def pconedetect():
url = "https://www.pcone.com.tw/api/merchant/products?items_per_page=1000&merchant_id=2945567&page=1"
my_headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'}
gotrq = requests.get(url,headers = my_headers)
data = json.loads(gotrq.text) #轉成python dict
pconeIDAry = []
for i in range(len(data["products"])):
pconeIDAry.append(data["products"][i]["display_id"])
GOTData = getsheet('商品ID!O:O') #獲取試算表所有資料
GOTDataAry = []
errorID = []
for i in range(len(GOTData)):
try:
GOTDataAry.append(GOTData[i][0]) #提取試算表資料
except:
GOTDataAry.append("") #空直例外
for i in range(len(pconeIDAry)):#找網頁上架ID在不在 試算表中
try:
GOTDataAry.index(pconeIDAry[i])
except: #找不到的話
errorID.append(pconeIDAry[i])
for i in range(len(errorID)):
output.insert(1.0,str(errorID[i])+"\n")
output.insert(1.0,"偵測完成\n")
def getALLpcd():
prdidData = getsheet('商品ID!K:L') #獲取試算表所有資料
wiAry = []
tiAry = []
wrval = []
for row in range(len(prdidData)):
wrval.append("")
for row in range(len(prdidData)):
print(str(row) + "/" + str(len(prdidData)))
try:
if prdidData[row][0]:
time.sleep(0.5) #PC會檔大量讀取
gotstock = getpcd(prdidData[row][0]) #gotstock 得到PC網頁的資料
for i in range(len(gotstock["prd"])): #依網頁資料款式的種類數量迴圈
if gotstock["prd"][i][0] == prdidData[row][
1]: #獲取的款式ID 等於 試算表上的款式ID
wrval[row] = [gotstock["prd"][i][1]] #指派數量資料
if wrval[row] == "":
wrval[row] = ["款式ID錯誤"]
else:
wrval[row] = ["商品ID錯誤"]
except:
try:
if prdidData[row][0]:
wrval[row] = ["錯誤或下架"]
except:
wrval[row] = [""]
wrval[0][0] = "PC梓原" + time.strftime("%m/%d", time.localtime())
delsheet("商品ID!V:V")
writesheet("商品ID!V1", wrval)
print("OK")
def getALLpcone():
prdidData = getsheet('商品ID!O:P') #獲取試算表所有資料
wiAry=[]
tiAry= []
wrval = []
for row in range(len(prdidData)):
wrval.append("")
for row in range(len(prdidData)):
print(str(row)+"/"+str(len(prdidData)))
try:
if prdidData[row][0]:
gotstock = getpcone(prdidData[row][0])
for i in range(len(gotstock["prd"])):
if gotstock["prd"][i][0] == prdidData[row][1]:
wrval[row] = [gotstock["prd"][i][1]]
if wrval[row] == "":
wrval[row] = ["款式ID錯誤"]
except:
try:
if prdidData[row][0]:
wrval[row] = ["錯誤或下架"]
except:
wrval[row] = [""]
wrval[0][0] = "Pcone" + time.strftime("%m/%d", time.localtime())
delsheet("商品ID!Q:Q")
writesheet("商品ID!Q1",wrval)
print("OK")
def pcddetect():
allid = []
for page in range(1, 200):
#登錄後才能訪問的網頁
url = 'http://seller.pcstore.com.tw/S188431702/plist_dt.htm?s=S188431702&c=&skw=&pg=' + str(
page) + '&sr=1&pp=50'
#瀏覽器登錄後得到的cookie，也就是剛才複製的字符串
cookie_str = r'cbj=IqhLsP6..LOKMq6kVcXtnWgBVcXtnqojj' #######################這邊要研究
my_headers = {
'user-agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}
#把cookie字符串處理成字典，以便接下來使用
cookies = {}
for line in cookie_str.split(
';'): #cookie_str.split(';') 依分號 分割成陣列 並列出
key, value = line.split('=', 1) #將陣列依序指派給key value
cookies[key] = value #新增物件
session = requests.Session()
res = session.get(url, cookies=cookies, headers=my_headers)
soup = BeautifulSoup(
res.text, "html.parser") #"html.parser" html解析器 將html 轉為bs4格式操作
html = soup.find_all('a', 'hotProdList')
for link in html:
linkID = link['href'].replace('/S188431702/',
'').replace('.htm', '')
allid.append(linkID)
if len(html) < 50:
break
output.insert(1.0, "\n")
GOTData = getsheet('商品ID!M:M')
takeid = []
for i in range(len(GOTData)):
try:
takeid.append(GOTData[i][0])
except:
continue
errorid = []
for i in range(len(allid)):
try:
takeid.index(allid[i]) #看試算表尚存不存在網頁ID
except:
output.insert(1.0, str(allid[i]) + "\n")
output.insert(1.0, "偵測完成\n")
def yahoodetect():
allid = []
for page in range(1, 200):
try:
output.insert(1.0, ".")
url = "https://tw.bid.yahoo.com/booth/Green-Forest-Y3489416698?bfe=1&page=" + str(
page)
my_headers = {
'user-agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}
gotrq = requests.get(url, headers=my_headers)
soup = BeautifulSoup(
gotrq.text,
"html.parser") #"html.parser" html解析器 將html 轉為bs4格式操作
yahoohtml = soup.find_all('div', 'item-wrap')
if len(yahoohtml) == 0: #找完跳出
break
for i in range(len(yahoohtml)):
allid.append(yahoohtml[i]['data-mid'])
except:
print("end")
break
output.insert(1.0, "\n")
GOTData = getsheet('商品ID!E:E')
takeid = []
for i in range(len(GOTData)):
try:
takeid.append(GOTData[i][0])
except:
continue
errorid = []
for i in range(len(allid)):
try:
takeid.index(allid[i]) #看試算表尚存不存在網頁ID
except:
output.insert(1.0, str(allid[i]) + "\n")
output.insert(1.0, "偵測完成\n")
def rutendetect():
allid = []
for page in range(1, 200):
output.insert(1.0, ".")
url = "http://class.ruten.com.tw/user/index00.php?s=ting865290&p=" + str(
page)
my_headers = {
'user-agent':
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}
gotrq = requests.get(url, headers=my_headers)
soup = BeautifulSoup(
gotrq.text, "html.parser") #"html.parser" html解析器 將html 轉為bs4格式操作
rutenhtml = soup.find_all('div',
'rt-product-tag-container tagging-class')
end = soup.find_all("div", class_="item-img-wrap")
for i in range(len(rutenhtml)):
try: #若裡面沒有重複值則新增
allid.index(rutenhtml[i]['name'])
except:
allid.append(rutenhtml[i]['name'])
if len(end) == 0:
break
output.insert(1.0, "\n")
GOTData = getsheet('商品ID!G:G')
takeid = []
for i in range(len(GOTData)):
try:
takeid.append(GOTData[i][0])
except:
continue
errorid = []
for i in range(len(allid)):
try:
takeid.index(allid[i]) #看試算表尚存不存在網頁ID
except:
output.insert(1.0, str(allid[i]) + "\n")
output.insert(1.0, "偵測完成\n")
def getALLRuten():
prdidData = getsheet('商品ID!G:H') #獲取試算表所有資料
wiAry=[]
tiAry= []
wrval = [] #寫入的陣列
for row in range(len(prdidData)):#新增同列數陣列
wrval.append([""])
for row in range(len(prdidData)):
#for row in range(5,12):
print(str(row)+"/"+str(len(prdidData))) #進度
try:
if prdidData[row][0]:
gotstock = getruten(prdidData[row][0]) #讀取網頁
if type(gotstock['prd']) == type(""): #如果prd為文字則為無款式
wrval[row] = [gotstock['prd']]
else:#有款式
for i in range(len(gotstock["prd"])):
if gotstock["prd"][i][0] == prdidData[row][1]: #有找到款式ID
wrval[row] = [gotstock["prd"][i][1]] #寫入資料
if gotstock["prd"][i][3] == "N": #如果發現款式是關閉
wrval[row]=["款式關閉"]
if wrval[row] == "":#都沒有找到
wrval[row] = ["款式ID錯誤"]
if gotstock["state"] == True:
wrval[row] = ["下架"]
except: #有可能ID錯誤，有可能ID無值
try:
if prdidData[row][0]:#ID錯誤
wrval[row] = ["商品ID錯誤或無款式ID"]
except:
wrval[row] = [""]
wrval[0][0] = "Ruten" + time.strftime("%m/%d", time.localtime())#寫入第一列
delsheet("商品ID!T:T") #刪除原有資料
writesheet("商品ID!T1",wrval) #寫入資料
return wrval
print("OK")
def getALLYahoo():
prdidData = getsheet('商品ID!E:F') #獲取試算表所有資料
wiAry = []
tiAry = []
wrval = [] #寫入的陣列
for row in range(len(prdidData)): #新增同列數陣列
wrval.append([""])
for row in range(len(prdidData)):
#for row in range(5,12):
print(str(row) + "/" + str(len(prdidData))) #進度
try:
if prdidData[row][0]:
gotstock = getyahoo(prdidData[row][0])
if type(gotstock['prd']) == type(""): #如果prd為文字則為無款式
wrval[row] = [gotstock['prd']]
else: #有款式
for i in range(len(gotstock["prd"])):
if gotstock["prd"][i][0] == prdidData[row][1]:
wrval[row] = [gotstock["prd"][i][1]]
if wrval[row] == "": #都沒有找到
wrval[row] = ["款式ID錯誤"]
if gotstock["state"] == '3':
wrval[row] = ["下架"]
except: #有可能ID錯誤，有可能ID無值
try:
if prdidData[row][0]: #ID錯誤
wrval[row] = ["商品ID錯誤或無款式ID"]
except:
wrval[row] = [""]
wrval[0][0] = "Yahoo" + time.strftime("%m/%d", time.localtime())
delsheet("商品ID!S:S")
writesheet("商品ID!S1", wrval)
return wrval
print("OK")