def ip_spider2():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '89免费代理'
page = 1
while True:
ip.source_page = f'http://www.89ip.cn/index_{page}.html'
data_list = ip.data_search(f'http://www.89ip.cn/index_{page}.html',
'//table[@class="layui-table"]//td/text()')
if not data_list:
break
print(f'第{page}页')
for i in range(0, 75, 5):
try:
ip_value = data_list[i].strip(' \n\t')
ip_port = data_list[i + 1].strip(' \n\t')
ip.ip = f"http://{ip_value}:{ip_port}"
ip.address = data_list[i + 2].strip(' \n\t')
except:
break
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
page += 1
time.sleep(2)
ip.spider_end()
def ip_spider7():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
page_all = ip.data_search('http://www.66ip.cn/index.html',
'//div[@id="PageList"]//a[last()-1]/text()')[0]
for page in range(1, int(page_all) + 1):
data_list = ip.data_search(
f'http://www.66ip.cn/{page}.html',
'//div[@class="containerbox boxindex"]//table//tr//text()',
'gbk')[5:]
for i in range(0, 10000, 5):
try:
ip.ip = f'http://{data_list[i]}:{data_list[i+1]}'
ip.address = data_list[i + 2]
ip.source_name = '66代理'
ip.source_page = f'http://www.66ip.cn/{page}.html'
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
except:
break
ip.spider_end()
def ip_spider5():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '开心代理'
page = 1
while True:
ip.source_page = f'http://ip.kxdaili.com/ipList/{page}.html#ip'
data_list = ip.data_search(
f'http://ip.kxdaili.com/ipList/{page}.html#ip',
'//table[@class="ui table segment"]//td/text()')
if not data_list:
break
for i in range(0, 70, 7):
ip.address = data_list[i + 5]
h_list = data_list[i + 3].split(',')
for h in h_list:
ip.ip = f'{h.lower()}://{data_list[i]}:{data_list[i+1]}'
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
page += 1
ip.spider_end()
def zjmyqyw_spdier():
company_deque=deque([],maxlen=35)
zjmyqyw=SuperSpider()
zjmyqyw.source_name='浙江名营企业网'
zjmyqyw.fax='-'
zjmyqyw.get_request('http://www.zj123.com/')
url_list1=['http://www.zj123.com/'+i.replace('1.','{}.') for i in zjmyqyw.data_search('find','.indsort dd a','href')]
profession_list=list(zjmyqyw.data_search('find','.indsort dd a'))
error_index=profession_list.index('特种印刷')
for profession,url1 in zip(profession_list[error_index:],url_list1[error_index:]):
for page in range(1,100):
print(f'{profession}——第{page}页')
try:
zjmyqyw.get_request(url1.format(page))
page_judge=zjmyqyw.data_search('find','.sleft .m.m1 .fred').__next__().split()[0]
except:
print(f'获取第{page}页失败')
page+=1
continue
if int(page_judge) != page:
break
url_list2=('http://www.zj123.com/member/VIPContact/'+i.split('-')[1]+'/index.htm' for i in zjmyqyw.data_search('find','.listdetail22 .listdetail dt a','href'))
url_list3=('http://www.zj123.com/member/VIPCompany/'+i.split('-')[1]+'/index.htm' for i in zjmyqyw.data_search('find','.listdetail22 .listdetail dt a','href'))
#print(url_list2)
for url2,url3 in zip(url_list2,url_list3):
try:
zjmyqyw.get_request(url2)
except:
continue
contact_info_dict={i.split('：')[0].strip():i.split('：')[-1].strip().replace('\xa0','') for i in zjmyqyw.data_search('find','.rkbody table tr')}
zjmyqyw.company_name=contact_info_dict['公司名称'] if contact_info_dict['公司名称'] else '-'
if zjmyqyw.company_name in company_deque:
print('信息重复')
continue
zjmyqyw.person_name=contact_info_dict['联系人'] if contact_info_dict['联系人'] else '-'
zjmyqyw.address=contact_info_dict['地 址'] if contact_info_dict['地 址'] else '-'
zjmyqyw.phone_number=contact_info_dict['电 话'] if contact_info_dict['电 话'] else '-'
zjmyqyw.qq=contact_info_dict['QQ'] if contact_info_dict['QQ'] else '-'
zjmyqyw.website=contact_info_dict['网 址'] if contact_info_dict['网 址'] else '-'
try:
zjmyqyw.get_request(url3)
except:
continue
company_info_list=list(zjmyqyw.data_search('find','.rkbody table tr td'))
company_info_dict={company_info_list[n].strip('： '):company_info_list[n+1].strip(': ') for n in range(0,24,2)}
#print(company_info_dict)
zjmyqyw.main_product=company_info_dict['主营产品或服务'] if company_info_dict['主营产品或服务'] else '-'
zjmyqyw.business_mode=company_info_dict['经营模式'] if company_info_dict['经营模式'] else '-'
zjmyqyw.company_type=company_info_dict['企业类型'] if company_info_dict['企业类型'] else '-'
zjmyqyw.register_money=company_info_dict['注册资本'] if company_info_dict['注册资本'] else '-'
zjmyqyw.register_money=company_info_dict['员工人数'] if company_info_dict['员工人数'] else '-'
zjmyqyw.source_page=url2
zjmyqyw.data_save()
zjmyqyw.phone_number=contact_info_dict['手机'] if contact_info_dict['手机'] else '-'
zjmyqyw.data_save()
company_deque.append(zjmyqyw.company_name)
print(f'{profession}——第{page}页——{zjmyqyw.company_name}信息导入完成')
zjmyqyw.spider_end()
def zjmyqyw():
zjmyqyw=SuperSpider()
zjmyqyw.source='浙江名营企业网'
zjmyqyw.fax='-'
zjmyqyw.get_request('http://www.zj123.com/')
url_list1=('http://www.zj123.com/'+i.replace('1.','{}.') for i in zjmyqyw.data_search('find','.indsort dd a','href'))
for url1 in url_list1:
page=1
while True:
print(f'第{page}页')
zjmyqyw.get_request(url1.format(page))
page_judge=zjmyqyw.data_search('find','.sleft .m.m1 .fred').__next__().split()[0]
if int(page_judge) != page:
break
print(page_judge)
url_list2=('http://www.zj123.com/member/VIPContact/'+i.split('-')[1]+'/index.htm' for i in zjmyqyw.data_search('find','.listdetail22 .listdetail dt a','href'))
url_list3=('http://www.zj123.com/member/VIPCompany/'+i.split('-')[1]+'/index.htm' for i in zjmyqyw.data_search('find','.listdetail22 .listdetail dt a','href'))
#print(url_list2)
for url2,url3 in zip(url_list2,url_list3):
zjmyqyw.get_request(url2)
contact_info_dict={i.split('：')[0].strip():i.split('：')[-1].strip().replace('\xa0','') for i in zjmyqyw.data_search('find','.rkbody table tr')}
zjmyqyw.company_name=contact_info_dict['公司名称'] if contact_info_dict['公司名称'] else '-'
zjmyqyw.person_name=contact_info_dict['联系人'] if contact_info_dict['联系人'] else '-'
zjmyqyw.address=contact_info_dict['地 址'] if contact_info_dict['地 址'] else '-'
zjmyqyw.phone_code=contact_info_dict['电 话'] if contact_info_dict['电 话'] else '-'
zjmyqyw.cell_phone=contact_info_dict['手机'] if contact_info_dict['手机'] else '-'
zjmyqyw.qq=contact_info_dict['QQ'] if contact_info_dict['QQ'] else '-'
zjmyqyw.website=contact_info_dict['网 址'] if contact_info_dict['网 址'] else '-'
zjmyqyw.get_request(url3)
company_info_list=list(zjmyqyw.data_search('find','.rkbody table tr td'))
company_info_dict={company_info_list[n].strip('： '):company_info_list[n+1].strip(': ') for n in range(0,24,2)}
#print(company_info_dict)
zjmyqyw.main_product=company_info_dict['主营产品或服务'] if company_info_dict['主营产品或服务'] else '-'
zjmyqyw.business_mode=company_info_dict['经营模式'] if company_info_dict['经营模式'] else '-'
zjmyqyw.company_type=company_info_dict['企业类型'] if company_info_dict['企业类型'] else '-'
zjmyqyw.register_money=company_info_dict['注册资本'] if company_info_dict['注册资本'] else '-'
zjmyqyw.data_save()
print(f'浙江企业网——{zjmyqyw.company_name}信息导入完成')
page+=1
zjmyqyw.spider_end()
#zjmyqyw()
# test_obj=SuperSpider()
# js='var btn=document.querySelector(".see_a.inactive_scode");btn.click();'
# test_obj.use_selenium()
# test_obj.selenium_js('https://www.china.cn/shukongjichuang/3746553522.html',js)
# test_obj.cell_phone=test_obj.selenium_search('css_selector','.inactive_top .number').__next__()
# print('aaaaaaa')
# print(test_obj.cell_phone)
def ip_spider4():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '方法SEO'
ip.source_page = 'https://ip.seofangfa.com/'
data_list = ip.data_search('https://ip.seofangfa.com/',
'//table[@class="table"]//td/text()')
for i in range(0, 250, 5):
ip.ip = f'http://{data_list[i]}:{data_list[i+1]}'
ip.address = data_list[i + 3]
ip.data_save()
print(f'{ip.source_name}-{ip.ip}-导入完成')
ip.spider_end()
def ip_spider1():
ip = SuperSpider(host='192.168.0.172',
table_name='ip_pool',
field_list=[
'spider_datetime', 'source_name', 'source_page', 'ip',
'address'
])
ip.source_name = '快代理'
for page in range(1, 100):
print(f'第{page}页')
ip.source_page = f'https://www.kuaidaili.com/free/inha/{page}/'
data_list = ip.data_search(
f'https://www.kuaidaili.com/free/inha/{page}/',
'//table[@class="table table-bordered table-striped"]//td/text()')
for i in range(0, 105, 7):
try:
ip.ip = f'http://{data_list[i]}:{data_list[i+1]}'
ip.address = data_list[i + 4]
except:
break
ip.data_save()
print(f'{ip.source_name}-第{page}页-{ip.ip}-导入完成')
time.sleep(10)
ip.spider_end()
def wl114_spider():
wl114 = SuperSpider()
wl114.source_name = '网络114'
wl114.business_mode = '-'
wl114.register_money = '-'
wl114.website = '-'
wl114.qq = '-'
wl114.get_request('http://www.net114.com/')
url_list1 = [
i.replace('.html', '-p-{}.html') for i in wl114.data_search(
'xpath',
'//*[@id="product_center_content"]/div/ul/li/p/a',
attr='href') if i.endswith('.html')
]
profession_list1 = [
i for i in wl114.data_search(
'xpath', '//*[@id="product_center_content"]/div/ul/li/p/a')
if i != '更多>>'
]
error_index = profession_list1.index('维护工具')
url_list2 = (i for i in wl114.data_search(
'xpath',
'//*[@id="product_center_content"]/div/ul/li/p/a',
attr='href') if not i.endswith('.html'))
profession_list2 = (i for i in wl114.data_search(
'xpath', '//*[@id="product_center_content"]/div/ul/li/p/a')
if i == '更多>>')
for url1, profession1 in zip(url_list1[error_index:],
profession_list1[error_index:]):
try:
wl114.get_request(url1.format(1))
all_page = wl114.data_search(
'find', '.page_p:not(span)').__next__().split('\xa0')[1]
except:
continue
for page in range(1, int(all_page) + 1):
print(f'{profession1}——第{page}页')
try:
wl114.get_request(url1.format(page))
except:
continue
url_list3 = list(
wl114.data_search('find', '.product_list_div_h143 h2 a',
'href'))
if not url_list3:
break
for url3 in url_list3:
try:
wl114.get_request(url3)
company_info_dict = {
i.split('：')[0].strip(): i.split('：')[-1].strip()
for i in wl114.data_search(
'find', '.right.w_250 .border.p_8 li') if '：' in i
}
phone_url = wl114.data_search(
'find', '.right.w_250 .border.p_8 li a',
'href').__next__()
except:
continue
wl114.company_type = company_info_dict.get('企业性质', '-')
wl114.main_product = company_info_dict.get('企业主营', '-')
wl114.address = company_info_dict.get('企业地址', '-')
try:
wl114.get_request(phone_url)
except:
continue
phone_info_data = wl114.data_search(
'find', 'td[valign="top"]:first-child')
try:
phone_info_list = phone_info_data.__next__().split('\n')
phone_info_dict = {
i.split('：')[0].strip(): i.split('：')[-1].strip()
for i in phone_info_list if '：' in i
}
except:
continue
wl114.company_name = phone_info_dict.get('公司名称', '-')
if wl114.company_name == '-':
wl114.company_name = phone_info_dict.get('企业名称', '-')
wl114.person_name = phone_info_dict.get('联系人', '-')
wl114.fax = phone_info_dict.get('传真', '-')
wl114.phone_number = phone_info_dict.get('手机', '-')
wl114.source_page = url3
wl114.data_save()
wl114.phone_number = phone_info_dict.get('联系电话', '-')
wl114.data_save()
print(f'{profession1}——第{page}页——{wl114.company_name}信息导入完成')
page += 1
for url2 in url_list2:
try:
wl114.get_request(url2)
except:
continue
url_list4 = (i.replace('.html', '-p-{}.html')
for i in wl114.data_search(
'find', '.product_w369_list a[href]', 'href'))
profession_list4 = wl114.data_search('find',
'.product_w369_list a[href]')
for profession4, url4 in zip(profession_list4, url_list4):
try:
wl114.get_request(url4.format(1))
all_page = wl114.data_search(
'find', '.page_p:not(span)').__next__().split('\xa0')[1]
except:
continue
for page in range(1, int(all_page) + 1):
print(f'{profession4}——第{page}页')
try:
wl114.get_request(url4.format(page))
except:
continue
url_list3 = list(
wl114.data_search('find', '.product_list_div_h143 h2 a',
'href'))
if not url_list3:
break
for url3 in url_list3:
try:
wl114.get_request(url3)
company_info_dict = {
i.split('：')[0].strip(): i.split('：')[-1].strip()
for i in wl114.data_search(
'find', '.right.w_250 .border.p_8 li')
if '：' in i
}
phone_url = wl114.data_search(
'find', '.right.w_250 .border.p_8 li a',
'href').__next__()
except:
continue
wl114.company_type = company_info_dict.get('企业性质', '-')
wl114.main_product = company_info_dict.get('企业主营', '-')
wl114.address = company_info_dict.get('企业地址', '-')
try:
wl114.get_request(phone_url)
except:
continue
phone_info_data = wl114.data_search(
'find', 'td[valign="top"]:first-child')
try:
phone_info_list = phone_info_data.__next__().split(
'\n')
phone_info_dict = {
i.split('：')[0].strip(): i.split('：')[-1].strip()
for i in phone_info_list if '：' in i
}
except:
continue
wl114.company_name = phone_info_dict.get('公司名称', '-')
if wl114.company_name == '-':
wl114.company_name = phone_info_dict.get('企业名称', '-')
wl114.person_name = phone_info_dict.get('联系人', '-')
wl114.fax = phone_info_dict.get('传真', '-')
wl114.phone_number = phone_info_dict.get('手机', '-')
wl114.source_page = url3
wl114.data_save()
wl114.phone_number = phone_info_dict.get('联系电话', '-')
wl114.data_save()
print(
f'{profession4}——第{page}页——{wl114.company_name}信息导入完成')
page += 1
wl114.spider_end()
def zggys_spider():
zggys = SuperSpider(host='192.168.0.172', default_field='-')
zggys.source_name = '中国供应商'
proxies_list = zggys.sql_search('select ip from ip_pool')
url_list1 = [
i + '?p={}' for i in zggys.data_search(
'https://cn.china.cn/',
'//*[@id="content"]/div[1]/div[1]/div/div[2]/div/div[2]/div/ul/li/div[2]/a/@href'
)
]
profession_list = zggys.data_search(
'https://cn.china.cn/',
'//*[@id="content"]/div[1]/div[1]/div/div[2]/div/div[2]/div/ul/li/div[2]/a/text()',
'GBK')
error_index = profession_list.index('睡袋')
for url1, profession in zip(url_list1[error_index:],
profession_list[error_index:]):
page = 1
while True:
time.sleep(2)
print(f'{profession}——第{page}页')
for i in range(20):
proxies = random.choice(proxies_list)[0]
print(f'使用代理-{proxies}')
key = 'http' if not proxies.startswith('https') else 'https'
try:
url_list2 = zggys.data_search(
url1.format(page),
'//ul[@class="extension_ul"]//h3[@class="title"]/a/@href',
'GBK',
proxies={key: proxies},
timeout=5)
except Exception as error:
print(error)
continue
if not url_list2:
print(f'{profession}——第{page}页——没有数据')
break
for url2 in url_list2:
for i in range(20):
try:
time.sleep(2)
proxies = random.choice(proxies_list)[0]
print(f'使用代理-{proxies}')
key = 'http' if not proxies.startswith(
'https') else 'https'
html = zggys.get_html(url2,
charset='GBK',
proxies={key: proxies},
timeout=5)
zggys.source_page = url2
if zggys.data_search(
html=html,
xpath='//div[@class="column_xx"]//p//a/text()'
):
zggys.company_name = zggys.data_search(
html=html,
xpath='//div[@class="column_xx"]//p//a/text()'
)[0]
company_info_list = [
i for i in zggys.data_search(
html=html,
xpath='//ul[@class="business_xx"]//li//text()')
if i.strip('\r\n |')
]
# print(company_info_list)
except Exception as error:
print(error)
continue
else:
try:
aim_index = company_info_list.index('经营模式')
zggys.business_mode = company_info_list[aim_index +
1]
except:
pass
try:
aim_index = company_info_list.index('注册资本')
zggys.register_money = company_info_list[
aim_index + 1].strip()
except:
pass
try:
aim_index = company_info_list.index('企业类型')
zggys.company_type = company_info_list[aim_index +
1]
except:
pass
try:
aim_index = company_info_list.index('主营产品')
zggys.main_product = company_info_list[aim_index +
1]
except:
pass
try:
aim_index = company_info_list.index('公司地址')
zggys.address = company_info_list[aim_index + 1]
except:
pass
try:
zggys.person_name = zggys.data_search(
html=html,
xpath=
'//div[@class="personal_top"]//div[@class="t"]//span/text()'
)[0]
except:
pass
phone_list = zggys.data_search(
html=html,
xpath='//div[@class="personal_bottom"]//span/text()'
)
if not phone_list:
# js=['var btn=document.querySelector(".see_a.inactive_scode");btn.click();']
# try:
# zggys.selenium_open(url2)
# zggys.selenium_js(js,sleep_time=2)
# zggys.phone_number=zggys.selenium_search('css_selector','.inactive_top .number').__next__()
# phone_info_dict={i.split('\n')[0]:i.split('\n')[1].strip('QQ交谈') for i in zggys.selenium_search('css_selector','.inactive_right .txt p')}
# except:
# continue
# zggys.fax=phone_info_dict.get('传真','-').strip()
# zggys.qq=phone_info_dict.get('Q Q','-').strip()
# zggys.data_save()
# zggys.phone_number=phone_info_dict.get('电话','-').strip()
# zggys.data_save()
break
for phone in phone_list:
zggys.phone_number = phone.strip()
zggys.data_save()
print(
f'{profession}—第{page}页—{zggys.company_name}信息导入完成'
)
break
page += 1
zggys.spider_end()
def xarcw_spider():
word_list = ['网络']
xarcw = SuperSpider(host='192.168.0.172', default_field='-')
xarcw.source_name = '新安人才网'
data = {'memberName': '13155291086', 'password': '******'}
xarcw.post_request('https://login.goodjobs.cn/index.php/action/UserLogin',
data=data)
for word in word_list:
for city_code in range(1043, 1061):
for page in range(1, 61):
print(f'{word}-{city_code}-第{page}页')
try:
url_list = xarcw.data_search(
f'https://search.goodjobs.cn/index.php?keyword={word}&boxwp=c{city_code}&page={page}',
'//div[@class="dw_table"]//span[@class="e1"]/a/@href')
except:
print(f'{word}-{city_code}-第{page}页获取失败')
continue
if not url_list:
print(f'{word}-{city_code}-第{page}页-爬取结束')
break
for url in url_list:
# print(url)
xarcw.source_page = url
time.sleep(1)
data_list = xarcw.data_search(url, [
'//p[@class="cname"]/a/text()',
'//p[@class="msg ltype"]/text()',
'//div[@class="w706 clearfix"]/text()',
'//div[@class="w706 clearfix"]/img/@src',
'//div[@class="comadress clearfix"]/text()'
])
if not data_list[0] or not data_list[3]:
continue
if not data_list[0]:
data_list = xarcw.data_search(url, [
'//div[@class="w240 whitespace pb16"]//a[@class="org"]/text()',
'//div[@class="w240 whitespace pb16"]//p[@class="grey lh28"]/span[@class="black"]/text()',
'//p[@class="duol mt20"]/text()',
'//p[@class="duol mt20"]/img/@src',
'//div[@class="comadress clearfix"]/text()'
])
xarcw.company_type = data_list[1][0]
xarcw.main_product = data_list[1][2]
else:
company_info_list = [
i.strip('\xa0\xa0\n ')
for i in data_list[1][0].split('|')
]
xarcw.company_type = company_info_list[0]
for j in company_info_list[1:]:
if '-' in j:
xarcw.staff_number = j
else:
xarcw.main_product = j
xarcw.company_name = data_list[0][0]
xarcw.person_name = [i for i in data_list[2]
if i.strip()][0]
try:
xarcw.phone_number = xarcw.use_tesseract(
url=data_list[3][0], lang=None)
except:
continue
xarcw.address = data_list[4][0].strip('工作地点：\u3000\n ')
xarcw.data_save()
print(
f'{xarcw.company_name}-{xarcw.person_name}-{xarcw.phone_number}-导入完成'
)
def zggys_spider():
zggys=SuperSpider(use_selenium=True)
zggys.source='中国供应商'
zggys.website='-'
zggys.get_request('https://cn.china.cn/')
url_list1=(i+'?p={}' for i in zggys.data_search('xpath','//*[@id="content"]/div[1]/div[1]/div/div[2]/div/div[2]/div/ul/li/div[2]/a','href'))
for url1 in url_list1:
page=10
while True:
print(f'第{page}页')
try:
zggys.get_request(url1.format(page))
except:
print(f'获取第{page}页失败')
page+=1
continue
url_list2=zggys.data_search('find','h3.title a','href')
if not url_list2:
break
for url2 in url_list2:
try:
zggys.get_request(url2)
zggys.company_name=zggys.data_search('find','.column_xx p a','title').__next__()
except:
continue
company_info_list=(i for i in zggys.data_search('find','.business_xx').__next__().split('\n') if '|' in i)
company_info_dict={i.split('|')[0]:i.split('|')[1] for i in company_info_list}
zggys.business_mode=company_info_dict.get('经营模式','-')
zggys.register_money=company_info_dict.get('注册资本','-')
zggys.company_type=company_info_dict.get('企业类型','-')
zggys.main_product=company_info_dict.get('主营产品','-')
zggys.address=company_info_dict.get('公司地址','-')
#print(business_mode,register_money,company_type,main_product,address)
zggys.person_name=zggys.data_search('find','.personal_top .t span').__next__()
phone_list=zggys.data_search('find','.personal_bottom span')
#print(phone_list)
cell_phone_list=[]
phone_code_list=[]
for phone in phone_list:
if not phone:
js='var btn=document.querySelector(".see_a.inactive_scode");btn.click();'
zggys.selenium_js(url2,js)
zggys.cell_phone=zggys.selenium_search('css_selector','.inactive_top .number').__next__()
phone_info_dict={i.split('\n')[0]:i.split('\n')[1].strip('QQ交谈') for i in zggys.selenium_search('css_selector','.inactive_right .txt p')}
zggys.phone_code=phone_info_dict.get('电话','-')
zggys.fax=phone_info_dict.get('传真','-')
zggys.qq=phone_info_dict.get('Q Q','-')
else:
if not phone.startswith('1'):
phone_code_list.append(phone)
else:
cell_phone_list.append(phone)
if cell_phone_list or phone_code_list:
zggys.phone_code='/'.join(phone_code_list) if phone_code_list else '-'
zggys.cell_phone='/'.join(cell_phone_list) if cell_phone_list else '-'
zggys.fax='-'
zggys.qq='-'
zggys.data_save()
print(f'中国供应商——{zggys.company_name}信息导入完成')
page+=1
zggys.spider_end()
def skb_spider(phone,passwd,word,page_now=1):
skb=SuperSpider(use_selenium=True)
skb.source_name='搜客宝'
skb.fax='-'
skb.staff_number='-'
skb.selenium_open('https://biz.lixiaoskb.com/login')
skb.selenium_input('xpath','//*[@id="app"]/div[1]/div/div/div[1]/div[2]/div[2]/form/div[1]/div/div/div/input',phone)
skb.selenium_input('xpath','//*[@id="app"]/div[1]/div/div/div[1]/div[2]/div[2]/form/div[2]/div/div/div/input',passwd,enter=True,sleep_time=3)
js3='document.querySelector("#tab-0").click();'
skb.selenium_js([js3])
skb.selenium_input('xpath','//*[@id="searchDeInput"]/div[1]/div/input',word,sleep_time=5,enter=True)
all_page=500
if int(page_now) == int(all_page):
print(f'{word}——所有数据爬取结束')
skb.spider_end()
return word,int(all_page)
for page in range(page_now,int(all_page)+1):
print(f'{word}——第{page}页')
try:
skb.selenium_scroll('//div[@id="jumpPage"]//input[@class="el-input__inner"]')
skb.selenium_input('css_selector','#jumpPage .el-input input',page,sleep_time=2,enter=True)
except Exception as e:
print(e)
continue
url_list=skb.selenium_search('xpath',f'//div[@class="card"]//span[@class="name"]//a',attr='href')
for url in url_list:
skb.source_page=url
js1=f'window.open("{url}")'
skb.selenium_js([js1],sleep_time=3)
skb.switch_window()
try:
skb.company_name=skb.selenium_search('css_selector','.top .name').__next__()
except Exception as e:
print(e)
skb.window_close()
skb.switch_window(sleep_time=2)
continue
try:
company_info_dict1={i.split(':')[0].strip():i.split(':')[-1].strip() for i in skb.selenium_search('css_selector','.line .group')}
skb.company_type=company_info_dict1.get('公司类型','-')
skb.address=company_info_dict1.get('通讯地址','-')
business_mode=company_info_dict1.get('所属行业','-')
skb.website=company_info_dict1.get('官方网站','-').strip('更多>> ')
except:
pass
try:
company_info_dict2={i.split('\n')[0].strip('/ '):i.split('\n')[-1].strip('/ ') for i in skb.selenium_search('css_selector','.gongshang-col')}
skb.person_name=company_info_dict2.get('法人/负责人','-')
skb.register_money=company_info_dict2.get('注册资本','-')
skb.main_product=company_info_dict2.get('经营范围','-')
except:
pass
js2='var open_btn=document.querySelector(".mask-box .action span");open_btn.click();'
try:
skb.selenium_js([js2],sleep_time=3)
except Exception as e:
print(e)
phone_list=[]
qq_list=[]
try:
phone_info=skb.selenium_search('css_selector','.el-scrollbar__view')
phone_info_list=list(phone_info)[1].split('\n')
except Exception as e:
print(e)
skb.window_close()
skb.switch_window(sleep_time=2)
continue
#print(phone_info_list)
for i,j in enumerate(phone_info_list):
if j == '选 择':
skb.phone_number=phone_info_list[i-1]
elif j == '联系人':
skb.person_name=phone_info_list[i+1]
elif j == 'qq号码':
skb.qq=phone_info_list[i+1].strip(',')
elif j == '电子邮箱':
skb.mail=phone_info_list[i+1].strip(',')
try:
skb.data_save()
except:
continue
print(f'{word}——第{page}页——{skb.company_name}信息导入完成')
skb.window_close()
skb.switch_window(sleep_time=2)
continue
phone_list=[]
qq_list=[]
try:
phone_info=skb.selenium_search('css_selector','.el-scrollbar__view')
phone_info_list=list(phone_info)[1].split('\n')
except Exception as e:
print(e)
skb.window_close()
skb.switch_window(sleep_time=2)
continue
#print(phone_info_list)
for i,j in enumerate(phone_info_list):
if j == '选 择':
skb.phone_number=phone_info_list[i-1]
elif j == '联系人':
skb.person_name=phone_info_list[i+1]
elif j == 'qq号码':
skb.qq=phone_info_list[i+1].strip(',')
elif j == '电子邮箱':
skb.mail=phone_info_list[i+1].strip(',')
try:
skb.data_save()
except:
continue
print(f'{word}——第{page}页——{skb.company_name}信息导入完成')
use_number=skb.selenium_search('css_selector','.inner-user .viewCount:first-child').__next__()
print(use_number)
if int(use_number) == 0:
print(f'{word}——第{page}页——今日次数已用完')
skb.spider_end()
return word,page
skb.window_close()
skb.switch_window(sleep_time=2)
skb.spider_end()
print(f'{word}——所有数据爬取结束')
return word,int(all_page)
def zgcpw_spider():
zgcpw = SuperSpider()
company_list = deque([], maxlen=35)
zgcpw.source_name = '中国产品网'
zgcpw.get_request('http://www.pe168.com/')
url_list1 = zgcpw.data_search('find', 'td div:nth-child(2) a', 'href')
profession_list = zgcpw.data_search('find', 'td div:nth-child(2) a')
for profession, url1 in zip(profession_list, url_list1):
try:
zgcpw.get_request(url1)
page_all = zgcpw.data_search('find', '.pages cite').__next__()
page_all_number = zgcpw.re_find(r'/(\d+)页',
page_all).__next__().group(1)
except:
continue
for page in range(1, int(page_all_number) + 1):
print(f'{profession}——第{page}页')
url2 = url1.replace('.html', f'-{page}.html')
try:
zgcpw.get_request(url2)
except:
continue
url_list3 = zgcpw.data_search(
'find', '.left_box form tr ul li:nth-last-child(1) a', 'href')
company_list3 = zgcpw.data_search(
'find', '.left_box form tr ul li:nth-last-child(1) a')
for company_name, url3 in zip(company_list3, url_list3):
if company_name in company_list:
print('信息重复')
continue
company_list.append(company_name)
zgcpw.company_name = company_name
try:
zgcpw.get_request(url3)
except:
continue
zgcpw.source_page = url3
try:
company_info_url = zgcpw.data_search(
'find', 'a[title="公司介绍"]', 'href').__next__()
except:
company_list.append(company_name)
continue
try:
zgcpw.get_request(company_info_url)
except:
continue
company_info_list = list(
zgcpw.data_search('find',
'.main_body:nth-last-child(1) td'))
zgcpw.company_type = company_info_list[
company_info_list.index('公司类型：') +
1] if '公司类型：' in company_info_list else '-'
zgcpw.staff_number = company_info_list[
company_info_list.index('公司规模：') +
1] if '公司规模：' in company_info_list else '-'
zgcpw.register_money = company_info_list[
company_info_list.index('注册资本：') +
1] if '注册资本：' in company_info_list else '-'
zgcpw.business_mode = company_info_list[
company_info_list.index('经营模式：') +
1] if '经营模式：' in company_info_list else '-'
zgcpw.main_product = company_info_list[
company_info_list.index('经营范围：') +
1] if '经营范围：' in company_info_list else '-'
try:
phone_info_url = zgcpw.data_search('find',
'a[title="联系方式"]',
'href').__next__()
except:
company_list.append(company_name)
continue
try:
zgcpw.get_request(phone_info_url)
except:
continue
phone_info_list = list(
zgcpw.data_search('find', '.px13.lh18 td'))
zgcpw.address = phone_info_list[
phone_info_list.index('公司地址：') +
1] if '公司地址：' in phone_info_list else '-'
zgcpw.fax = phone_info_list[
phone_info_list.index('公司传真：') +
1] if '公司传真：' in phone_info_list else '-'
zgcpw.website = phone_info_list[
phone_info_list.index('公司网址：') +
1] if '公司网址：' in phone_info_list else '-'
zgcpw.person_name = phone_info_list[
phone_info_list.index('联 系 人：') +
1] if '联 系 人：' in phone_info_list else '-'
zgcpw.phone_number = phone_info_list[
phone_info_list.index('公司电话：') +
1] if '公司电话：' in phone_info_list else '-'
zgcpw.data_save()
zgcpw.phone_number = phone_info_list[
phone_info_list.index('手机号码：') +
1] if '手机号码：' in phone_info_list else '-'
zgcpw.data_save()
print(f'{profession}——第{page}页——{company_name}导入完成')
zgcpw.spider_end()
