temp=[title,price,price_original,color_count,product_href]
queue_for_result.put(temp)
print(temp)
time.sleep(abs(random.gauss(4,1)))
def run(self):
print('begin')
self.get_info()
if __name__=='__main__':
queue_for_result=Queue(0)
# 网址生成
url_list=gen_url()
# 配置线程数
thread_count=10
url_list=list_split.list_split(url_list,thread_count)
Get_productInfo_thread=[]
for item in url_list:
Get_productInfo_thread.append(Get_productInfo(url_list=item))
for item in Get_productInfo_thread:
item.start()
for item in Get_productInfo_thread:
item.join()
# 结果持久化
# 结果提取及标题处理
result=[]
for i in range(queue_for_result.qsize()):
result.append(queue_for_result.get())
title=['product_title','price','price_original','color_count','product_href']
except:
print('*'*20+u'程序运行失误，已跳过'+'*'*20+url[1])
def run(self):
self.get_info()
if __name__=='__main__':
file_name='d:/spider/aliexpress/aliexpress_contact_href_2015-08-06.csv'
href_temp=[]
queue_for_result=Queue(0)
with open(file_name,'r') as csv_file:
reader=csv.reader(csv_file)
for row in reader:
href_temp.append(row)
href_temp=href_temp[1:]
href_temp_2=list_split.list_split(href_temp,2)
Get_contact_detail_thread=[]
for item in href_temp_2:
Get_contact_detail_thread.append(Get_contact_detail(item))
for item in Get_contact_detail_thread:
item.start()
for item in Get_contact_detail_thread:
item.join()
data=[]
for i in range(queue_for_result.qsize()):
data.append(queue_for_result.get())
title=['shop_name','contact_page_href','contact_name','department','tel_phone','mobile_phone','fax_num','address','province','city']
writer=My_Csv.Write_Csv(path='D:/spider/aliexpress',name='aliexpress_contact_detail',title=title,result=data)
writer.add_title_data()
print('*'*20+u'程序运行完毕，请检查数据'+'*'*20)
def run(self):
self.get_desc()
if __name__=='__main__':
queue_href=Queue(0)
result_brand=[]
# 构造品牌列表网址：
temp=''.join(map(chr,range(97,123)))
url_list=['http://brand.vip.com/list-'+item+'/' for item in temp]
url_list.append('http://brand.vip.com/list-0-9/')
# 获取品牌名称数据
print('*'*20+u'正在抓取品牌列表'+'*'*20)
thread_count=5
Get_BrandHref_thread=[]
url_list=list_split.list_split(url_list,thread_count)
for url_s in url_list:
Get_BrandHref_thread.append(Get_BrandHref(url_s))
for item in Get_BrandHref_thread:
item.start()
for item in Get_BrandHref_thread:
item.join()
for i in range(queue_href.qsize()):
result_brand.append(queue_href.get())
writer=My_Csv.Write_Csv(path='D:/spider/vip',name='vip_allbrand_list',result=result_brand)
writer.add_title_data(title=['en_brand','ch_brand','href'])
# 获取品牌简介及收藏量数据
print('*'*20+u'正在抓取品牌简介'+'*'*20)
queue_brandtext=Queue(0)
result_brandText=[]
thread_count_2=30
# url_list=url_for_spider()
# had_get_url_list=os.listdir('d:/spider/aliexpress/src')
# had_get_url_list=['http://www.aliexpress.com/wholesale?'+item.split('.txt')[0] for item in had_get_url_list]
# url_list=[item for item in url_list if item not in had_get_url_list]
#
# Get_src_thread=[]
# url_list=list_split.list_split(url_list,25)
# for item in url_list:
# Get_src_thread.append(Get_src(item))
# for item in Get_src_thread:
# item.start()
# for item in Get_src_thread:
# item.join()
original_file_list = os.listdir("d:/spider/aliexpress/src")
file_list_1 = list_split.list_split(original_file_list, 600)
i = 0
for temp in file_list_1:
i += 1
print("*" * 15 + "ROUND " + str(i) + "*" * 15)
file_list = list_split.list_split(temp, 30)
Get_info_thread = []
for item in file_list:
Get_info_thread.append(Get_info(item))
for item in Get_info_thread:
item.start()
for item in Get_info_thread:
item.join()
save_data()
print("+" * 15 + u"文件" + str(i) + u"已保存！" + "*" * 15)
# 当日代理可能未有，需先行调用，避免开启多线程的时候同时抓取代理
def use_proxy():
proxy_port=my_proxy.is_proxy_exists()
return proxy_port
if __name__=='__main__':
queue_for_result=Queue(0)
# 返回链接
get_contactHref_d=Get_contactHref(r'D:\spider\alibaba_inter').get_contactHref()
# 链接列表切割，为多个线程服务
# 配置项：计划开启线程数
thread_count=10
get_contactHref_split=list_split.list_split(get_contactHref_d,thread_count)
# 信息获取
# 配置项，是否使用代理
is_proxy=1
if is_proxy:
use_proxy()
Get_contactInfo_thread=[]
for item in get_contactHref_split:
Get_contactInfo_thread.append(Get_contactInfo(contact_href_list=item,proxy=is_proxy))
for item in Get_contactInfo_thread:
item.start()
for item in Get_contactInfo_thread:
item.join()
frame.find_element_by_css_selector(css_source).text]
# print frame.find_element_by_css_selector(css_source).text
except:result=''
return result
def run(self):
self.get_info()
if __name__=='__main__':
queue_result=Queue(0)
Get_phoneaddr_thread=[]
temp_com=xlrd.open_workbook(u'D:/spider/唯品会（VIPShop）商机线索输出_0731.xlsx')
table=temp_com.sheet_by_index(0)
arr_com=table.col_values(5)
arr_com=[item for item in arr_com[1:] if item != u'-']
temp_arr_com=list_split.list_split(arr_com,2)
for arr in temp_arr_com:
print(len(arr))
for item in temp_arr_com:
Get_phoneaddr_thread.append(Get_phoneaddr(item))
for item in Get_phoneaddr_thread:
item.start()
for item in Get_phoneaddr_thread:
item.join()
result=[]
for i in range(queue_result.qsize()):
result.append(queue_result.get())
result=[item for i in result for item in i]
writer=My_Csv.Write_Csv(path='D:/spider/vip',name='vip_compang_phoneaddr',result=result)
writer.add_title_data(title=[])
print('*'*20+u'程序运行完毕，请检查数据'+'*'*20)
