def gen_url():
def url_join(t):
if '.html' in t:
return None
else:
temp = t.rsplit('/', 1)
return temp[0] + '/contactinfo/' + temp[1] + '.html'
def change_par(x):
if '//www' in x:
return url_join(x)
elif '//pt' in x:
return url_join(x.replace('//pt', '//www'))
elif '//ru' in x:
return url_join(x.replace('//ru', '//www'))
elif '//es' in x:
return url_join(x.replace('//es', '//www'))
else:
return None
db_g = DBService(dbName=db_name, tableName='aliexpress_temp', **connect_dict)
href_list_t = db_g.getData(var='store_href', distinct=True)
href_s = map(
lambda t: change_par(t), map(
lambda x: x[0], href_list_t
)
)
return list(set(filter(lambda x: 1 if x else 0, href_s)))
def push2DB():
from ms_spider_fw.DBSerivce import DBService
data=getKeyword()
db=DBService('taobaodata','keyword')
tableTitle=['categoryFi', 'categorySe', 'categoryTi']
db.createTable(tableTitle=tableTitle)
db.data2DB(data=data)
def spiderMain():
"""
# main主程序
:return:
"""
dler = Dler()
dler.downLoad(100)
DB = DBService(dbName='jddata', tableName='thirdPartShopInfo')
DB.createTable(
tableTitle=['productHref', 'companyName', 'shopName', 'shopHref', 'scoreSum', 'scoreProduct', 'scoreProductAvg',
'scoreService',
'scoreServiceAvg', 'scoreExpress', 'scoreExpressAvg', 'gradeHref'])
while True:
que = DBN.queueForDownLoad
if not que.empty():
url, src = que.get()
pPer = PPer(src)
temp = pPer.pageParser()
# proxy_test=temp[0]
# if proxy_test=='-':
# continue
# else:
# print(proxy_test)
print(temp[0])
DB.data2DB(data=[url] + temp)
else:
time.sleep(1)
def productInfo():
db = DBService(dbName='jddata', tableName='jdproductbaseinfo2database')
data = db.getData(var='productHref,commentCount', limit=200000)
proDict = {}
for item in data:
proDict[item[0]] = item[1]
return proDict
def craweldhref():
db = DBService('elec_platform', 'yms_tmall_shopinfo_com_withoutjudge')
href = db.getData(var='href')
href = [item[0] for item in href]
F = lambda x: x[:-1] if x[-1] == '/' else x
href = map(F, href)
print(len(href))
return href
def spiderMain():
# 主程序
from ms_spider_fw.CSVService import CSV
dler = Dler()
dler.downLoad(100)
DB = DBService(dbName="jddata", tableName="shop_grade_score")
DB.createTable(
tableTitle=[
"gradeHref",
"totalScore",
"totalScore_avg",
"productScore",
"productScore_avg",
"productQualityScore",
"productQualityScore_avg",
"productDescribeScore",
"productDescribeScore_avg",
"returnExchangeRate",
"returnExchangeRate_avg",
"serviceScore",
"serviceScore_avg",
"sellerCSI",
"sellerCSI_avg",
"distributionCSI",
"distributionCSI_avg",
"onlineServiceCSI",
"onlineServiceCSI_avg",
"returnExchangeCSI",
"returnExchangeCSI_avg",
"temporalityScore",
"temporalityScore_avg",
"expScore",
"expScore_avg",
"sendPromptnessScore",
"sendPromptnessScore_avg",
"returnExchangeTime",
"returnExchangeTime_avg",
"onLineSeriveTime",
"onLineSeriveTime_avg",
"spider_time",
]
)
# while True:
que = DBN.queueForDownLoad
while True:
url, src = que.get()
try:
pPer = PPer(src)
result = pPer.pageParser()
total = [url] + result
DB.data2DB(data=total)
print(result)
except:
continue
def companyInfo():
# 返回公司信息，字典形式
db = DBService(dbName='jddata', tableName='thirdPartShopInfo')
data = db.getData(limit=200000)
data = [item for item in data if not item[2] == '-']
comDict = {}
for item in data:
comDict[item[1]] = item[1:]
return comDict
def gen_url():
DB = DBService(dbName="alibaba", tableName="alibaba_cow_powder_3")
url_detail_page = DB.getData(var="credit_detail_href", distinct=True)
urls = map(lambda x: x[0] if x else " ", url_detail_page)
url = []
for t in urls:
if t:
url.append(t)
return url
def run(thread_count=1000):
run_test(thread_count)
db_server_c = DBService(dbName=db_name, tableName='proxy_ok', **connect_dict)
db_server_c.createTable(tableTitle=['proxy_port', 'test_time'], x='Y')
res = []
print '#'*100
print qu_proxy_ok.qsize()
while qu_proxy_ok.qsize():
res.append(qu_proxy_ok.get())
db_server_c.data2DB(data=res)
def proxy_collection():
# get proxies from website
proxies_list_website = pc.get_proxies_from_website()
# at the same time , get other proxies from local database
table_names_proxies = 'proxy_other_source,proxy_you_dai_li'
proxies_list_local = list()
for proxies_t_n in table_names_proxies.split(','):
dbs = DBService(dbName='base', tableName=proxies_t_n, **connect_dict)
proxies_list_local += map(lambda x: x[0], dbs.getData(var='proxy_port'))
return list(set(proxies_list_website + proxies_list_local))
def commentHrefList():
db = DBService('elec_platform', 'tmall_baseinfo_everyweek')
judgePageHref = db.getData(var='name,href,judgepage_href')
judgePageHref = [tuple(item) for item in judgePageHref if
not 'http' in item[2]]
judgePageHref = [item for item in judgePageHref if not item[2].isnumeric()]
judgePageHref = set(judgePageHref)
judgePageHref = list(judgePageHref)
print(len(judgePageHref))
return judgePageHref
def run(thread_count=20000):
muti_thread_test(thread_count)
db_server_c = DBService(dbName=db_name, tableName='proxy_ok', **connect_dict)
db_server_c.createTable(tableTitle=['proxy_port', 'test_time'], x='Y')
res = []
while qu_proxy_ok.qsize():
res.append([
qu_proxy_ok.get(),
time.strftime('%Y-%m-%d %X', time.localtime())
])
db_server_c.data2DB(data=res)
def begin():
db = DBService(dbName='jddata', tableName='thirdPartShopInfo')
data = db.getData()
title = db.getTableTitle()[1:-2]
S = set()
for item in data:
S.add(tuple(item[1:-2]))
data = []
for item in S:
data.append(list(item))
csv = CSV()
csv.writeCsv(savePath='D:/spider', fileTitle=title, data=data, fileName='jdData')
def sumCommentCount():
db = DBService(dbName='jddata', tableName='thirdPartShopInfoAddCommnetCount')
# db = DBService(dbName='jddata', tableName='thirdPartShopInfoAddtest')
data = db.getData(var='shopName,commnetCount')
dict = {}
for item in data:
if item[0] in dict.keys():
dict[item[0]] = int(item[1]) + dict[item[0]]
else:
dict[item[0]] = int(item[1])
data = []
for item in dict.items():
data.append([item[0], item[1]])
csv = CSV()
csv.writeCsv(savePath='D:/spider', fileTitle=['shopName', 'commnetCount'], data=data, fileName='jdDataSum')
def startUrlList(self):
"""
# 方法重载
:return:
"""
dbs = DBService(dbName='jddata', tableName='jdproductbaseinfo2database')
data = dbs.getData(var='productHref,sku', distinct=True)
dataThirdPartBase = [item[0] for item in data if len(item[1]) >= 10]
dataHadCrawled = DBService(dbName='jddata', tableName='thirdPartShopInfo').getData(var='productHref')
if not dataHadCrawled:
return dataThirdPartBase
dataHadCrawled = set([item[0] for item in dataHadCrawled])
dataThirdPart = [item for item in dataThirdPartBase if item not in dataHadCrawled]
dataThirdPart = [item for item in dataThirdPart if item[:4] == 'http']
# print len(dataThirdPart)
return dataThirdPart
def savePicture():
from screenShot import saveScreenShot
from ms_spider_fw.DBSerivce import DBService
import time
import random
db = DBService(dbName='tmalldata', tableName='tmall_baseinfo_realtime')
data = db.getData(var='name,href', distinct=True)
nameD = map(lambda x: x[0], data)
data = map(lambda x: x[1], data)
print(len(data))
dri = None
for url in data:
name=nameD[data.index(url)]
print(name)
dri = saveScreenShot(url, driver=dri,title=name)
time.sleep(abs(random.gauss(3, 2)))
def spiderMain():
"""
# main主程序
:return:
"""
dler = Dler()
dler.downLoad(10)
DB = DBService(#host='localhost',
# user='******',
# passwd='',
# charset='utf8',
# dbName='spider',
dbName='alibaba',
tableName='alibaba_cow_powder_3')
DB.createTable(tableTitle=
['company_name',
'keyword',
'sale',
'href',
'member_id',
'offer_id',
'cxt_year',
'credit_detail_href',
'goods_from',
'product_title_sample',
'product_detail_sample',
'location',
'url_base'])
while True:
que = DBN.queueForDownLoad
if not que.empty():
url, src = que.get()
pPer = PPer(src)
temp = pPer.pageParser()
if temp:
temp = map(lambda x: x + [url], temp)
DB.data2DB(data=temp)
print(u'++成功:%s'%url)
else:
print(u'--失败:%s'%url)
else:
time.sleep(1)
def spiderMain():
# 主程序
dler = Dler()
dler.downLoad(100)
DB = DBService(dbName="jddata", tableName="thirdPartShopSearchPage")
DB.createTable(tableTitle=["tttt"])
while True:
que = DBN.queueForDownLoad
if not que.empty():
url, src = que.get()
pPer = PPer(src)
temp = pPer.pageParser()
print("=" * 30)
print(url)
for item in temp:
print(item)
# DB.data2DB(data=[url] + temp)
else:
time.sleep(1)
def spiderMain():
# 主程序
dler = Dler()
dler.downLoad(100)
DB = DBService(dbName='jddata', tableName='thirdPartShopAppID')
DB.createTable(tableTitle=['shopHref','appID'])
while True:
que = DBN.queueForDownLoad
if not que.empty():
url, src = que.get()
pPer = PPer(src)
temp = pPer.pageParser()
print('='*30)
print(url)
print(temp)
if temp:
DB.data2DB(data=[url] + temp)
else:
time.sleep(1)
def get_parser(url, driver):
import random
time.sleep(abs(random.gauss(5, 5)))
driver.get(url)
print(driver.title)
contacts_name = "-"
contacts_sex = "-"
contacts_job = "-"
try:
contacts_name = driver.find_element_by_css_selector(".contact-info .membername").text
contacts_sex = driver.find_element_by_css_selector(".contact-info>dl>dd").text.split(" ")[1]
contacts_job = driver.find_element_by_css_selector(".contact-info>dl>dd").text.split("（")[1]
contacts_job = contacts_job.split("）")[0]
except:
pass
phone_frames = driver.find_elements_by_css_selector(".contcat-desc dl")
cell_phone = "-"
tel_phone = "-"
fax_phone = "-"
shop_addr = "-"
for i in range(len(phone_frames)):
text = driver.find_element_by_css_selector(".contcat-desc dl:nth-child(" + str(i + 1) + ") dt").text.strip()
if text == u"移动电话：":
cell_phone = driver.find_element_by_css_selector(".contcat-desc dl:nth-child(" + str(i + 1) + ") dd").text
continue
elif text == u"电 话：":
tel_phone = driver.find_element_by_css_selector(".contcat-desc dl:nth-child(" + str(i + 1) + ") dd").text
continue
elif text == u"传 真：":
fax_phone = driver.find_element_by_css_selector(".contcat-desc dl:nth-child(" + str(i + 1) + ") dd").text
continue
elif text == u"地 址：":
shop_addr = driver.find_element_by_css_selector(".contcat-desc dl:nth-child(" + str(i + 1) + ") dd").text
continue
spider_time = time.strftime("%Y-%m-%d %X", time.localtime())
result = [contacts_name, contacts_sex, contacts_job, cell_phone, tel_phone, fax_phone, shop_addr, spider_time, url]
DB = DBService(dbName="alibaba", tableName="alibaba_cow_powder_phone")
DB.data2DB(data=result)
def getCategoryAndStartUrl():
import json
global queue_for_url_targetBase
queue_for_url_targetBase = Queue(0)
src = myUrlOpen.requestByProxy('http://dc.3.cn/category/get?callback=getCategoryCallback')
srcTemp = src.split('(', 1)[1][:-1]
srcTemp = srcTemp.decode('gbk', 'ignore')
srcJson = json.loads(srcTemp)['data']
category = []
for Fi in srcJson:
targetFi = Fi['s']
for Se in targetFi:
targetSeTitle = Se['n']
targetSe = Se['s']
for Ti in targetSe:
targetTiTitle = Ti['n']
targetTi = Ti['s']
for Fo in targetTi:
targetFoTitle = Fo['n']
categoryTemp = [targetSeTitle.split('|')[1], targetSeTitle.split('|')[0],
targetTiTitle.split('|')[1], targetTiTitle.split('|')[0],
targetFoTitle.split('|')[1], targetFoTitle.split('|')[0]]
category.append(categoryTemp)
queue_for_url_targetBase.put((targetFoTitle.split('|')[1], targetFoTitle.split('|')[0]))
db = DBService(dbName='jddata', tableName='jdkeyword')
db.createTable(tableTitle=['category_fi_name', 'category_fi', 'category_se_name', 'category_se', 'category_ti_name',
'category_ti'])
db.data2DB(data=category)
# for item in category:
# print(item)
# try:
# db.data2DB(data=item)
# except:continue
# print('=' * 50)
return category
def dataGen():
comDict = companyInfo()
proDict = productInfo()
dict = {}
for item in comDict.items():
if item[0] in proDict.keys():
dict[item[0]] = comDict[item[0]] + [proDict[item[0]]]
else:
continue
data = [item[1] for item in dict.items()]
db1 = DBService(dbName='jddata', tableName='thirdPartShopInfo')
title = db1.getTableTitle()
title = title + ['commnetCount']
print(title)
db2 = DBService(dbName='jddata', tableName='thirdPartShopInfoAddtest')
db2.createTable(tableTitle=title)
db2.data2DB(data=data)
#coding:utf8 __author__ = '613108' from ms_spider_fw.DBSerivce import DBService dbs=DBService(dbName='elec_platform',tableName='tmall_baseinfo_everyweek') data=dbs.getData() data=[item for item in data if int(item[-2])>=35] print(len(data))
def putDataIntoDB(path):
data = getData(path=path)
dbs = DBService(dbName='elec_platform', tableName='tmall_baseinfo_weekly_2016')
dbs.data2DB(data=data)
print(len(judgePageHref))
return judgePageHref
def craweldhref():
db = DBService('elec_platform', 'yms_tmall_shopinfo_com_withoutjudge')
href = db.getData(var='href')
href = [item[0] for item in href]
F = lambda x: x[:-1] if x[-1] == '/' else x
href = map(F, href)
print(len(href))
return href
def href():
temp1 = commentHrefList()
temp2 = craweldhref()
temp2 = set(temp2)
temp3 = []
for item in temp1:
if not item[1] in temp2:
temp3.append(list(item))
else:
continue
temp3=[[item[0],item[1]+'/','http://rate.taobao.com/user-rate-'+item[2]+'.htm']for item in temp3]
return temp3
temp = href()
db=DBService('elec_platform', 'yms_tmall_shopinfo_com_withoutjudge')
db.data2DB(data=temp,tableTitle=['name','href','judgepage_href'])
def startUrlList(self):
db = DBService(dbName='jddata', tableName='thirdPartShopInfo')
data = db.getData(var='shopHref', distinct=True)
data = [item[0] for item in data]
return data
__author__ = '613108' from ms_spider_fw.DBSerivce import DBService dbs = DBService(dbName='jddata', tableName='thirdPartShopInfo') companyCount = dbs.getData(var='companyName', distinct=True) shopCount1 = dbs.getData(var='shopHref', distinct=True) shopCount2 = dbs.getData(var='shopName', distinct=True) gradeHref = dbs.getData(var='gradeHref', distinct=True) print len(companyCount) print len(shopCount1) print len(shopCount2) print len(gradeHref)
def startUrlList(self):
db = DBService(dbName="jddata", tableName="thirdPartShopAppID")
data = db.getData(var="appID")
data = ["http://mall.jd.com/view_search-" + item[0] + "-0-5-1-24-1.html" for item in data if item[0]]
return data
import pymysql
import json
from ms_spider_fw.DBSerivce import DBService
import threading
import Queue
json_file_queue = Queue.Queue(0)
connect_jd = pymysql.connect(
host='10.118.187.12',
user='******',
passwd='admin',
database='platform_data'
)
connect_dict = {'host': '10.118.187.12', 'user': '******', 'passwd': 'admin', 'charset': 'utf8'}
dbs = DBService(dbName='platform_data', tableName='jd_data_temp_0326', **connect_dict)
dbs.createTable(
tableTitle=
map(lambda x: x.strip(),
'shop_name, addr, com_name, shop_href, cate_0, score_summary, '
'express_score, product_score, service_score,product_href, vender_id, '
'sku_id, size_count'.split(','))
)
def get_min_max_id():
sql_min = 'SELECT MIN(id) FROM jd_product_detail'
sql_max = 'SELECT MAX(id) FROM jd_product_detail'
cur = connect_jd.cursor()
cur.execute(sql_min)
min_id = cur.fetchall()
reload(sys)
sys.setdefaultencoding('utf8')
# config_text
db_name = 'platform_data'
table_name = 'suning'
table_title = 'product_url,catalogue,sub_catalogue,product_title,promotion_desc,origin_price,price,' \
'product_stars,comment_count,sending_service,other_service,product_params,shop_name,' \
'shop_href,product_rating,product_rating_avg,serice_rating,service_rating_avg,express_rating,' \
'express_rating_avg,com_name_tel,crawl_time'
url_start = 'http://www.suning.com/emall/pgv_10052_10051_1_.html' # start url for crawl,string
connect_dict = {'host': '10.118.187.12', 'user': '******', 'passwd': 'admin', 'charset': 'utf8'}
# script
db_server = DBService(dbName=db_name, tableName=table_name, **connect_dict)
if not db_server.isTableExist():
db_server.createTable(tableTitle=table_title.split(','))
class Handler(BaseHandler):
crawl_config = {
}
@every(minutes=24 * 60)
def on_start(self):
self.crawl(url_start, callback=self.step_first)
@config(age=2 * 24 * 60 * 60)
def step_first(self, response):
