import bs4 import requests import xlwt import datetime params={ 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36' } date = datetime.datetime.now().strftime('%Y-%m-%d') # 給文件打上時間戳，便于數據更新 url = 'https://uland.taobao.com/sem/tbsearch?refpid=mm_26632360_8858797_29866178&keyword=%E4%B9%A6%E7%B1%8D&clk1=da382fc3cc2efef28fd1c72638a78aca&upsId=da382fc3cc2efef28fd1c72638a78aca&spm=a2e0b.20350158.search.1&pid=mm_26632360_8858797_29866178&union_lens=recoveryid%3A201_11.170.86.131_4623454_1620196433004%3Bprepvid%3A201_11.170.86.131_4623454_1620196433004' # 網址 # payload = {'SearchText': 'taob', 'page': '1', 'ie': 'utf8', 'g': 'y'} # 字典傳遞url參數 resp = requests.get(url,headers=params) soup = bs4.BeautifulSoup(resp.text, "html.parser") print(resp.url) # 打印訪問的網址 # print(resp.text) print(resp.status_code) resp.encoding = 'utf-8' # 設置編碼 title=[] # 標題 all_title = soup.find_all('span',class_="title-text") print(all_title) # for j in all_title: # soup_title = bs4.BeautifulSoup(str(j), "html.parser") # title.append(soup_title.span.string) # print(title) # # # 店鋪名稱 # all_store = soup.find_all('span', class_="shopNick") # for k in all_store: # soup_store = bs4.BeautifulSoup(str(k), "html.parser", ) # store.append(soup_store.span.string) # # # 價格 # all_price = soup.find_all('span', class_="pricedetail") # for l in all_price: # soup_price = bs4.BeautifulSoup(str(l), "html.parser") # price.append(soup_price.strong.string) # # # 銷售量 # all_paynum = soup.find_all('span', class_="payNum") # for m in all_paynum: # soup_paynum = bs4.BeautifulSoup(str(m), "html.parser") # paynum.append(soup_paynum.span.string) # # # 數據驗證 # print(len(title)) # print(len(store)) # print(len(price)) # print(len(paynum))

?

總結

以上是生活随笔為你收集整理的爬虫-淘宝的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。