from urllib.request import *
import re
import json
import urllib.parse
import urllib.request
from bs4 import BeautifulSoup
import random
import re
import json
import xlrd
import csv
def randHeader():
head_connection = ['Keep-Alive', 'close']
head_accept = ['text/html, application/xhtml+xml, */*']
head_accept_language = ['zh-CN,fr-FR;q=0.5', 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']
head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',
'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',
'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',
'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']
header = {
'Connection': head_connection[0],
'Accept': head_accept[0],
'Accept-Language': head_accept_language[1],
'User-Agent': head_user_agent[random.randrange(0, len(head_user_agent))]
}
return header
def getPartNumber(no):
url = 'http://catalog.monroe.com/catalogPart/partResults.do?&domain=monroe&locale=en&partNumber='+no+'&selection=findPart'
# print(url)
req = urllib.request.Request(url= url , headers=randHeader())
webpage = urllib.request.urlopen(req)
html = str(webpage.read())
html = re.findall("^b'(.*)'", html)[0]
if html.strip()=="null":
print("kong")
return "0"
s = str(html).replace("\\xae", "") # 转成str,替换编码174的符号为空
sjson = re.findall("\[(.*?)\]",s)[0]
sjson = json.loads(sjson)
selectedPartId = sjson["value"]
return selectedPartId
def getTECHandWhereUsed(no):
# print(no)
selectedPartId = getPartNumber(no)
if selectedPartId== "0":
file2 = open("tech_specs.csv", "a", newline="")
writer = csv.writer(file2)
writer.writerow([no, "#", "#" ,"#", "#" ,"#" ,"#", "#" ,"#" ,"#", "#" ])
file1 = open("where_used.csv", "a", newline="")
writer1 = csv.writer(file1)
writer1.writerow([no, "#"])
return
url = "http://catalog.monroe.com/catalogPart/partResults.do?&selectedCatalogId=974&selectedPartId="+str(selectedPartId)+"&selection=partDetails"
req = urllib.request.Request(url= url , headers=randHeader())
webpage = urllib.request.urlopen(req)
html = webpage.read() # 字节编码
s = str(html).replace("\\xae","") #转成str,替换编码174的符号为空
s = re.findall("^b'(.*)'", s)[0]
s = s.replace("\\\\","\\") #将\\转换成\
s = s.replace("\\'" , "'")#将\'转换成'
s = json.loads(s )
att = s["part"]["attributes"] #定位属性
for i in att:
for key , value in i.items(): #选择指定的属性
key = str(key)
if key == "Body Type":
bType = value
elif key == "Body Length":
bLength = value
elif key == "Compressed Length":
cLength = value
elif key == "Extended Length":
eLength = value
elif key == "Travel Length":
tlength = value
elif key == "Dust Shield":
dShield = value
elif key == "Parts Pack(s)":
ppack = value
elif key == "Compressed Bumper Stop":
cBStop = value
elif key == "Extended Bumper Stop":
ebStop = value
elif key == "Extended Hydraulic Lockout":
ehLockout = value
# print(bType, bLength, cLength , eLength , tlength , dShield , ppack , cBStop , ebStop , ehLockout)
file2 = open("tech_specs.csv","a" , newline="")
writer = csv.writer(file2)
writer.writerow([no , bType, bLength, cLength , eLength , tlength , dShield , ppack , cBStop , ebStop , ehLockout])
result = []
ve = s["vehicles"] #定位车型
for i in ve:
make = i["make"]
modle = i["models"]
for i in modle :
model = i["model"]
app = i["applications"]
for i in app:
location = i["location"]
startYear = i["startYear"]
endYear = i["endYear"]
fitment = str(startYear)+" - "+ str(endYear) + " "+ str(location).upper()
result.append([make , model , fitment])
# print(result)
file1 = open("where_used.csv","a",newline="")
writer1 = csv.writer(file1)
for fitment in result:
writer1.writerow([no , fitment])
#读入no
data = xlrd.open_workbook("no.xlsx") #代开excel
table = data.sheet_by_name("Sheet1") #读sheet
nrows = table.nrows
cols = table.ncols
nos = []
for i in range(1,nrows): #指定从1开始,到最后一列,跳过表头
for j in range(cols):
ctype = table.cell(i , j).ctype #判断python读取的返回类型 0 --empty,1 --string, 2 --number(都是浮点), 3 --date, 4 --boolean, 5 --error
no = table.cell(i, j).value #获取单元格的值
if ctype == 2 :
no = str(int(no)) #将浮点转换成整数再转换成字符串
nos.append(no)
#写入csv表头
with open("tech_specs.csv","a",newline="") as f:
head = ["no","bType", "bLength", "cLength" , "eLength" , "tlength" , "dShield" , "ppack" , "cBStop" , "ebStop" , "ehLockout"]
writer =csv.DictWriter(f, fieldnames=head)
writer.writeheader()
with open("where_used.csv","a" , newline="") as wf :
head= ["no", "fitment"]
writer2 = csv.DictWriter(wf , fieldnames= head)
writer2.writeheader()
for no in nos:
print(no)
getTECHandWhereUsed(no)
# getTECHandWhereUsed("171340R")
python 代码中有的正则表达式消失的需要参考上面修改
from urllib.request import *
import re
import json
import urllib.parse
import urllib.request
from bs4 import BeautifulSoup
import random
import re
import json
import xlrd
import csv
def randHeader():
head_connection = ['Keep-Alive', 'close']
head_accept = ['text/html, application/xhtml+xml, */*']
head_accept_language = ['zh-CN,fr-FR;q=0.5', 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']
head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',
'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',
'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',
'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',
'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',
'Opera/9.27 (Windows NT 5.2; U; zh-cn)',
'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',
'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',
'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',
'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',
'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',
'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']
header = {
'Connection': head_connection[0],
'Accept': head_accept[0],
'Accept-Language': head_accept_language[1],
'User-Agent': head_user_agent[random.randrange(0, len(head_user_agent))]
}
return header
def getPartNumber(no):
url = 'http://catalog.monroe.com/catalogPart/partResults.do?&domain=monroe&locale=en&partNumber='+no+'&selection=findPart'
# print(url)
req = urllib.request.Request(url= url , headers=randHeader())
webpage = urllib.request.urlopen(req)
html = str(webpage.read())
html = re.findall("^b'(.*)'", html)[0]
if html.strip()=="null":
print("kong")
return "0"
s = str(html).replace("\\xae", "") # 转成str,替换编码174的符号为空
sjson = re.findall("\[(.*?)\]",s)[0]
sjson = json.loads(sjson)
selectedPartId = sjson["value"]
return selectedPartId
def getTECHandWhereUsed(no):
# print(no)
selectedPartId = getPartNumber(no)
if selectedPartId== "0":
file2 = open("tech_specs.csv", "a", newline="")
writer = csv.writer(file2)
writer.writerow([no, "#", "#" ,"#", "#" ,"#" ,"#", "#" ,"#" ,"#", "#" ])
file1 = open("where_used.csv", "a", newline="")
writer1 = csv.writer(file1)
writer1.writerow([no, "#"])
return
url = "http://catalog.monroe.com/catalogPart/partResults.do?&selectedCatalogId=974&selectedPartId="+str(selectedPartId)+"&selection=partDetails"
req = urllib.request.Request(url= url , headers=randHeader())
webpage = urllib.request.urlopen(req)
html = webpage.read() # 字节编码
s = str(html).replace("\\xae","") #转成str,替换编码174的符号为空
s = re.findall("^b'(.*)'", s)[0]
s = s.replace("\\\\","\\") #将\\转换成\
s = s.replace("\\'" , "'")#将\'转换成'
s = json.loads(s )
att = s["part"]["attributes"] #定位属性
for i in att:
for key , value in i.items(): #选择指定的属性
key = str(key)
if key == "Body Type":
bType = value
elif key == "Body Length":
bLength = value
elif key == "Compressed Length":
cLength = value
elif key == "Extended Length":
eLength = value
elif key == "Travel Length":
tlength = value
elif key == "Dust Shield":
dShield = value
elif key == "Parts Pack(s)":
ppack = value
elif key == "Compressed Bumper Stop":
cBStop = value
elif key == "Extended Bumper Stop":
ebStop = value
elif key == "Extended Hydraulic Lockout":
ehLockout = value
# print(bType, bLength, cLength , eLength , tlength , dShield , ppack , cBStop , ebStop , ehLockout)
file2 = open("tech_specs.csv","a" , newline="")
writer = csv.writer(file2)
writer.writerow([no , bType, bLength, cLength , eLength , tlength , dShield , ppack , cBStop , ebStop , ehLockout])
result = []
ve = s["vehicles"] #定位车型
for i in ve:
make = i["make"]
modle = i["models"]
for i in modle :
model = i["model"]
app = i["applications"]
for i in app:
location = i["location"]
startYear = i["startYear"]
endYear = i["endYear"]
fitment = str(startYear)+" - "+ str(endYear) + " "+ str(location).upper()
result.append([make , model , fitment])
# print(result)
file1 = open("where_used.csv","a",newline="")
writer1 = csv.writer(file1)
for fitment in result:
writer1.writerow([no , fitment])
#读入no
data = xlrd.open_workbook("no.xlsx") #代开excel
table = data.sheet_by_name("Sheet1") #读sheet
nrows = table.nrows
cols = table.ncols
nos = []
for i in range(1,nrows): #指定从1开始,到最后一列,跳过表头
for j in range(cols):
ctype = table.cell(i , j).ctype #判断python读取的返回类型 0 --empty,1 --string, 2 --number(都是浮点), 3 --date, 4 --boolean, 5 --error
no = table.cell(i, j).value #获取单元格的值
if ctype == 2 :
no = str(int(no)) #将浮点转换成整数再转换成字符串
nos.append(no)
#写入csv表头
with open("tech_specs.csv","a",newline="") as f:
head = ["no","bType", "bLength", "cLength" , "eLength" , "tlength" , "dShield" , "ppack" , "cBStop" , "ebStop" , "ehLockout"]
writer =csv.DictWriter(f, fieldnames=head)
writer.writeheader()
with open("where_used.csv","a" , newline="") as wf :
head= ["no", "fitment"]
writer2 = csv.DictWriter(wf , fieldnames= head)
writer2.writeheader()
for no in nos:
print(no)
getTECHandWhereUsed(no)
# getTECHandWhereUsed("171340R")