action, method) = fill_login_form(args.url, r.text,
            args.username, args.password)
    print '''url: {0}
method: {1}
payload:'''.format(action, method)
    for (k, v) in values:
        print '- {0}: {1}'.format(k, v)


if __name__ == '__main__':
    sys.exit(main())

2016-10-02 23:31:28 [scrapy] INFO: Scrapy 1.1.3 started (bot: scraptest)
2016-10-02 23:31:28 [scrapy] INFO: Overridden settings: {'NEWSPIDER_MODULE': 'scraptest.spiders', 'FEED_URI': 'medic.json', 'SPIDER_MODULES': ['scraptest.spiders'], 'BOT_NAME': 'scraptest', 'ROBOTSTXT_OBEY': True, 'USER_AGENT': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:39.0) Gecko/20100101 Firefox/39.0', 'FEED_FORMAT': 'json', 'AUTOTHROTTLE_ENABLED': True}
2016-10-02 23:31:28 [scrapy] INFO: Enabled extensions:
['scrapy.extensions.feedexport.FeedExporter',
 'scrapy.extensions.logstats.LogStats',
 'scrapy.extensions.telnet.TelnetConsole',
 'scrapy.extensions.corestats.CoreStats',
 'scrapy.extensions.throttle.AutoThrottle']
2016-10-02 23:31:28 [scrapy] INFO: Enabled downloader middlewares:
['scrapy.downloadermiddlewares.robotstxt.RobotsTxtMiddleware',
 'scrapy.downloadermiddlewares.httpauth.HttpAuthMiddleware',
 'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware',
 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware',
 'scrapy.downloadermiddlewares.retry.RetryMiddleware',
 'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware',
 'scrapy.downloadermiddlewares.redirect.MetaRefreshMiddleware',
 'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware',
 'scrapy.downloadermiddlewares.redirect.RedirectMiddleware',
 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware',
 'scrapy.downloadermiddlewares.chunked.ChunkedTransferMiddleware',
 'scrapy.downloadermiddlewares.stats.DownloaderStats']
2016-10-02 23:31:28 [scrapy] INFO: Enabled spider middlewares:
['scrapy.spidermiddlewares.httperror.HttpErrorMiddleware',
 'scrapy.spidermiddlewares.offsite.OffsiteMiddleware',
 'scrapy.spidermiddlewares.referer.RefererMiddleware',
 'scrapy.spidermiddlewares.urllength.UrlLengthMiddleware',
 'scrapy.spidermiddlewares.depth.DepthMiddleware']
2016-10-02 23:31:28 [scrapy] INFO: Enabled item pipelines:
[]
2016-10-02 23:31:28 [scrapy] INFO: Spider opened
2016-10-02 23:31:28 [scrapy] INFO: Crawled 0 pages (at 0 pages/min), scraped 0 items (at 0 items/min)
2016-10-02 23:31:28 [scrapy] DEBUG: Telnet console listening on 127.0.0.1:6024
2016-10-02 23:31:29 [scrapy] DEBUG: Crawled (200) <GET https://www.zauba.com/robots.txt> (referer: None)
2016-10-02 23:31:38 [scrapy] DEBUG: Crawled (200) <GET https://www.zauba.com/import-gold/p-1-hs-code.html> (referer: None)
2016-10-02 23:31:38 [scrapy] INFO: Closing spider (finished)
2016-10-02 23:31:38 [scrapy] INFO: Dumping Scrapy stats:
{'downloader/request_bytes': 558,
 'downloader/request_count': 2,
 'downloader/request_method_count/GET': 2,
 'downloader/response_bytes': 136267,
 'downloader/response_count': 2,
 'downloader/response_status_count/200': 2,
 'finish_reason': 'finished',
 'finish_time': datetime.datetime(2016, 10, 3, 6, 31, 38, 560012),
 'log_count/DEBUG': 3,
 'log_count/INFO': 7,
 'response_received_count': 2,
 'scheduler/dequeued': 1,
 'scheduler/dequeued/memory': 1,
 'scheduler/enqueued': 1,
 'scheduler/enqueued/memory': 1,
 'start_time': datetime.datetime(2016, 10, 3, 6, 31, 28, 927872)}
2016-10-02 23:31:38 [scrapy] INFO: Spider closed (finished)

>>> scrapy shell "https://www.zauba.com/import-gold/p-1-hs-code.html"
from scrapy import FormRequest
login_data={'name':'mylogin', 'pass':'mypass'})
request = FormRequest.from_response(response, formdata=login_data)
print(request.body)
# b'form_build_id=form-Lf7bFJPTN57MZwoXykfyIV0q3wzZEQqtA5s6Ce-bl5Y&form_id=user_login_block&op=Log+in&pass=mypass&name=mylogin'