def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(1)
driver = driverInitialize(path='/home/mayank/.mozilla/firefox/4s3bttuq.default/', timeout=timeout)
driver.set_page_load_timeout(timeout)
for version in versions:
url = url_base + str(version)
try:
logger.info('Fetching URL[%s]' % url)
driver.get(url)
logger.info('After Fetch[%s]' % url)
except Exception as e:
logger.info("Warning %s", e)
if os.path.exists(csv_file):
version_file = 'CSVs/' + str(version) + '.csv'
logger.info('Writing %s' % version_file)
os.rename(csv_file, version_file)
else:
logger.error('Missed file[%s] from URL[%s]' % (version_file, url))
logger.info("CSV Fetched From [%s]" % url)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(0)
driver = driverInitialize()
for mandal in mandals:
report = generate_report(logger, driver, mandal, districts[mandal])
logger.info('Finally: \n%s' % report)
filename = './mandals/' +mandal + '.csv'
with open(filename, 'wb') as csv_file:
logger.info("Writing to [%s]" % filename)
csv_file.write(report.encode('utf-8'))
if final_report[0][0] == '':
rows = report.split('|')
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
return
def main():
runTestSuite()
exit(0)
if __name__ == '__main__':
main()
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
db = dbInitialize(db="biharPDS", charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
inyear=args['year']
logger.info(inyear)
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
#Start Program here
url="http://www.google.com"
driver.get(url)
myhtml=driver.page_source
print myhtml
# End program here
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def setUp(self):
self.logger = loggerFetch('info')
self.logger.info('BEGIN PROCESSING')
# Pass 0 for headless
self.display = displayInitialize(1)
#, path='/path/to/firefox/')
self.driver = driverInitialize(browser='firefox')
self.url = URL
def setUp(self):
self.logger = loggerFetch('info')
self.logger.info('BEGIN PROCESSING...')
self.display = displayInitialize(0)
# self.driver = driverInitialize(timeout=3)
self.driver = driverInitialize(
timeout=3, options='--headless'
) # driverInitialize(path='/opt/firefox/', timeout=3)
def setUp(self):
self.args = argsFetch()
self.logger = loggerFetch('info')
self.logger.info('BEGIN PROCESSING')
self.display = displayInitialize(self.args['visible'])
self.driver = driverInitialize(browser=self.args['browser'] , path='/home/mayank/.mozilla/firefox/4s3bttuq.default/')
self.cmd = 'nohup youtube-dl --username %s --password %s -o %s ' % (user, password, '"%(title)s.%(ext)s"')
self.url = self.args['url']
def downloadJobcards(logger, db, cmd=None, directory=None, url=None, isVisible=None, isPushInfo=None, query=None, fetch_jobcard_details=None):
'''
Crawl the html for the musters
'''
logger.info("BEGIN %s..." % cmd)
if cmd == None:
cmd="Downloading"
if directory == None:
directory = "./jobcards"
if url == None:
url = 'http://www.nrega.telangana.gov.in/Nregs/FrontServlet?requestType=HouseholdInf_engRH&actionVal=SearchJOB&JOB_No='
if isVisible == None:
isVisible = 0
if isPushInfo == None:
isPushInfo = False
logger.info("Command[%s] Directory[%s] URL[%s]" % (cmd, directory, url))
if not query:
# Mynk - use when b.name is not all 'Ghattu' query = 'select j.jobcard, p.name, b.name from jobcardRegister j, panchayats p, blocks b where j.blockCode=p.blockCode and j.panchayatCode=p.panchayatCode and j.blockCode=b.blockCode'
query = 'select j.jobcard, p.name, p.panchayatCode from jobcardRegister j, panchayats p, blocks b where j.blockCode=p.blockCode and j.panchayatCode=p.panchayatCode and j.blockCode=b.blockCode and DATE_SUB(NOW(), INTERVAL 1 DAY) >= downloadDate order by j.downloadDate'
logger.info('Executing query: [%s]', query)
cur = db.cursor()
cur.execute(query)
jobcard_details = cur.fetchall()
if jobcard_details:
logger.debug("Jobcard Details [%s]" % str(jobcard_details))
display = displayInitialize(isVisible)
driver = driverInitialize()
for (jobcard, panchayat, panchayat_code) in jobcard_details:
logger.info( "jobcard[%s] panchayat[%s] panchayat_code[%s]" % (jobcard, panchayat, panchayat_code))
dirname = directory + '/' + panchayat
html_source = downloadJobcardHTML(logger, driver, db, jobcard, dirname)
if isPushInfo or fetch_jobcard_details:
if html_source:
pushMusterInfo(logger, db, html_source, jobcard, panchayat_code, fetch_jobcard_details)
else:
query = 'update jobcardRegister set isDownloaded=0 where jobcard="%s"' % (jobcard) # Mynk
logger.info('Executing query: [%s]', query)
cur = db.cursor()
cur.execute(query)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END %s" % cmd)
def contextInitialize(self, logger, args):
self.logger = logger
self.db = dbInitialize(db="mahabubnagar")
self.display = displayInitialize(args['visible'])
if args['visible']:
delay=5
else:
delay=1
self.driver = driverInitialize(args['browser'])
# contextRegister(self)
logger.info("Context Initialized")
def setUp(self):
self.args = argsFetch()
self.logger = loggerFetch('info')
self.logger.info('BEGIN PROCESSING')
self.display = displayInitialize(self.args['visible'])
self.driver = driverInitialize(
browser=self.args['browser'],
path='/home/mayank/.mozilla/firefox/4s3bttuq.default/')
self.cmd = 'nohup youtube-dl --username %s --password %s -o %s ' % (
user, password, '"%(title)s.%(ext)s"')
self.url = self.args['url']
def setUp(self):
args = argsFetch()
level = args['log_level']
if not level:
level = 'info'
self.logger = loggerFetch(level)
self.logger.info('args: %s', str(args))
self.logger.info('BEGIN PROCESSING...')
self.parse = args['parse']
dirname = args['directory']
if not self.parse:
self.display = displayInitialize(args['visible'])
self.driver = driverInitialize(timeout=3, options='--headless') # driverInitialize(path='/opt/firefox/', timeout=3)
def __init__(self, logger=None, is_selenium=None):
if logger:
self.logger = logger
else:
logger = self.logger = logger_fetch('info')
logger.info(f'Constructor({type(self).__name__})')
#self.url = 'http://ceo.karnataka.gov.in/draftroll_2020/'
self.url = 'http://ceo.karnataka.gov.in/finalrolls_2020/'
self.status_file = 'status.csv'
language = 'English' # 'Kannada' if KANNADA else 'English'
if IS_DEBUG:
self.dir = f'BBMP/{language}'
else:
self.dir = f'../Data/BBMP/{language}'
if not os.path.exists(self.dir):
os.makedirs(self.dir)
self.ignore = True
self.is_selenium = False
if is_selenium:
self.is_selenium = is_selenium
if self.is_selenium:
self.display = displayInitialize(isDisabled = not is_virtual, isVisible = is_visible)
self.driver = driverInitialize(timeout=3)
#self.driver = driverInitialize(path='/opt/firefox/', timeout=3)
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = r'../private/aap.bangaluru.json'
self.project = 'BBMP-OCR'
self.bucket_name = 'aap_bangaluru' # 'bbmp_bucket' # 'test_aap'
self.storage_client = storage.Client()
self.vision_client = vision.ImageAnnotatorClient()
df = pd.read_csv('Ward-AC-LS-Mapping.csv')
#lookup_df = df[['AC#', 'LS#']].drop_duplicates('AC#', keep='last')
self.ac2ls = dict(zip(df['AC#'], df['LS#']))
self.ls_name_of = {
'23': 'Bangalore Rural',
'24': 'Bangalore North',
'25': 'Bangalore Central',
'26': 'Bangalore South',
'27': 'Chikkabalapura',
}
self.ac_name_of = dict(zip(df['AC#'], df['Assembly constituency']))
self.ac_name_of[177] = 'Anekal'
self.ac2ls[177] = 26
self.ward2ac = dict(zip(df['Ward No'], df['AC#']))
self.ward_name_of = dict(zip(df['Ward No'], df['Ward Name']))
df = pd.read_csv('Booths2WardMapping.csv')
self.part2ward = dict(zip(df['Part'], df['Ward']))
self.ward_name_of[999] = 'Extra Data'
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
if args['limit']:
limit = int(args['limit'])
else:
limit =1
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
url="http://nrega.nic.in/netnrega/sthome.aspx"
driver.get(url)
myMusters=Muster.objects.filter( Q(isDownloaded=False) | Q(musterDownloadAttemptDate__lt = musterTimeThreshold,isComplete=0) )[:limit]
for eachMuster in myMusters:
logger.info(eachMuster.musterURL)
logger.info("Processing musterNo: %s FullblockCode: %s " % (eachMuster.musterNo,eachMuster.block.fullBlockCode))
driver.get(eachMuster.musterURL)
driver.get(eachMuster.musterURL)
myhtml = driver.page_source
error,musterTable,musterSummaryTable=validateMusterHTML(eachMuster,myhtml)
if error is None:
outhtml=''
outhtml+=stripTableAttributes(musterSummaryTable,"musterSummary")
outhtml+=stripTableAttributes(musterTable,"musterDetails")
title="Muster: %s state:%s District:%s block:%s finyear:%s " % (eachMuster.musterNo,eachMuster.block.district.state.name,eachMuster.block.district.name,eachMuster.block.name,getFullFinYear(eachMuster.finyear))
logger.info(title)
outhtml=htmlWrapperLocal(title=title, head='<h1 aling="center">'+title+'</h1>', body=outhtml)
try:
outhtml=outhtml.encode("UTF-8")
except:
outhtml=outhtml
filename="%s.html" % (eachMuster.musterNo)
eachMuster.musterFile.save(filename, ContentFile(outhtml))
eachMuster.musterDownloadAttemptDate=datetime.now()
eachMuster.isDownloaded=True
eachMuster.save()
else:
logger.info("Muster Download Erorr: %s " % (error))
eachMuster.musterDownloadAttemptDate=datetime.now()
eachMuster.downloadError=error
eachMuster.save()
# myMusters=Muster.objects.filter(
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
exit(0)
def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(1)
driver = driverInitialize(path='/opt/firefox/')
driver.get(url)
logger.info("Fetching...[%s]" % url)
driver.get(url) # A double refresh required for the page to load
logger.info("Refreshing...[%s]" % url)
html_source = driver.page_source.replace('<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
logger.debug("HTML Fetched [%s]" % html_source)
bs = BeautifulSoup(html_source, "html.parser")
tr_list = bs.findAll('tr', attrs={'class':['normalRow', 'alternateRow']})
logger.debug(str(tr_list))
for tr in tr_list:
td = tr.find('td')
td = td.findNext('td')
panchayat = td.text.strip()
logger.info("Panchayat[%s]", panchayat)
elem = driver.find_element_by_link_text(panchayat)
elem.click()
filename="/tmp/%s.html" % panchayat
with open(filename, 'wb') as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(driver.page_source.encode('utf-8'))
driver.back()
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
db = dbInitialize(db="surguja", charset="utf8")
if not args['parse']:
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
if args['visible']:
delay = 2
download_dir = args['directory']
if download_dir:
download_dir = download_dir + '/' + strftime('%B-%Y')
logger.info('download_dir[%s]' % download_dir)
if not os.path.exists(download_dir):
os.makedirs(download_dir)
if args['prev']:
pdsFetchPrev(logger, driver, db, download_dir, args['month'], args['year'])
elif args['parse']:
pdsReportParse(logger, db, download_dir)
elif args['work_allocation']:
downloadWorkAllocationHTML(driver, db, logger) # Mynk Fix Order
elif args['fetch']:
pdsFetchReports(logger, driver, db, download_dir)
else:
pdsFetch(logger, driver, db, download_dir)
if not args['parse']:
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db)
logger.info("...END PROCESSING")
exit(0)
def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(0)
driver = driverInitialize()
report = generate_report(logger, driver)
logger.info('Finally: \n%s' % report)
with open(filename, 'wb') as csv_file:
logger.info("Writing to [%s]" % filename)
csv_file.write(report.encode('utf-8'))
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
return
def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(0)
driver = driverInitialize()
report = generate_report(logger, driver)
logger.info('Finally: \n%s' % report)
with open(filename, 'wb') as csv_file:
logger.info("Writing to [%s]" % filename)
csv_file.write(report.encode('utf-8'))
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
return
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
if args['jobcard']:
jobcard=args['jobcard']
else:
jobcard='141975701001010679'
logger.info("Fetching Jobcard[%s]..." % jobcard)
html = downloadJobcardHTML(logger, driver, jobcard)
logger.info(html)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
db = dbInitialize(db=nregaDB, charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
if args['limit']:
limit = int(args['limit'])
else:
limit =50000
limitString=" limit %s " % str(limit)
additionalFilters=''
if args['district']:
additionalFilters+= " and b.districtName='%s' " % args['district']
if args['finyear']:
additionalFilters+= " and finyear='%s' " % args['finyear']
if args["downloadWagelists"]:
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
url="http://164.100.129.6/netnrega/nregasearch1.aspx"
driver.get(url)
time.sleep(22)
htmlsource = driver.page_source
#writeFile("/tmp/a.html",htmlsource)
stateName="CHHATTISGARH"
districtName="SURGUJA"
wagelistNo="3305002062WL005160"
try:
maintab = driver.current_window_handle
Select(driver.find_element_by_id("ddl_search")).select_by_visible_text("WageList")
driver.find_element_by_css_selector("option[value=\"WageList\"]").click()
Select(driver.find_element_by_id("ddl_state")).select_by_visible_text(stateName.upper())
#myvalue='value="%s"' % stateCode
driver.find_element_by_css_selector("option[value=\"33\"]").click()
# driver.find_element_by_css_selector("option[%s]" % myvalue).click()
Select(driver.find_element_by_id("ddl_district")).select_by_visible_text(districtName.upper())
#myvalue='value="%s"' % (stateCode+districtCode)
driver.find_element_by_css_selector("option[value=\"3305\"]").click()
#driver.find_element_by_css_selector("option[%s]" % myvalue).click()
driver.find_element_by_id("txt_keyword2").clear()
driver.find_element_by_id("txt_keyword2").send_keys(wagelistNo)
driver.find_element_by_id("btn_go").click()
time.sleep(30)
#logger.info("Currently the number of active tabs are %s" % str(len(driver.window_handles)))
error=0
except:
error=1
wurl="http://164.100.129.6/netnrega/srch_wg_dtl.aspx?state_code=&district_code=3305&state_name=CHHATTISGARH&district_name=SURGUJA&block_code=3305002&wg_no=3305002062WL005160&short_name=CH&fin_year=2016-2017&mode=wg"
driver.get(wurl)
htmlsource = driver.page_source
filename="%s/b.html" % tempDir
writeFile(filename,htmlsource)
query="select w.id,w.wagelistNo,b.rawBlockName,b.fullBlockCode,b.blockCode,b.districtCode,b.stateCode,b.stateShortCode,w.finyear,b.stateName,b.districtName from wagelists w,blocks b where w.fullBlockCode=b.fullBlockCode and ( (w.isDownloaded=0) or (w.isComplete=0 and TIMESTAMPDIFF(HOUR, w.downloadAttemptDate, now()) > 48 )) %s order by w.isDownloaded %s " % (additionalFilters,limitString)
cur.execute(query)
results=cur.fetchall()
for row in results:
[rowid,wagelistNo,blockName,fullBlockCode,blockCode,districtCode,stateCode,stateShortCode,finyear,stateName,districtName] = row
fullfinyear=getFullFinYear(finyear)
logger.info(" RowID : %s, wagelistNo: %s " % (str(rowid),wagelistNo))
jobcardPrefix="%s-%s-" % (stateShortCode,districtCode)
#logger.info("Jobcard Prefix : %s " % jobcardPrefix)
fullDistrictCode=stateCode+districtCode
if wagelistNo != '':
#logger.info(wagelistNo)
wurl="http://%s/netnrega/srch_wg_dtl.aspx?state_code=&district_code=%s&state_name=%s&district_name=%s&block_code=%s&wg_no=%s&short_name=%s&fin_year=%s&mode=wg" % (searchIP,fullDistrictCode,stateName.upper(),districtName.upper(),fullBlockCode,wagelistNo,stateShortCode,fullfinyear)
logger.info("URL: %s " % wurl)
driver.get(wurl)
htmlsource = driver.page_source
htmlsource=htmlsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
success=0
isComplete=0
if ("WageList Agency Code" in htmlsource) and (jobcardPrefix in htmlsource):
filepath=nregaRawDataDir.replace("stateName",stateName.upper()).replace("districtName",districtName.upper())
filename=filepath+blockName.upper()+"/WAGELISTS/"+fullfinyear+"/"+wagelistNo+".html"
# filename=filepath+blockName.upper()+"/WAGELIST/"+fullfinyear+"/"+wagelistNo+".html"
# logger.info(filename)
writeFile(tempDir+wagelistNo+".html",htmlsource)
writeFile(filename,htmlsource)
success=1
isComplete=1
htmlsoup=BeautifulSoup(htmlsource)
tables=htmlsoup.findAll('table')
for table in tables:
#logger.info("Found the Table")
rows=table.findAll("tr")
for row in rows:
cols=row.findAll("td")
ftoNo=cols[12].text
if ftoNo != "FTO No.":
#logger.info("FTO No : %s " % ftoNo)
if stateShortCode not in ftoNo:
isComplete=0
else:
query="select * from ftos where finyear='%s' and fullBlockCode='%s' and ftoNo='%s'" % (finyear,fullBlockCode,ftoNo)
#logger.info(query)
cur.execute(query)
if cur.rowcount == 0:
query="insert into ftos (finyear,ftoNo,fullBlockCode,stateCode,districtCode,blockCode) values ('%s','%s','%s','%s','%s','%s') " % (finyear,ftoNo,fullBlockCode,stateCode,districtCode,blockCode)
#logger.info(query)
cur.execute(query)
query="update wagelists set isDownloaded=%s,isComplete=%s,downloadAttemptDate=NOW() where id=%s" %(str(success),str(isComplete),str(rowid))
#logger.info(query)
cur.execute(query)
# driver.find_element_by_tag_name('body').send_keys(Keys.CONTROL + 'w')
# driver.switch_to_window(maintab)
driverFinalize(driver)
displayFinalize(display)
if args["downloadFTOs"]:
#additionalFilters=''
#limitString= "limit 1 "
query="select f.id,f.ftoNo,f.blockCode,f.finyear,f.fullBlockCode,b.rawBlockName,b.districtName,b.stateName,b.stateCode from ftos f,blocks b where f.fullBlockCode=b.fullBlockCode and f.isComplete=0 and ( (f.isDownloaded=0) or (TIMESTAMPDIFF(HOUR, f.downloadAttemptDate, now()) > 48 ) or f.downloadAttemptDate is NULL ) %s order by f.downloadAttemptDate,finyear %s " % (additionalFilters,limitString)
logger.info(query)
cur.execute(query)
results=cur.fetchall()
for row in results:
[rowid,ftoNo,blockCode,finyear,fullBlockCode,blockName,districtName,stateName,stateCode]=row
logger.info("districtName: %s, blockName: %s finyear: %s ftoNo: %s " % (districtName,blockName,finyear,ftoNo))
fullfinyear=getFullFinYear(finyear)
if ftoNo != '':
# filepath=nregaRawDataDir.replace("stateName",stateName.upper()).replace("districtName",districtName.upper())
filepath=nregaWebDir.replace("stateName",stateName.upper()).replace("districtName",districtName.upper())
filename=filepath+blockName.upper()+"/FTOs/"+fullfinyear+"/"+ftoNo+".html"
logger.info("Downloading FTO: %s " % ftoNo)
htmlresponse,htmlsource = getFTO(fullfinyear,stateCode,ftoNo)
logger.info("Response = %s " % htmlresponse)
success=0
isPopulatedString=''
if htmlresponse['status'] == '200':
logger.info("Status is 200")
isPopulatedString="isPopulated=0,"
success,outhtml=alterFTO(cur,logger,htmlsource,stateName,districtName,blockName,ftoNo,rowid)
#htmlsource=htmlsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
if not os.path.exists(os.path.dirname(filename)):
os.makedirs(os.path.dirname(filename))
myfile = open(filename, "wb")
myfile.write(outhtml.encode("UTF-8"))
logger.info(filename)
#writeFile(filename,htmlsource)
#writeFile3("/home/libtech/webroot/nreganic.libtech.info/temp/"+ftoNo+".html",htmlsource)
query="update ftos set isDownloaded=%s,%sdownloadAttemptDate=NOW() where id=%s" %(str(success),str(isPopulatedString),str(rowid))
logger.info(query)
cur.execute(query)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
db = dbInitialize(db="biharPDS", charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
inyear=args['year']
logger.info(inyear)
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
#Start Program here
base_url = "http://sfc.bihar.gov.in/"
verificationErrors = []
accept_next_alert = True
driver.get("http://sfc.bihar.gov.in/login.htm")
driver.get(base_url + "/fpshopsSummaryDetails.htm")
Select(driver.find_element_by_id("year")).select_by_visible_text(inyear)
time.sleep(10)
select_box = driver.find_element_by_id("district_id") # if your select_box has a name.. why use xpath?..... this step could use either xpath or name, but name is sooo much easier.
options = [x for x in select_box.find_elements_by_tag_name("option")] #this part is cool, because it searches the elements contained inside of select_box and then adds them to the list options if they have the tag name "options"
for element in options:
distCode=element.get_attribute("value") #
distName=element.get_attribute("text") #
logger.info("District Code: %s District Name: %s " %(distCode,distName))
Select(driver.find_element_by_id("district_id")).select_by_value(distCode)
time.sleep(10)
block_box = driver.find_element_by_id("block_id") # if your select_box has a name.. why use xpath?..... this step could use either xpath or name, but name is sooo much easier.
blockOptions = [y for y in block_box.find_elements_by_tag_name("option")] #this part is cool, because it searches the elements contained inside of select_box and then adds them to the list options if they have the tag name "options"
for blockElement in blockOptions:
blockCode=blockElement.get_attribute("value") #
blockName=blockElement.get_attribute("text") #
logger.info("distCode:%s distName:%s blockCode:%s blockName:%s " % (distCode,distName,blockCode,blockName))
Select(driver.find_element_by_id("block_id")).select_by_value(blockCode)
time.sleep(10)
fps_box = driver.find_element_by_id("fpshop_id") # if your select_box has a name.. why use xpath?..... this step could use either xpath or name, but name is sooo much easier.
fpsOptions = [z for z in fps_box.find_elements_by_tag_name("option")] #this part is cool, because it searches the elements contained inside of select_box and then adds them to the list options if they have the tag name "options"
for fpsElement in fpsOptions:
fpsCode=fpsElement.get_attribute("value") #
fpsName=fpsElement.get_attribute("text") #
myString=distCode+','+distName+','+blockCode+','+blockName+','+fpsCode+','+fpsName
logger.info(myString)
if "Select" in myString:
logger.info("This will not be entered into Database")
else:
fpsName1=cleanFPSName(fpsName)
whereClause="where fpsCode='%s' and blockCode='%s' and distCode='%s' " % (fpsCode,blockCode,distCode)
query="select * from pdsShops %s " % (whereClause)
cur.execute(query)
if cur.rowcount == 0:
query="insert into pdsShops (fpsCode,blockCode,distCode) values ('%s','%s','%s') " % (fpsCode,blockCode,distCode)
cur.execute(query)
query="update pdsShops set distName='%s',blockName='%s',fpsName='%s' %s " % (distName,blockName,fpsName1,whereClause)
logger.info(query)
cur.execute(query)
# End program here
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
districtName=args['district']
logger.info("DistrictName "+districtName)
db = dbInitialize(db=districtName.lower(), charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
jobcardPrefix="%s-%s" % (stateShortCode,districtCode)
logger.info("crawlIP "+crawlIP)
logger.info("State Name "+stateName)
#Start Program here
url="http://nrega.nic.in/netnrega/sthome.aspx"
driver.get(url)
elem = driver.find_element_by_link_text(stateName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
elem = driver.find_element_by_link_text(districtName.upper())
elem.send_keys(Keys.RETURN)
time.sleep(1)
#Query to get all the blocks
query="select stateCode,districtCode,blockCode,name from blocks where isRequired=1"
cur.execute(query)
results = cur.fetchall()
for row in results:
stateCode=row[0]
blockCode=row[2]
blockName=row[3]
logger.info("Block Name" + blockName)
elem = driver.find_element_by_link_text(blockName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
query="select name,panchayatCode,id from panchayats where isRequired=1 and stateCode='"+stateCode+"' and districtCode='"+districtCode+"' and blockCode='"+blockCode+"' order by jobcardCrawlDate"
cur.execute(query)
panchresults = cur.fetchall()
for panchrow in panchresults:
panchayatName=panchrow[0]
panchayatCode=panchrow[1]
panchID=panchrow[2]
logger.info(stateCode+districtCode+blockCode+blockName+panchayatCode+panchayatName)
elem = driver.find_element_by_link_text(panchayatName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
elem = driver.find_element_by_link_text("Job card/Employment Register")
elem.send_keys(Keys.RETURN)
time.sleep(5)
curtime = time.strftime('%Y-%m-%d %H:%M:%S')
html_source = driver.page_source
htmlsoup=BeautifulSoup(html_source)
#logger.info(html_source)
#f=open("/tmp/ab.html","w")
#f.write(html_source)
try:
table=htmlsoup.find('table',align="center")
rows = table.findAll('tr')
status=1
except:
status=0
query="update panchayats set jobcardCrawlStatus="+str(status)+", jobcardCrawlDate='"+curtime+"' where id="+str(panchID)
logger.info(query)
cur.execute(query)
logger.info("Status is " + str(status))
if status==1:
for tr in rows:
cols = tr.findAll('td')
jclink=''
for link in tr.find_all('a'):
jclink=link.get('href')
if len(cols) > 2:
jcno="".join(cols[1].text.split())
if jobcardPrefix in jcno:
logger.info(jcno)
query="insert into jobcardRegister (jobcard,stateCode,districtCode,blockCode,panchayatCode) values ('"+jcno+"','"+stateCode+"','"+districtCode+"','"+blockCode+"','"+panchayatCode+"')"
try:
cur.execute(query)
except MySQLdb.IntegrityError,e:
errormessage=(time.strftime("%d/%m/%Y %H:%M:%S "))+str(e)+"\n"
#errorfile.write(errormessage)
continue
driver.back()
driver.back()
time.sleep(5)
driver.back()
time.sleep(5)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
display = displayInitialize()
driver = driverInitialize()
db = dbInitialize(db="libtech", charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
limitString=''
if args['limit']:
limitString=' limit '+args['limit']
if args['district']:
districtName=args['district']
logger.info("DistrictName "+districtName)
if args['finyear']:
finyear=args['finyear']
logger.info("finyear "+finyear)
#Query to get all the blocks
query="use libtech"
cur.execute(query)
query="select crawlIP from crawlDistricts where name='%s'" % districtName.lower()
crawlIP=singleRowQuery(cur,query)
query="select state from crawlDistricts where name='%s'" % districtName.lower()
stateName=singleRowQuery(cur,query)
logger.info("crawlIP "+crawlIP)
logger.info("State Name "+stateName)
query="use %s" % districtName.lower()
cur.execute(query)
ftofilepath=nregaDataDir.replace("stateName",stateName.title())+"/"+districtName.upper()+"/"
#
url="http://services.ptcmysore.gov.in/emo/Trackfto.aspx"
#ftofilepath="/home/libtech/libtechdata/CHATTISGARH/"+districtName+"/"
query="select b.name,f.ftoNo,f.stateCode,f.districtCode,f.blockCode,f.finyear,f.id from ftoDetails f,blocks b where TIMESTAMPDIFF(HOUR, f.statusDownloadDate, now()) > 48 and f.isStatusDownloaded=0 and f.finyear='%s' and f.blockCode=b.blockCode and f.stateCode=b.stateCode and f.districtCode=b.districtCode %s;" % (finyear,limitString)
#query="select b.name,f.ftoNo,f.stateCode,f.districtCode,f.blockCode,f.finyear,f.id from ftoDetails f,blocks b where f.isDownloaded=0 and f.blockCode=b.blockCode and f.stateCode=b.stateCode and f.districtCode=b.districtCode and b.blockCode='003';"
cur.execute(query)
if cur.rowcount:
logger.info("Number of records tobe processed:" +str(cur.rowcount))
results = cur.fetchall()
for row in results:
blockName=row[0]
ftono=row[1]
stateCode=row[2]
districtCode=row[3]
blockCode=row[4]
finyear=row[5]
ftoid=row[6]
fullBlockCode=stateCode+districtCode+blockCode
fullDistrictCode=stateCode+districtCode
fullfinyear=getFullFinYear(finyear)
logger.info(stateCode+districtCode+blockCode+blockName)
ftofilename=ftofilepath+blockName+"/FTO/"+fullfinyear+"/"+ftono+"_status.html"
if not os.path.exists(os.path.dirname(ftofilename)):
os.makedirs(os.path.dirname(ftofilename))
logger.info(ftofilename)
driver.get(url)
driver.find_element_by_id("ctl00_ContentPlaceHolder1_txtFTO").clear()
#driver.find_element_by_id("ctl00_ContentPlaceHolder1_txtFTO").send_keys("CH3305003_081015FTO_142597")
driver.find_element_by_id("ctl00_ContentPlaceHolder1_txtFTO").send_keys(ftono)
driver.find_element_by_id("ctl00_ContentPlaceHolder1_Button1").click()
html_source = driver.page_source
html_source=html_source.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
# print html_source
f = open(ftofilename, 'w')
f.write(html_source.encode("UTF-8"))
query="update ftoDetails set isStatusDownloaded=1,statusDownloadDate=now() where id="+str(ftoid)
logger.info(query)
cur.execute(query)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
display = displayInitialize(args['visible'])
driver = driverInitialize(browser=args['browser'] , path='/home/mayank/.mozilla/firefox/4s3bttuq.default/')
base_url="https://www.skillshare.com/login"
driver.get(base_url)
logger.info('Fetching URL[%s]' % base_url)
# driver.find_element_by_link_text("Sign In").click()
try:
driver.find_element_by_name("LoginForm[email]").clear()
driver.find_element_by_name("LoginForm[email]").send_keys("*****@*****.**")
driver.find_element_by_name("LoginForm[password]").clear()
# driver.find_element_by_name("LoginForm[password]").send_keys("#######")
# driver.find_element_by_xpath("//input[@value='Sign In']").click()
time.sleep(100) # If you want to manually log in
except Exception as e:
logger.info('Already signed in [%s]', e)
time.sleep(10)
filename = "./z.csv"
content = csv.reader(open(filename, 'r'), delimiter=',', quotechar='"')
for (title, url) in content:
# driver.get('https://www.skillshare.com/classes/Sketchbook-Practice-Bring-watercolour-to-Life-with-Line-Drawing/1053382271/classroom/discuss')
logger.info('Fetching URL[%s]' % url)
driver.get(url)
time.sleep(10)
escaped_title = re.sub(r"[^A-Za-z 0-9]+", '', title).replace(' ', '_')
dirname = 'SkillsShare/' + escaped_title
cmd = 'mkdir -p ' + dirname
logger.info(cmd)
os.system(cmd)
els = driver.find_elements_by_class_name("session-item")
for i, el in enumerate(els):
logger.debug(str(el))
bs = BeautifulSoup(el.get_attribute('innerHTML'), "html.parser")
p = bs.find('p')
name = p.text
name = "%02d" % (i+1) + '_' + re.sub(r"[^A-Za-z 0-9]+", '', name).replace(' ', '_') + '.mp4'
logger.info(str(p) + name)
el.click()
time.sleep(10)
html_source = driver.page_source
bs = BeautifulSoup(html_source, "html.parser")
html = bs.findAll('video', attrs={'class':['vjs-tech']})
str_html = str(html)
logger.info(str_html)
url = str_html[str_html.find("src=")+5:]
fetch_url = url[:url.find("?pubId")]
logger.info(fetch_url)
if os.path.exists(dirname + '/' + name):
continue
cmd = 'cd %s && curl -s %s -o %s' % (dirname, fetch_url, name)
logger.info(cmd)
# os.system(cmd)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
if args['enumerate']:
myFPSShops=FPSShop.objects.all()
for eachFPSShop in myFPSShops:
startYear=2016
now = datetime.now()
endYear=now.year
yearArray=list(range(startYear,endYear+1))
for eachYear in yearArray:
if (eachYear == now.year):
maxMonth=now.month
else:
maxMonth=12
eachMonth=0
while eachMonth < maxMonth:
eachMonth=eachMonth+1
logger.info("%d-%d" % (eachMonth,eachYear))
myShop=FPSStatus.objects.filter(fpsShop=eachFPSShop,fpsMonth=eachMonth,fpsYear=eachYear).first()
if myShop is None:
FPSStatus.objects.create(fpsShop=eachFPSShop,fpsMonth=eachMonth,fpsYear=eachYear)
logger.info("Created object")
myShop=FPSStatus.objects.filter(fpsShop=eachFPSShop,fpsMonth=eachMonth,fpsYear=eachYear).first()
myVillages=FPSVillage.objects.filter(fpsShop=eachFPSShop)
for eachVillage in myVillages:
myVillageFPSStatus=VillageFPSStatus.objects.filter(fpsVillage=eachVillage,fpsStatus=myShop).first()
if myVillageFPSStatus is None:
VillageFPSStatus.objects.create(fpsVillage=eachVillage,fpsStatus=myShop)
if args['crawl']:
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
#Start Program here
base_url = "http://sfc.bihar.gov.in/"
verificationErrors = []
accept_next_alert = True
driver.get("http://sfc.bihar.gov.in/login.htm")
driver.get(base_url + "/fpshopsSummaryDetails.htm")
# Select(driver.find_element_by_id("year")).select_by_visible_text(inyear)
# time.sleep(10)
myBlocks=Block.objects.filter(fpsRequired=True)
myBlocks=Block.objects.filter(fpsRequired=True)
for eachBlock in myBlocks:
logger.info("District Name: %s Block Name: %s " % (eachBlock.name,eachBlock.district.name))
districtCode=eachBlock.district.fpsCode
blockCode=eachBlock.fpsCode
Select(driver.find_element_by_id("district_id")).select_by_value(districtCode)
time.sleep(10)
Select(driver.find_element_by_id("block_id")).select_by_value(blockCode)
time.sleep(10)
fps_box = driver.find_element_by_id("fpshop_id") # if your select_box has a name.. why use xpath?..... this step could use either xpath or name, but name is sooo much easier.
fpsOptions = [z for z in fps_box.find_elements_by_tag_name("option")] #this part is cool, because it searches the elements contained inside of select_box and then adds them to the list options if they have the tag name "options"
for fpsElement in fpsOptions:
fpsCode=fpsElement.get_attribute("value") #
fpsName=fpsElement.get_attribute("text") #
logger.info("fpsCode: %s, fpsName: %s " % (fpsCode,fpsName))
myFPSShop=FPSShop.objects.filter(fpsCode=fpsCode).first()
if myFPSShop is None:
FPSShop.objects.create(fpsCode=fpsCode,name=fpsName,block=eachBlock)
#
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
exit(0)
def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(0)
driver = driverInitialize()
'''
content = csv.reader(open('./gats.csv', 'r'), delimiter=',', quotechar='"')
for (gat, d) in content:
'''
for gat in gat_list:
logger.info('Fetching gat[%s]...' % gat)
driver.get(url)
try:
driver.find_element_by_xpath("//form[@id='aspnetForm']/div[3]/div/div/div[3]/a[3]/p").click()
except:
logger.error('Cant find element for [%s]' % gat)
continue
Select(driver.find_element_by_id("distSelect")).select_by_visible_text(dn)
Select(driver.find_element_by_id("talSelect")).select_by_visible_text(tn)
Select(driver.find_element_by_id("vilSelect")).select_by_visible_text(vn)
# Select(driver.find_element_by_id("vilSelect")).select_by_visible_text(u"सार्पिली")
# driver.find_element_by_css_selector("option[value=\"string:273200030399810000\"]").click()
driver.find_element_by_id("rbsryno").click()
driver.find_element_by_xpath("//input[@type='number']").clear()
driver.find_element_by_xpath("//input[@type='number']").send_keys(gat)
driver.find_element_by_css_selector("input[type=\"button\"]").click()
'''
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
try:
WebDriverWait(driver, 5).until(EC.alert_is_present(), 'Waiting for alert timed out')
alert = driver.switch_to_alert()
alert.accept()
logger.warning("alert accepted")
except:
logger.info("Yippie!")
'''
if len(driver.window_handles) > 1:
logger.info("Dialog Box Window [" + str(driver.window_handles) + "]")
# self.assertEqual(u"सर्वे नंबर / गट नंबर तपासुन पहा.", self.close_alert_and_get_its_text())
# driver.find_element_by_xpath("//div[@id='block-desktop']/div[3]/div[2]/div").click()
driver.switch_to_alert().accept()
continue
html_source = driver.page_source.replace('<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
logger.debug("HTML Fetched [%s]" % html_source)
soup = BeautifulSoup(driver.page_source, "html.parser")
#dict_from_json = soup.find(attribute).text
sno_select = soup.find("select", {"ng-model" : "selectedSno"}) # ng-model="selectedSno"
sno_options = sno_select.findAll("option")
snos = [ sno_option.text for sno_option in sno_options ]
logger.debug("Found [%s]" % str(snos))
snos = snos[1:]
logger.info("SNO List [%s]" % str(snos))
#time.sleep(5)
for sno in snos:
logger.info('Processing [%s]' % sno)
filename = '/home/mayank/wd/SaatBaara/7-12-mahabhulekh/%s.html' % sno.replace('/','_')
if os.path.exists(filename):
#time.sleep(1)
continue
Select(driver.find_element_by_xpath("//form[@id='aspnetForm']/div[3]/div/div/div[3]/div/div[3]/table/tbody/tr[3]/td/select")).select_by_visible_text(sno)
#logger.info(driver.find_element_by_link_text(sno))
driver.find_element_by_css_selector("td.last-rows > input[type=\"button\"]").click()
time.sleep(5)
parent_handle = driver.current_window_handle
logger.info("Handles : %s Number : %s" % (driver.window_handles, len(driver.window_handles)))
if len(driver.window_handles) == 2:
driver.switch_to_window(driver.window_handles[-1])
else:
logger.error("Handlers gone wrong [" + str(driver.window_handles) + "]")
driver.save_screenshot('z.png')
html_source = driver.page_source.replace('<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>').encode('utf-8')
logger.debug("HTML Fetched [%s]" % html_source)
if(driver.title != '७/१२'):
logger.error(driver.title)
driver.close()
driver.switch_to_window(parent_handle)
continue
bs = BeautifulSoup(html_source, "html.parser")
body = bs.find('tbody')
try:
body = body.findNext('tbody')
except:
logger.error('Empty body for [%s]' % sno)
driver.close()
driver.switch_to_window(parent_handle)
continue
body = body.findNext('tbody')
logger.debug(body)
td = body.find('td')
td = td.findAll('td')
logger.info("Checking [%s]" % td[2].text)
if(sno != td[2].text):
logger.error('sno[%s] != td.text[%s]' % (sno, td[2].text))
driver.close()
driver.switch_to_window(parent_handle)
continue
with open(filename, 'wb') as html_file:
logger.info('Writing [%s]' % filename)
html_file.write(html_source)
driver.close()
driver.switch_to_window(parent_handle)
time.sleep(1)
time.sleep(1)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
if args['limit']:
limit = int(args['limit'])
else:
limit =1
myVillages=Village.objects.all()[:limit]
for eachVillage in myVillages:
logger.info(eachVillage.name)
stateName=eachVillage.panchayat.block.district.state.name
districtName=eachVillage.panchayat.block.district.name
blockName=eachVillage.panchayat.block.name
panchayatName=eachVillage.panchayat.name
villageName=eachVillage.name
eachPanchayat=eachVillage.panchayat
url="http://www.nrega.telangana.gov.in/Nregs/FrontServlet?requestType=SmartCardreport_engRH&actionVal=MobnumberStatus&id=%s&Retype=null&type=null&file=%s" % (eachVillage.tcode,eachVillage.name)
logger.info(url)
try:
driver.get(url)
driver.get(url)
myhtml = driver.page_source
error=0
except:
error=1
if error==0:
logger.info("No Error")
error1,myTable=validateWorkerList(myhtml)
if error1 is None:
logger.info("Worker List found")
outhtml=''
outcsv=''
outhtml+=stripTableAttributes(myTable,"myTable")
outcsv+=table2csv(myTable)
title="WorkerList state:%s District:%s block:%s panchayat: %s vilage:%s " % (stateName,districtName,blockName,panchayatName,villageName)
outhtml=htmlWrapperLocal(title=title, head='<h1 aling="center">'+title+'</h1>', body=outhtml)
try:
outhtml=outhtml.encode("UTF-8")
except:
outhtml=outhtml
try:
outcsv=outcsv.encode("UTF-8")
except:
outcsv=outcsv
filename=eachVillage.slug+"_tjr.html"
filenamecsv=eachVillage.slug+"_tjr.csv"
finyear=getCurrentFinYear()
reportType="telJobcardRegisterHTML"
saveVillageReport(logger,eachVillage,finyear,reportType,filename,outhtml)
reportType="telJobcardRegisterCSV"
saveVillageReport(logger,eachVillage,finyear,reportType,filenamecsv,outcsv)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
exit(0)
def fetchMusterDetails(logger, db, cmd=None, directory=None, url=None, is_parse_info=None, is_push_info=None, is_visible=None):
'''
Fetch the Muster Details for specified parameters in the specified directory
'''
if not cmd:
cmd="FETCH MUSTER DETAILS"
logger.info("BEGIN %s..." % cmd)
if not directory:
directory = "./Downloads"
if not url:
url = 'http://khadya.cg.nic.in/pdsonline/cgfsa/Report/SSRS_Reports/RptMonthWiseDeleteRestoreNew_RC.aspx'
url = 'http://164.100.112.66/netnrega/Citizen_html/Musternew.aspx?id=2&lflag=eng&ExeL=GP&fin_year=2015-2016&state_code=33&district_code=3305&block_code=3305007&panchayat_code=3305007038&State_name=CHHATTISGARH&District_name=SURGUJA&Block_name=BATAULI&panchayat_name=Govindpur'
if not is_visible:
is_visible = 0 # Set to 1 for debugging selenium
if not is_parse_info:
is_parse_info = False
if not is_push_info:
is_push_info = False
# The part below could be moved to a function downloadMusterDetails() to make it reusable
filename = directory + '/' + 'test.html' # Use your naming logic + blockName + '_' + panchayat + '_' + shopCode + '.html'
logger.info('filename[%s]' % filename)
filepath = os.path.dirname(filename)
if not os.path.exists(filepath):
logger.info('Creating direcotry [%s] as it does not exist' % filepath)
os.makedirs(filepath)
display = displayInitialize(is_visible)
driver = driverInitialize()
logger.error("Current URL [%s] Title [%s]" % (driver.current_url, driver.title))
# cookieDump(driver)
# driver.delete_all_cookies()
logger.error("Current URL [%s] Title [%s]" % (driver.current_url, driver.title))
logger.info("Fetching...[%s]" % url)
driver.get(url)
logger.error("Current URL [%s] Title [%s]" % (driver.current_url, driver.title))
# cookieDump(driver)
# Use double refresh if need be like in AP sites
if False:
logger.info("Refreshing...[%s]" % url)
driver.get(url) # A double refresh required for the page to load
logger.error("Current URL [%s] Title [%s]" % (driver.current_url, driver.title))
# cookieDump(driver)
el = waitUntilID(logger, driver, 'ctl00_ContentPlaceHolder1_ddlwork', 10)
if el:
#el = driver.find_element_by_id('ctl00_ContentPlaceHolder1_ddlwork')
logger.info("Found El[%s]" % str(el))
html_source = driver.page_source.replace('<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
logger.debug("HTML Fetched [%s]" % html_source)
# cookieDump(driver)
with open(filename, "wb") as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(html_source.encode('UTF-8'))
else:
logger.error("Failed to fetch the page [%s]" % driver.current_url)
logger.error("Current URL [%s] Title [%s]" % (driver.current_url, driver.title))
# cookieDump(driver)
html_source = driver.page_source
logger.info("HTML Fetched [%s]" % html_source)
with open(filename, "wb") as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(html_source.encode('UTF-8'))
driverFinalize(driver)
displayFinalize(display)
return # Error condition to be dealt with
'''
try:
logger.info("Waiting for the page to load...")
elem = WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.ID, 'ctl00_ContentPlaceHolder1_ddlwork'))
)
logger.info("...done looking")
except (NoSuchElementException, TimeoutException):
logger.error("Failed to fetch the page")
driverFinalize(driver)
displayFinalize(display)
return # Error condition to be dealt with
finally:
html_source = driver.page_source.replace('<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
logger.debug("HTML Fetched [%s]" % html_source)
with open(filename, "wb") as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(html_source.encode('UTF-8'))
'''
# If you have information to parse using Beautiful Soup
if is_parse_info:
bs = BeautifulSoup(html_source, "html.parser")
tr_list = bs.findAll('tr', attrs={'class':['normalRow', 'alternateRow']})
logger.debug(str(tr_list))
for tr in tr_list:
td = tr.find('td')
td = td.findNext('td')
panchayat = td.text.strip()
logger.info("Panchayat[%s]", panchayat)
elem = driver.find_element_by_link_text(panchayat)
elem.click()
filename="/tmp/%s.html" % panchayat
with open(filename, 'w') as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(driver.page_source)
driver.back()
driverFinalize(driver)
displayFinalize(display)
# If you want to push the information to the Database
if is_push_info:
query = 'select j.jobcard, p.name, p.panchayatCode from jobcardRegister j, panchayats p, blocks b where j.blockCode=p.blockCode and j.panchayatCode=p.panchayatCode and j.blockCode=b.blockCode and j.jobcard="%s"' % jobcard
logger.info("Command[%s] Directory[%s] URL[%s] jobcard[%s]" % (cmd, dir, url, jobcard))
pushInfoIntoDB(logger, db, "POPULATE_DATABASE", dir, url, is_visible, is_push_info, query) # So that function can be shared
logger.info("...END %s" % cmd)
def runTestSuite():
logger = loggerFetch("info")
logger.info("BEGIN PROCESSING...")
display = displayInitialize(1)
driver = driverInitialize()
'''
content = csv.reader(open('./gats.csv', 'r'), delimiter=',', quotechar='"')
for (gat, d) in content:
'''
for gat in gat_list:
logger.info('Fetching gat[%s]...' % gat)
driver.get(url)
try:
driver.find_element_by_xpath(
"//form[@id='aspnetForm']/div[3]/div/div/div[3]/a[3]/p").click(
)
except:
logger.error('Cant find element for [%s]' % gat)
continue
Select(
driver.find_element_by_id("distSelect")).select_by_visible_text(dn)
Select(
driver.find_element_by_id("talSelect")).select_by_visible_text(tn)
Select(
driver.find_element_by_id("vilSelect")).select_by_visible_text(vn)
# Select(driver.find_element_by_id("vilSelect")).select_by_visible_text(u"सार्पिली")
# driver.find_element_by_css_selector("option[value=\"string:273200030399810000\"]").click()
driver.find_element_by_id("rbsryno").click()
driver.find_element_by_xpath("//input[@type='number']").clear()
driver.find_element_by_xpath("//input[@type='number']").send_keys(gat)
driver.find_element_by_css_selector("input[type=\"button\"]").click()
'''
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
try:
WebDriverWait(driver, 5).until(EC.alert_is_present(), 'Waiting for alert timed out')
alert = driver.switch_to_alert()
alert.accept()
logger.warning("alert accepted")
except:
logger.info("Yippie!")
'''
if len(driver.window_handles) > 1:
logger.info("Dialog Box Window [" + str(driver.window_handles) +
"]")
# self.assertEqual(u"सर्वे नंबर / गट नंबर तपासुन पहा.", self.close_alert_and_get_its_text())
# driver.find_element_by_xpath("//div[@id='block-desktop']/div[3]/div[2]/div").click()
driver.switch_to_alert().accept()
continue
html_source = driver.page_source.replace(
'<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
)
logger.debug("HTML Fetched [%s]" % html_source)
soup = BeautifulSoup(driver.page_source, "html.parser")
#dict_from_json = soup.find(attribute).text
sno_select = soup.find(
"select", {"ng-model": "selectedSno"}) # ng-model="selectedSno"
sno_options = sno_select.findAll("option")
snos = [sno_option.text for sno_option in sno_options]
logger.debug("Found [%s]" % str(snos))
snos = snos[1:]
logger.info("SNO List [%s]" % str(snos))
#time.sleep(5)
for sno in snos:
logger.info('Processing [%s]' % sno)
filename = '/home/mayank/wd/SaatBaara/remaining/%s.html' % sno.replace(
'/', '_')
if os.path.exists(filename):
#time.sleep(1)
continue
Select(
driver.find_element_by_xpath(
"//form[@id='aspnetForm']/div[3]/div/div/div[3]/div/div[3]/table/tbody/tr[3]/td/select"
)).select_by_visible_text(sno)
#logger.info(driver.find_element_by_link_text(sno))
driver.find_element_by_css_selector(
"td.last-rows > input[type=\"button\"]").click()
time.sleep(5)
parent_handle = driver.current_window_handle
logger.info("Handles : %s Number : %s" %
(driver.window_handles, len(driver.window_handles)))
if len(driver.window_handles) == 2:
driver.switch_to_window(driver.window_handles[-1])
else:
logger.error("Handlers gone wrong [" +
str(driver.window_handles) + "]")
driver.save_screenshot('z.png')
html_source = driver.page_source.replace(
'<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
).encode('utf-8')
logger.debug("HTML Fetched [%s]" % html_source)
if (driver.title != '७/१२'):
logger.error(driver.title)
driver.close()
driver.switch_to_window(parent_handle)
continue
bs = BeautifulSoup(html_source, "html.parser")
body = bs.find('tbody')
try:
body = body.findNext('tbody')
except:
logger.error('Empty body for [%s]' % sno)
driver.close()
driver.switch_to_window(parent_handle)
continue
body = body.findNext('tbody')
logger.debug(body)
td = body.find('td')
td = td.findAll('td')
logger.info("Checking [%s]" % td[2].text)
if (sno != td[2].text):
logger.error('sno[%s] != td.text[%s]' % (sno, td[2].text))
driver.close()
driver.switch_to_window(parent_handle)
continue
with open(filename, 'wb') as html_file:
logger.info('Writing [%s]' % filename)
html_file.write(html_source)
driver.close()
driver.switch_to_window(parent_handle)
time.sleep(1)
time.sleep(1)
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
districtName=args['district']
logger.info("DistrictName "+districtName)
limitString=''
if args['limit']:
limitString=" limit %s " % args['limit']
db = dbInitialize(db=districtName.lower(), charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
additionalFilters = ''
if args['blockCode']:
additionalFilters=" and b.blockCode='%s' " % args['blockCode']
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
crawlIP,stateName,stateCode,stateShortCode,districtCode=getDistrictParams(cur,districtName)
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
jobcardPrefix="%s-%s" % (stateShortCode,districtCode)
logger.info("crawlIP "+crawlIP)
logger.info("State Name "+stateName)
jcReportFilePath=nregaDir.replace("districtName",districtName.lower())+districtName.upper()+"/"
jcReportRawFilePath=nregaRawDir.replace("districtName",districtName.lower())+districtName.upper()+"/"
#Start Program here
url="http://nrega.nic.in/netnrega/sthome.aspx"
driver.get(url)
elem = driver.find_element_by_link_text(stateName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
elem = driver.find_element_by_link_text(districtName.upper())
elem.send_keys(Keys.RETURN)
time.sleep(1)
#Query to get all the blocks
query="select b.blockCode,b.name,p.panchayatCode,p.name from blocks b,panchayats p where b.blockCode=p.blockCode and p.isRequired=1 and jobcardCrawlDate is not NULL order by jobcardDownloadDate %s %s" % (additionalFilters,limitString)
cur.execute(query)
results = cur.fetchall()
for row in results:
blockCode=row[0]
blockName=row[1]
panchayatCode=row[2]
panchayatName=row[3]
panchayatNameOnlyLetters=re.sub(r"[^A-Za-z]+", '', panchayatName)
elem = driver.find_element_by_link_text(blockName)
elem.send_keys(Keys.RETURN)
elem = driver.find_element_by_link_text(panchayatName)
elem.send_keys(Keys.RETURN)
elem = driver.find_element_by_link_text("List of Worker with Aadhar No.(UID No.)")
elem.send_keys(Keys.RETURN)
time.sleep(15)
query="update panchayats set jobcardDownloadDate=now() where blockCode='%s' and panchayatCode='%s' " % (blockCode,panchayatCode)
cur.execute(query)
jcsource = driver.page_source
driver.back()
time.sleep(5)
driver.back()
time.sleep(5)
driver.back()
rawhtml=jcsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
jcfilename=jcReportRawFilePath+blockName.upper()+"/"+panchayatNameOnlyLetters.upper()+"/jobcardRegister/workerList.html"
logger.info(jcfilename)
writeFile(jcfilename,rawhtml)
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def fetchMusterDetails(logger,
db,
cmd=None,
directory=None,
url=None,
is_parse_info=None,
is_push_info=None,
is_visible=None):
'''
Fetch the Muster Details for specified parameters in the specified directory
'''
if not cmd:
cmd = "FETCH MUSTER DETAILS"
logger.info("BEGIN %s..." % cmd)
if not directory:
directory = "./Downloads"
if not url:
url = 'http://khadya.cg.nic.in/pdsonline/cgfsa/Report/SSRS_Reports/RptMonthWiseDeleteRestoreNew_RC.aspx'
url = 'http://164.100.112.66/netnrega/Citizen_html/Musternew.aspx?id=2&lflag=eng&ExeL=GP&fin_year=2015-2016&state_code=33&district_code=3305&block_code=3305007&panchayat_code=3305007038&State_name=CHHATTISGARH&District_name=SURGUJA&Block_name=BATAULI&panchayat_name=Govindpur'
if not is_visible:
is_visible = 0 # Set to 1 for debugging selenium
if not is_parse_info:
is_parse_info = False
if not is_push_info:
is_push_info = False
# The part below could be moved to a function downloadMusterDetails() to make it reusable
filename = directory + '/' + 'test.html' # Use your naming logic + blockName + '_' + panchayat + '_' + shopCode + '.html'
logger.info('filename[%s]' % filename)
filepath = os.path.dirname(filename)
if not os.path.exists(filepath):
logger.info('Creating direcotry [%s] as it does not exist' % filepath)
os.makedirs(filepath)
display = displayInitialize(is_visible)
driver = driverInitialize()
logger.error("Current URL [%s] Title [%s]" %
(driver.current_url, driver.title))
# cookieDump(driver)
# driver.delete_all_cookies()
logger.error("Current URL [%s] Title [%s]" %
(driver.current_url, driver.title))
logger.info("Fetching...[%s]" % url)
driver.get(url)
logger.error("Current URL [%s] Title [%s]" %
(driver.current_url, driver.title))
# cookieDump(driver)
# Use double refresh if need be like in AP sites
if False:
logger.info("Refreshing...[%s]" % url)
driver.get(url) # A double refresh required for the page to load
logger.error("Current URL [%s] Title [%s]" %
(driver.current_url, driver.title))
# cookieDump(driver)
el = waitUntilID(logger, driver, 'ctl00_ContentPlaceHolder1_ddlwork', 10)
if el:
#el = driver.find_element_by_id('ctl00_ContentPlaceHolder1_ddlwork')
logger.info("Found El[%s]" % str(el))
html_source = driver.page_source.replace(
'<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>'
)
logger.debug("HTML Fetched [%s]" % html_source)
# cookieDump(driver)
with open(filename, "wb") as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(html_source.encode('UTF-8'))
else:
logger.error("Failed to fetch the page [%s]" % driver.current_url)
logger.error("Current URL [%s] Title [%s]" %
(driver.current_url, driver.title))
# cookieDump(driver)
html_source = driver.page_source
logger.info("HTML Fetched [%s]" % html_source)
with open(filename, "wb") as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(html_source.encode('UTF-8'))
driverFinalize(driver)
displayFinalize(display)
return # Error condition to be dealt with
'''
try:
logger.info("Waiting for the page to load...")
elem = WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.ID, 'ctl00_ContentPlaceHolder1_ddlwork'))
)
logger.info("...done looking")
except (NoSuchElementException, TimeoutException):
logger.error("Failed to fetch the page")
driverFinalize(driver)
displayFinalize(display)
return # Error condition to be dealt with
finally:
html_source = driver.page_source.replace('<head>',
'<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
logger.debug("HTML Fetched [%s]" % html_source)
with open(filename, "wb") as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(html_source.encode('UTF-8'))
'''
# If you have information to parse using Beautiful Soup
if is_parse_info:
bs = BeautifulSoup(html_source, "html.parser")
tr_list = bs.findAll('tr',
attrs={'class': ['normalRow', 'alternateRow']})
logger.debug(str(tr_list))
for tr in tr_list:
td = tr.find('td')
td = td.findNext('td')
panchayat = td.text.strip()
logger.info("Panchayat[%s]", panchayat)
elem = driver.find_element_by_link_text(panchayat)
elem.click()
filename = "/tmp/%s.html" % panchayat
with open(filename, 'w') as html_file:
logger.info("Writing [%s]" % filename)
html_file.write(driver.page_source)
driver.back()
driverFinalize(driver)
displayFinalize(display)
# If you want to push the information to the Database
if is_push_info:
query = 'select j.jobcard, p.name, p.panchayatCode from jobcardRegister j, panchayats p, blocks b where j.blockCode=p.blockCode and j.panchayatCode=p.panchayatCode and j.blockCode=b.blockCode and j.jobcard="%s"' % jobcard
logger.info("Command[%s] Directory[%s] URL[%s] jobcard[%s]" %
(cmd, dir, url, jobcard))
pushInfoIntoDB(logger, db, "POPULATE_DATABASE", dir, url, is_visible,
is_push_info, query) # So that function can be shared
logger.info("...END %s" % cmd)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
districtName=args['district']
logger.info("DistrictName "+districtName)
limitString=''
if args['limit']:
limitString=" limit %s " % args['limit']
db = dbInitialize(db=districtName.lower(), charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
jobcardPrefix="%s-%s" % (stateShortCode,districtCode)
logger.info("crawlIP "+crawlIP)
logger.info("State Name "+stateName)
jcReportFilePath=nregaDownloadsDir.replace("districtName",districtName.lower())+districtName.upper()+"/"
jcReportRawFilePath=nregaRawDownloadsDir.replace("districtName",districtName.lower())+districtName.upper()+"/"
#Start Program here
url="http://nrega.nic.in/netnrega/sthome.aspx"
driver.get(url)
elem = driver.find_element_by_link_text(stateName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
elem = driver.find_element_by_link_text(districtName.upper())
elem.send_keys(Keys.RETURN)
time.sleep(1)
#Query to get all the blocks
query="select b.blockCode,b.name,p.panchayatCode,p.name from blocks b,panchayats p where b.blockCode=p.blockCode and p.isRequired=1 order by jobcardCrawlDate %s" % (limitString)
cur.execute(query)
results = cur.fetchall()
for row in results:
blockCode=row[0]
blockName=row[1]
panchayatCode=row[2]
panchayatName=row[3]
elem = driver.find_element_by_link_text(blockName)
elem.send_keys(Keys.RETURN)
elem = driver.find_element_by_link_text(panchayatName)
elem.send_keys(Keys.RETURN)
elem = driver.find_element_by_link_text("Job card/Employment Register")
elem.send_keys(Keys.RETURN)
time.sleep(5)
query="update panchayats set jobcardCrawlDate=now() where blockCode='%s' and panchayatCode='%s' " % (blockCode,panchayatCode)
cur.execute(query)
query="select jobcard from jobcardRegister where isDownloaded=0 and stateCode='"+stateCode+"' and districtCode='"+districtCode+"' and blockCode='"+blockCode+"' and panchayatCode='"+panchayatCode+"' limit 50"
cur.execute(query)
jcresults = cur.fetchall()
for jcrow in jcresults:
jobcard=jcrow[0]
logger.info("blockName %s panchayatName: %s jobcard: %s" % (blockName,panchayatName,jobcard) )
elem = driver.find_element_by_link_text(jobcard)
elem.send_keys(Keys.RETURN)
jcsource = driver.page_source
driver.back()
rawhtml=jcsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
jcfilename=jcReportRawFilePath+blockName.upper()+"/"+panchayatName.upper()+"/jobcardRegister/"+jobcard.replace("/","_")+".html"
logger.info(jcfilename)
writeFile(jcfilename,rawhtml)
category,isBPL=getCategoryBPL(rawhtml)
logger.info("Category : %s " % category)
logger.info("isBPL : %s " % isBPL)
htmlSoup=BeautifulSoup(rawhtml,"lxml")
myhtml=''
myhtml+=getSpans(htmlSoup,rawhtml)
myhtml+=rewriteTable(htmlSoup,"Family Details","GridView4")
myhtml+=rewriteTable(htmlSoup,"Requested Period of Employment","GridView1")
myhtml+=rewriteTable(htmlSoup,"Period and Work on which Employment Offered","GridView2")
myhtml+=rewriteTable(htmlSoup,"Period and Work on which Employment Given","GridView3")
myhtml=htmlWrapperLocal(title="Jobcard Details", head='<h1 aling="center">'+jobcard+'</h1>', body=myhtml)
jcfilename=jcReportFilePath+blockName.upper()+"/"+panchayatName.upper()+"/jobcardRegister/"+jobcard.replace("/","_")+".html"
logger.info(jcfilename)
writeFile(jcfilename,myhtml)
query="update jobcardRegister set isDownloaded=1 where jobcard='"+jobcard+"'"
cur.execute(query)
# if not os.path.exists(os.path.dirname(jcfilename)):
# os.makedirs(os.path.dirname(jcfilename))
# myfile = open(jcfilename, "w")
# myfile.write(myhtml.encode("UTF-8"))
# query="update jobcardRegister set isDownloaded=1 where jobcard='"+jobcard+"'"
# cur.execute(query)
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def setUp(self):
self.logger = loggerFetch('info')
self.logger.info('BEGIN PROCESSING...')
self.display = displayInitialize(1)
self.driver = driverInitialize(path='/opt/firefox/', timeout=3)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
limitString=''
if args['limit']:
limitString=" limit %s " % args['limit']
additionalFilters=''
if args['district']:
additionalFilters+= " and p.districtName='%s' " % args['district']
db = dbInitialize(db=nregaDB, charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
url="http://nrega.nic.in/netnrega/sthome.aspx"
driver.get(url)
query="select p.stateCode,p.districtCode,p.blockCode,p.panchayatCode,p.stateName,p.districtName,p.rawBlockName,p.panchayatName,p.fullPanchayatCode,p.stateShortCode,p.crawlIP from panchayats p,panchayatStatus ps where p.fullPanchayatCode=ps.fullPanchayatCode and p.isRequired=1 and ( (TIMESTAMPDIFF(DAY, ps.jobcardCrawlDate, now()) > 7) or ps.jobcardCrawlDate is NULL) %s order by ps.jobcardCrawlDate,fullPanchayatCode %s" % (additionalFilters,limitString)
cur.execute(query)
results=cur.fetchall()
for row in results:
[stateCode,districtCode,blockCode,panchayatCode,stateName,districtName,blockName,panchayatName,fullPanchayatCode,stateShortCode,crawlIP]=row
filepath=nregaWebDir.replace("stateName",stateName.upper()).replace("districtName",districtName.upper())
filename=filepath+blockName.upper()+"/%s/%s_jobcardRegister.html" % (panchayatName.upper(),panchayatName.upper())
logger.info(filename)
jobcardPrefix="%s-" % (stateShortCode)
logger.info("Processing %s-%s-%s-%s " % (stateName,districtName,blockName,panchayatName))
elem = driver.find_element_by_link_text(stateName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
elem = driver.find_element_by_link_text(districtName.upper())
elem.send_keys(Keys.RETURN)
time.sleep(1)
elem = driver.find_element_by_link_text(blockName)
elem.send_keys(Keys.RETURN)
time.sleep(1)
compareText="Panchayat_Code=%s" % fullPanchayatCode
elems = driver.find_elements_by_xpath("//a[@href]")
foundCode=0
for elem in elems:
hrefLink=str(elem.get_attribute("href"))
if compareText in hrefLink:
logger.info("Found the Code")
foundCode=1
break
#elem = driver.find_element_by_link_text(panchayatName)
if foundCode==1:
elem.send_keys(Keys.RETURN)
time.sleep(1)
#Before thsi lets download the applicatn Register:
elem = driver.find_element_by_link_text("Registration Application Register")
elem.send_keys(Keys.RETURN)
time.sleep(5)
html_source = driver.page_source
#filename="%s/%s.html" % (tempDir,panchayatName)
writeFile(filename,html_source)
driver.back()
elem = driver.find_element_by_link_text("Download Panchayatwise MGNREGA Bank A/C Detail")
elem.send_keys(Keys.RETURN)
time.sleep(15)
jcsource = driver.page_source
rawhtml=jcsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
filename=filepath+blockName.upper()+"/%s/%s_bankAccounts.html" % (panchayatName.upper(),panchayatName.upper())
writeFile(filename,rawhtml)
driver.back()
elem = driver.find_element_by_link_text("Download Panchayatwise MGNREGA Post Office Account Detail")
elem.send_keys(Keys.RETURN)
time.sleep(15)
jcsource = driver.page_source
rawhtml=jcsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
filename=filepath+blockName.upper()+"/%s/%s_postAccounts.html" % (panchayatName.upper(),panchayatName.upper())
writeFile(filename,rawhtml)
driver.back()
elem = driver.find_element_by_link_text("Download Panchayat Wise MGNREGA Co-operative Bank A/C Detail")
elem.send_keys(Keys.RETURN)
time.sleep(15)
jcsource = driver.page_source
rawhtml=jcsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
filename=filepath+blockName.upper()+"/%s/%s_cobankAccounts.html" % (panchayatName.upper(),panchayatName.upper())
writeFile(filename,rawhtml)
driver.back()
elem = driver.find_element_by_link_text("Job card/Employment Register")
elem.send_keys(Keys.RETURN)
time.sleep(5)
curtime = time.strftime('%Y-%m-%d %H:%M:%S')
html_source = driver.page_source
htmlsoup=BeautifulSoup(html_source,"html.parser")
try:
table=htmlsoup.find('table',align="center")
rows = table.findAll('tr')
status=1
except:
status=0
query="update panchayatStatus set jobcardCrawlDate=NOW() where fullPanchayatCode='%s'"%fullPanchayatCode
logger.info(query)
cur.execute(query)
logger.info("Status is " + str(status))
if status==1:
for tr in rows:
cols = tr.findAll('td')
jclink=''
for link in tr.find_all('a'):
jclink=link.get('href')
if len(cols) > 2:
jcno="".join(cols[1].text.split())
headOfFamily=cols[2].text.replace("'","").lstrip().rstrip()
logger.info("%s-%s" % (jcno,jobcardPrefix))
if jobcardPrefix in jcno:
logger.info(jcno)
jcNumber=getjcNumber(jcno)
query="select * from jobcards where jobcard='%s' " % jcno
cur.execute(query)
if cur.rowcount == 0:
query="insert into jobcards (name,jobcard,stateCode,districtCode,blockCode,panchayatCode,fullPanchayatCode) values ('"+headOfFamily+"','"+jcno+"','"+stateCode+"','"+districtCode+"','"+blockCode+"','"+panchayatCode+"',"+fullPanchayatCode+")"
logger.info(query)
cur.execute(query)
driver.back()
driver.back()
driver.back()
driver.back()
driver.back()
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
if args['limit']:
limit = int(args['limit'])
else:
limit =1
nicBlockCode=args["nicBlockCode"]
myBlock=Block.objects.filter(code=nicBlockCode).first()
blockCode=myBlock.tcode
blockName=myBlock.name
url="http://www.nrega.telangana.gov.in/Nregs/FrontServlet?requestType=SmartCardreport_engRH&actionVal=MobnumberStatus&id=%s&Retype=null&type=null&file=%s" % (blockCode,blockName)
logger.info(url)
try:
driver.get(url)
driver.get(url)
myhtml = driver.page_source
error=0
except:
error=1
if error==0:
logger.info("No Error")
# dom = lxml.html.fromstring(myhtml)
# for link in dom.xpath('//a/@href'): # select the url in href for all a tags(links)
# print(link)
htmlsoup=BeautifulSoup(myhtml,"html.parser")
table=htmlsoup.find('table',id="sortable")
if table is not None:
print("Found")
for link in table.find_all('a'):
logger.info(link['href'])
panchayatLink="http://www.nrega.telangana.gov.in"+link['href']
myArray=panchayatLink.split("file=")
panchayatName=myArray[1]
logger.info(panchayatName+panchayatLink)
myPanchayat=Panchayat.objects.filter(block=myBlock,name=panchayatName).first()
if myPanchayat is not None:
try:
driver.get(panchayatLink)
driver.get(panchayatLink)
phtml = driver.page_source
perror=0
except:
perror=1
if perror==0:
logger.info("No Error")
phtmlsoup=BeautifulSoup(phtml,"html.parser")
ptable=phtmlsoup.find('table',id="sortable")
if ptable is not None:
print("Found")
for link in ptable.find_all('a'):
logger.info(link['href'])
villageLink="http://www.nrega.telangana.gov.in"+link['href']
myArray=villageLink.split("file=")
villageName=myArray[1]
par = parse_qs(urlparse(villageLink).query)
villageID=str(par['id'][0]).lstrip().rstrip()
villageName=str(par['file'][0])
logger.info(villageName+villageID)
logger.info(par)
logger.info(len(villageID))
myVillage=Village.objects.filter(tcode=villageID).first()
if myVillage is None:
Village.objects.create(tcode=villageID)
myVillage=Village.objects.filter(tcode=villageID).first()
myVillage.name=villageName
myVillage.code=villageID
myVillage.panchayat=myPanchayat
myVillage.save()
driverFinalize(driver)
displayFinalize(display)
logger.info("...END PROCESSING")
exit(0)
def main():
args = argsFetch()
logger = loggerFetch(args.get('log_level'))
logger.info('args: %s', str(args))
logger.info("BEGIN PROCESSING...")
districtName=args['district']
finyear=args['finyear']
logger.info("DistrictName "+districtName)
limitString=''
if args['limit']:
limitString=" limit %s " % args['limit']
db = dbInitialize(db=districtName.lower(), charset="utf8") # The rest is updated automatically in the function
cur=db.cursor()
db.autocommit(True)
additionalFilters = ''
if args['blockCode']:
additionalFilters=" and b.blockCode='%s' " % args['blockCode']
#Query to set up Database to read Hindi Characters
query="SET NAMES utf8"
cur.execute(query)
crawlIP,stateName,stateCode,stateShortCode,districtCode=getDistrictParams(cur,districtName)
filepath=nregaRawDataDir.replace("districtName",districtName.lower())
fullfinyear=getFullFinYear(finyear)
fullDistrictCode=stateCode+districtCode
display = displayInitialize(args['visible'])
driver = driverInitialize(args['browser'])
url="http://164.100.129.6/netnrega/nregasearch1.aspx"
driver.get(url)
time.sleep(22)
htmlsource = driver.page_source
writeFile("/home/libtech/webroot/nreganic.libtech.info/temp/a.html",htmlsource)
query="select w.id,w.wagelistNo,b.name from wagelists w,blocks b where w.blockCode=b.blockCode and ( (w.isDownloaded=0) or (w.isComplete=0 and TIMESTAMPDIFF(HOUR, w.downloadAttemptDate, now()) > 48 )) and finyear='%s' %s order by w.isDownloaded %s " % (finyear,additionalFilters,limitString)
query="select w.id,w.wagelistNo,b.name from wagelists w,blocks b where w.blockCode=b.blockCode and w.id=1 and finyear='%s' %s order by w.isDownloaded limit 1 " % (finyear,additionalFilters)
logger.info(query)
cur.execute(query)
results=cur.fetchall()
for row in results:
rowid=str(row[0])
wagelistNo=row[1]
blockName=row[2]
logger.info("Same WagelistNo %s " % wagelistNo)
if wagelistNo != '':
# logger.info(wagelistNo)
maintab = driver.current_window_handle
Select(driver.find_element_by_id("ddl_search")).select_by_visible_text("WageList")
driver.find_element_by_css_selector("option[value=\"WageList\"]").click()
Select(driver.find_element_by_id("ddl_state")).select_by_visible_text(stateName.upper())
myvalue='value="%s"' % stateCode
#driver.find_element_by_css_selector("option[value=\"33\"]").click()
driver.find_element_by_css_selector("option[%s]" % myvalue).click()
Select(driver.find_element_by_id("ddl_district")).select_by_visible_text(districtName.upper())
myvalue='value="%s"' % (stateCode+districtCode)
#driver.find_element_by_css_selector("option[value=\"3305\"]").click()
driver.find_element_by_css_selector("option[%s]" % myvalue).click()
driver.find_element_by_id("txt_keyword2").clear()
driver.find_element_by_id("txt_keyword2").send_keys(wagelistNo)
driver.find_element_by_id("btn_go").click()
time.sleep(30)
logger.info("Currently the number of active tabs are %s" % str(len(driver.window_handles)))
if len(driver.window_handles) > 1:
logger.info("There are multiple tabs")
driver.switch_to_window(driver.window_handles[1])
#htmlsource = driver.page_source
#logger.info(htmlsource)
# ERROR: Caught exception [ERROR: Unsupported command [waitForPopUp | | 30000]]
# ERROR: Caught exception [ERROR: Unsupported command [selectWindow | null | ]]
elems = driver.find_elements_by_xpath("//a[@href]")
if len(elems) > 0:
query="select w.id,w.wagelistNo,b.name,b.blockCode from wagelists w,blocks b where w.blockCode=b.blockCode and ( (w.isDownloaded=0) or (w.isComplete=0 and TIMESTAMPDIFF(HOUR, w.downloadAttemptDate, now()) > 48 )) and finyear='%s' %s order by w.isDownloaded %s " % (finyear,additionalFilters,limitString)
cur.execute(query)
results1=cur.fetchall()
for row1 in results1:
rowid=str(row1[0])
wagelistNo=row1[1]
blockName=row1[2]
blockCode=row1[3]
jobcardPrefix="%s-%s-%s-" % (stateShortCode,districtCode,blockCode)
logger.info("Jobcard Prefix : %s " % jobcardPrefix)
fullBlockCode=stateCode+districtCode+blockCode
if wagelistNo != '':
logger.info(wagelistNo)
wurl="http://%s/netnrega/srch_wg_dtl.aspx?state_code=&district_code=%s&state_name=%s&district_name=%s&block_code=%s&wg_no=%s&short_name=%s&fin_year=%s&mode=wg" % (searchIP,fullDistrictCode,stateName.upper(),districtName.upper(),fullBlockCode,wagelistNo,stateShortCode,fullfinyear)
logger.info("URL: %s " % wurl)
driver.get(wurl)
htmlsource = driver.page_source
htmlsource=htmlsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
success=0
isPopulatedString=''
if ("WageList Agency Code" in htmlsource) and (jobcardPrefix in htmlsource):
filename=filepath+blockName.upper()+"/WAGELIST/"+fullfinyear+"/"+wagelistNo+".html"
logger.info(filename)
writeFile("/home/libtech/webroot/nreganic.libtech.info/temp/"+wagelistNo+".html",htmlsource)
writeFile(filename,htmlsource)
success=1
isPopulatedString="isProcessed=0,"
query="update wagelists set isDownloaded=%s,%sdownloadAttemptDate=NOW() where id=%s" %(str(success),isPopulatedString,str(rowid))
logger.info(query)
cur.execute(query)
# elem=driver.find_element_by_link_text(wagelistNo)
# hrefLink=str(elem.get_attribute("href"))
# logger.info(hrefLink)
# driver.get(hrefLink)
# htmlsource = driver.page_source
# htmlsource=htmlsource.replace('<head>','<head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>')
# success=0
# isPopulatedString=''
# if "WageList Agency Code" in htmlsource:
# filename=filepath+blockName.upper()+"/WAGELIST/"+fullfinyear+"/"+wagelistNo+".html"
# logger.info(filename)
# writeFile("/home/libtech/webroot/nreganic.libtech.info/temp/"+wagelistNo+".html",htmlsource)
# writeFile(filename,htmlsource)
# success=1
# isPopulatedString="isProcessed=0,"
# query="update wagelists set isDownloaded=%s,%sdownloadAttemptDate=NOW() where id=%s" %(str(success),isPopulatedString,str(rowid))
# logger.info(query)
# cur.execute(query)
driver.find_element_by_tag_name('body').send_keys(Keys.CONTROL + 'w')
driver.switch_to_window(maintab)
driverFinalize(driver)
displayFinalize(display)
dbFinalize(db) # Make sure you put this if there are other exit paths or errors
logger.info("...END PROCESSING")
exit(0)
def setUp(self):
self.logger = loggerFetch('info')
self.logger.info('BEGIN PROCESSING...')
self.display = displayInitialize(0)
# self.driver = driverInitialize(timeout=3)
self.driver = driverInitialize(timeout=3, options='--headless') # driverInitialize(path='/opt/firefox/', timeout=3)
