def _extract_external_link_requests(self, response, tag, counter):
r = []
siteList = []
ObjectList = dict()
externalSites = []
#uniqueExternalSites=[]
if isinstance(response, HtmlResponse):
tag = 'L'
#linkcount=0
counterValueLink = counter
sites = Selector(response).xpath("//link/@href").extract()
# for site in sites:
# linkcount=linkcount+1
#logging.info('linkcount',linkcount)
#logwr = csv.writer(logFile, delimiter=',',quotechar=' ', quoting=csv.QUOTE_MINIMAL)
for item in sites:
if isinstance(item, unicode):
item = item.encode('utf-8')
siteList.append(item)
else:
siteList.append(item)
sites.append(counterValueLink)
externallinkCount, InternallinkCount, uniqueExternalSites, externalSites, secondlevelurl = _extract_object_count(
siteList)
#wr.writerow(siteList)
linkcount = len(siteList)
#lock.acquire()
# ObjectList['url']=response.url
# ObjectList['counter']=counterValueLink
# ObjectList['linkcount']=linkcount
# ObjectList['InternallinkCount']=InternallinkCount
# ObjectList['ExternallinkCount']=externallinkCount
# #lock.acquire()
# logwr.writerow([ObjectList])
logwr.writerow({
'url': response.url,
'counter': counterValueLink,
'InternallinkCount': InternallinkCount,
'ExternallinkCount': externallinkCount,
'UniqueExternalSites': uniqueExternalSites,
'ExternalSites': externalSites,
'secondlevelurl': secondlevelurl
})
#lock.acquire()
#lock.release()
r.extend(
Request(site,
callback=self.parse,
meta={
'tagType': tag,
'counter': counterValueLink
}) for site in siteList
if site.startswith("http://") or site.startswith("https://"))
return r
def parse(self, response):
sel = Selector(response)
try:
page_json = sel.re(weibos_re)[0]
except IndexError:
raise LoginFailed()
page_html = json.loads(page_json).get('html')
if not page_html:
raise IgnoreRequest()
page_urls = Selector(text=page_html).xpath(
'.//a[contains(@suda-data,"key=tblog_search_weibo&value=weibo_page'
'")]/@href'
).extract()
page_urls.pop(-1)
page_urls.append(self.search_url.format(1))
for href in page_urls:
url = ''.join([self.url_prefix, href])
yield Request(url=url,
meta={'cookiejar': 1},
cookies=self.cookies,
callback=self.parse_weibo)
def _extract_external_link_requests(self,response,tag,counter):
r=[]
siteList=[]
ObjectList=dict()
externalSites=[]
#uniqueExternalSites=[]
if isinstance(response, HtmlResponse):
tag='L'
#linkcount=0
counterValueLink=counter
sites = Selector(response).xpath("//link/@href").extract()
# for site in sites:
# linkcount=linkcount+1
#logging.info('linkcount',linkcount)
#logwr = csv.writer(logFile, delimiter=',',quotechar=' ', quoting=csv.QUOTE_MINIMAL)
for item in sites:
if isinstance(item, unicode):
item=item.encode('utf-8')
siteList.append(item)
else:
siteList.append(item)
sites.append(counterValueLink)
externallinkCount,InternallinkCount,uniqueExternalSites,externalSites,secondlevelurl=_extract_object_count(siteList)
#wr.writerow(siteList)
linkcount=len(siteList)
#lock.acquire()
# ObjectList['url']=response.url
# ObjectList['counter']=counterValueLink
# ObjectList['linkcount']=linkcount
# ObjectList['InternallinkCount']=InternallinkCount
# ObjectList['ExternallinkCount']=externallinkCount
# #lock.acquire()
# logwr.writerow([ObjectList])
logwr.writerow({'url': response.url, 'counter': counterValueLink,'InternallinkCount':InternallinkCount,'ExternallinkCount':externallinkCount,'UniqueExternalSites':uniqueExternalSites,'ExternalSites':externalSites,'secondlevelurl':secondlevelurl})
#lock.acquire()
#lock.release()
r.extend(Request(site, callback=self.parse,meta={'tagType': tag,'counter': counterValueLink})for site in siteList if site.startswith("http://") or site.startswith("https://"))
return r
def Vacancy(link):
url = link
headers = {
"User-Agent":
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.75 Safari/537.36",
"Accept-Language": "en-US,en;q=0.9,ru;q=0.8"
}
page = requests.get(url, headers=headers)
# Company
try:
company = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[1]/h4/text()').get()
except:
company = ""
# position
try:
position = Selector(response=page).xpath(
'//*[@id="loyal"]/div[2]/div/div[1]/h4/text()').get()
except:
position = ""
# logo
try:
logo = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[1]/img/@src').get()
except:
logo = ""
# Job_type
try:
job_type = Selector(response=page).xpath(
'/html/body/div[3]/div/div[1]/div[2]/div[1]/div[2]/div[1]/div[1]//text()[2]'
).get()
job_type = job_type.strip()
except:
job_type = ""
# Contact Person
try:
person = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[2]/div/text()[2]').get(
)
person = person.strip()
except:
person = ""
# Email
try:
email = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[2]/div/text()[3]').get(
)
email = email.strip()
email = [email]
except:
email = []
# Phone
try:
phone = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[2]/div/text()[4]').get(
)
phone = phone.strip()
if "," in phone:
phones = phone.split(",")
phone = []
for each in phones:
each = each.strip()
if "+" in each and " " in each:
number = each.split(" ",
1)[1].replace('-',
"").replace(" ", "")
country_code = each.split(" ", 1)[0].replace('+', "")
phone.append({
"country_code": country_code,
"number": number
})
elif "+" in each and " " not in each:
if "+374" in each:
country_code = "374"
number = each.replace("+374", "")
phone.append({
"country_code": country_code,
"number": number
})
elif "+1" in each:
country_code = "1"
number = each.replace("+1", "")
phone.append({
"country_code": country_code,
"number": number
})
else:
country_code = "374"
number = each
phone.append({
"country_code": country_code,
"number": number
})
elif "+" not in each:
number = each.replace('-', "").replace(" ", "")
country_code = "374"
phone.append({
"country_code": country_code,
"number": number
})
else:
if "+" in phone and " " in phone:
number = phone.split(" ", 1)[1].replace('-',
"").replace(" ", "")
country_code = phone.split(" ", 1)[0].replace('+', "")
phone = [{"country_code": country_code, "number": number}]
elif "+" in phone and " " not in phone:
if "+374" in phone:
country_code = "374"
number = phone.replace("+374", "")
phone = [{"country_code": country_code, "number": number}]
elif "+1" in phone:
country_code = "1"
number = phone.replace("+1", "")
phone = [{"country_code": country_code, "number": number}]
else:
country_code = "374"
number = phone
phone = [{"country_code": country_code, "number": number}]
elif "+" not in phone:
number = phone.replace('-', "").replace(" ", "")
country_code = "374"
phone = [{"country_code": country_code, "number": number}]
except Exception as e:
phone = []
# Website
try:
website = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[2]/div/text()[5]').get(
)
website = website.strip()
if "not" in website:
website = []
else:
website = [website]
except:
website = []
# Published
try:
published = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[1]/div[2]/text()[2]').get()
published = published.strip()
publish_day = int(published.split("-")[2])
publish_month = int(published.split("-")[1])
publish_year = int(published.split("-")[0])
except:
publish_day = 0
publish_month = 0
publish_year = 0
# Ends
try:
ends = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[1]/div[2]/text()[5]').get()
ends = ends.strip()
deadline_day = int(ends.split("-")[2])
deadline_month = int(ends.split("-")[1])
deadline_year = int(ends.split("-")[0])
except:
deadline_day = 0
deadline_month = 0
deadline_year = 0
# Career Level
try:
career_level = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[1]/div[2]/span[1]/text()').get(
)
if career_level == None:
career_level = ""
except:
career_level = ""
# Education
try:
education = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[1]/div[2]/span[2]/text()').get(
)
if education == None:
education = ""
except:
education = ""
# Experience
try:
experience = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[1]/div[2]/span[3]/text()').get(
)
if experience == None:
experience = ""
except:
experience = ""
# Salary
try:
salary = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[1]/div[2]/strong/text()').get(
)
if "-" in salary:
salary = salary.split("-")
min_salary = salary[0].strip()
min_salary = int(min_salary.replace(".", ""))
max_salary = salary[1].strip()
max_salary = int(max_salary.replace('.', ""))
elif "-" not in salary and salary != "N/A":
min_salary = int(salary.replace("."))
max_salary = int(salary.replace("."))
else:
min_salary = 0
max_salary = 0
except:
min_salary = 0
max_salary = 0
# Vacancy Description
try:
v_description = Selector(
response=page).xpath('//*[@id="loyal"]/div[2]/div/div[1]').get()
v_description = remove_tags(v_description).strip()
v_description = v_description.replace('\xa0', " ")
except:
v_description = ""
try:
if detect(v_description) == "et":
try:
v_description_en = Translate(v_description)
except:
v_description_en = " "
v_description_am = v_description
else:
v_description_en = v_description
v_description_am = ""
except:
v_description_am = ""
v_description_en = ""
# Company Description
try:
c_description = Selector(response=page).xpath(
'//*[@id="loyal"]/div[1]/div[2]/div[2]/div[1]/p/text()').get()
c_description = c_description.strip()
except:
c_description = ""
try:
if detect(c_description) == "et":
try:
c_description_en = Translate(c_description)
except:
c_description_en = " "
c_description_am = c_description
else:
c_description_en = c_description
c_description_am = ""
except:
c_description_am = ""
c_description_en = ""
# c_descrip ; //*[@id="loyal"]/div[1]/div[2]/div[2]/div[1]/p/text()
data = {
"company": company,
"position": position,
"logo": logo,
"person": person,
"job_type": job_type,
"email": email,
"phone": phone,
"website": website,
"publish_day": publish_day,
"publish_month": publish_month,
"publish_year": publish_year,
"deadline_day": deadline_day,
"deadline_month": deadline_month,
"deadline_year": deadline_year,
"career_level": career_level,
"education": education,
"experience": experience,
"min_salary": min_salary,
"max_salary": max_salary,
"v_description_am": v_description_am,
"v_description_en": v_description_en,
"c_description_am": c_description_am,
"c_description_en": c_description_en,
}
print(data)
return data
# Vacancy("https://rezume.am/job/2184")
try:
phone = Selector(response=page).xpath(
'//*[@id="ContactsBox"]/table/tbody/tr[2]/td[2]/span').get(
)
phone = remove_tags(phone)
if "," in phone:
array = phone.split(",")
phone = []
for each in array:
each = each.lstrip()
each = each.rstrip()
each = each.split(" ", 1)
code = each[0]
code = code.replace("+", "")
number = each[1]
phone.append({"country_code": code, "number": number})
else:
phone = phone.lstrip()
add = phone.rstrip()
add = add.split(" ", 1)
code = add[0]
code = code.replace("+", "")
number = add[1]
phone = [{"country_code": code, "number": number}]
except:
phone = []
# Web
try:
web = Selector(response=page).xpath(
'//*[@id="ContactsBox"]/table/tbody/tr[3]/td[2]/span').get(
def BiaFunction(company):
driver.get(f"https://www.bia.ge/EN")
driver.find_element_by_xpath('//*[@id="Filter_Query"]').send_keys(
f"{company}")
time.sleep(3)
try:
link = driver.find_element_by_xpath(
'/html/body/div[8]/div[2]').get_attribute('data-url')
page = requests.get(link)
# Company name
name = Selector(response=page).xpath(
'//*[@id="TrademarksListBox"]/li/text()').get()
# Vat number
vat_number = Selector(response=page).xpath(
'//*[@id="tpAboutCompany"]/table/tbody/tr[2]/td[2]/span[2]/text()'
).get()
# Address
try:
address = Selector(response=page).xpath(
'//*[@id="tpAboutCompany"]/table/tbody/tr[4]/td[2]/span[2]/text()'
).get()
raw = address.split(",")
postal_code = raw[0]
location = raw[1]
location = location.lstrip()
region = raw[2]
appartment = raw[3]
city_id = Geonames(location)
address = {
"location": {
"country": "GE",
"city": {
"id": f"{city_id}",
"city": location
}
},
"postal_code": postal_code,
"appartament": appartment,
"region": region
}
except Exception as e:
print(e)
address = {}
# Working hours
try:
working_hours = Selector(response=page).xpath(
'//*[@id="tpAboutCompany"]/table/tbody/tr[5]/td[2]/ul/li/text()'
).get()
raw = working_hours.split(":", 1)
days = raw[0].split("-")
till = days[1].lstrip().lower()
days = []
for day in weekdays:
if day != till:
days.append(day)
else:
days.append(day)
break
hourfrom = raw[1].split("-")[0]
hourfrom = hourfrom.lstrip()
hourfrom = hourfrom.rstrip()
hourto = raw[1].split("-")[1]
hourto = hourto.lstrip()
hourto = hourto.rstrip()
business_hours = {
"week_days": days,
"hour_from": hourfrom,
"hour_to": hourto
}
except:
business_hours = {}
# Foundation Date
foundation_date = Selector(response=page).xpath(
'//*[@id="tpAboutCompany"]/table/tbody/tr[3]/td[2]/span[2]/text()'
).get()
# Phone
try:
phone = Selector(response=page).xpath(
'//*[@id="ContactsBox"]/table/tbody/tr[2]/td[2]/span').get()
phone = remove_tags(phone)
if "," in phone:
array = phone.split(",")
phone = []
for each in array:
each = each.lstrip()
each = each.rstrip()
each = each.split(" ", 1)
code = each[0]
code = code.replace("+", "")
number = each[1]
number = number.replace(" ", "")
phone.append({"country_code": code, "number": number})
else:
phone = phone.lstrip()
add = phone.rstrip()
add = add.split(" ", 1)
code = add[0]
code = code.replace("+", "")
number = add[1]
number = number.replace(" ", "")
phone = [{"country_code": code, "number": number}]
except:
phone = []
# Web
try:
web = Selector(response=page).xpath(
'//*[@id="ContactsBox"]/table/tbody/tr[3]/td[2]/span').get()
web = remove_tags(web)
if "," in web:
array = web.split(",")
web = []
for each in array:
each = each.lstrip()
each = each.rstrip()
web.append(each)
else:
web = web.lstrip()
add = web.rstrip()
web = [add]
except:
web = []
# Email
try:
email = Selector(
response=page).xpath('//*[@id="TabPanelBox"]').get()
email = email.replace("*****@*****.**", "")
email = re.findall(r'[\w\.-]+@[\w\.-]+', email)
except:
email = []
info = {
"name": name,
"vat": vat_number,
"addresses": address,
"business_hours": business_hours,
"phones": phone,
"websites": web,
"emails": email,
"foundation_date": foundation_date
}
print("Bia Scraped Successfully")
# print(info)
return info
except:
print("No info")
return "No info"
# driver.find_element_by_xpath('//*[@id="Filter_Query"]').send_keys(Keys.RETURN)
# try:
# logo = driver.find_element_by_id('LogoImageUploaderBox').get_attribute("style")
# except:
# logo = ""
# print(logo)
# try:
# name = driver.find_element_by_id('CompanyNameBox').text
# except:
# name = ""
# print(name)
# try:
# trademarks = driver.find_element_by_xpath('//*[@id="TrademarksListBox"]/li').text
# except:
# trademarks = ""
# print(trademarks)
# try:
# legal_form = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[2]/td[1]/span[2]').text
# except:
# legal_form = ""
# print(legal_form)
# try:
# registration_number = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[3]/td[1]/span[2]').text
# except:
# registration_number = ""
# print(registration_number)
# try:
# registration_authority = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[4]/td[1]/span[2]').text
# except:
# registration_authority = ""
# print(registration_authority)
# try:
# status = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[5]/td[1]/span[2]').text
# except:
# status = ""
# print(status)
# try:
# brands = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[1]/td[2]/span[2]').text
# except:
# brands = ""
# print(brands)
# try:
# vat_number = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[2]/td[2]/span[2]').text
# except:
# vat_number = ""
# print(vat_number)
# try:
# registration_date = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[3]/td[2]/span[2]').text
# except:
# registration_date = ""
# print(registration_date)
# try:
# legal_address = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[4]/td[2]/span[2]').text
# except:
# legal_address = ""
# print(legal_address)
# try:
# working_hours = driver.find_element_by_xpath('//*[@id="tpAboutCompany"]/table/tbody/tr[5]/td[2]/ul/li').text
# except:
# working_hours = ""
# print(working_hours)
# try:
# phone = driver.find_element_by_xpath('//*[@id="ContactsBox"]/table/tbody/tr[2]/td[2]/span').text
# except:
# phone = ""
# print(phone)
# try:
# website = driver.find_element_by_xpath('//*[@id="ContactsBox"]/table/tbody/tr[3]/td[2]/span').text
# except:
# website = ""
# print(website)
# x = mycol.insert_one({
# "Name": name,
# "Logo": logo,
# "Trademarks": trademarks,
# "Legal_Form": legal_form,
# "Registration_Number": registration_number,
# "Registration_Authority": registration_authority,
# "Status": status,
# "Brands": brands,
# "VAT_Number": vat_number,
# "Registration_Date": registration_date,
# "Legal_Address": legal_address,
# "Working_Hours": working_hours,
# "Phone": phone,
# "Website": website
# })
# driver.find_element_by_xpath('').text
# driver.find_element_by_xpath('').text
# //*[@id="ContactsBox"]/table/tbody/tr[2]/td[2]/span/a
# //*[@id="ContactsBox"]/table/tbody/tr[2]/td[2]/span
