python3實踐-從某網站擷取資料，python3擷取

python3實踐-從某網站擷取資料，python3擷取

 

作為一個新手，自己邊看邊實踐一些簡單的實際應用，下面的程式是從某個網站上擷取需要的資料。

程式寫的可能並不好，但基本上實現了自己的需求。

希望有高手來指點下~~

 1 # Code based on Python 3.x 2 # _*_ coding: utf-8 _*_ 3 # __Author: "LEMON" 4  5 from bs4 import BeautifulSoup 6 import requests 7 import csv 8  9 urllink = 'http://www.bjets.com.cn/article/jyxx/?'10 links = []11 for n in range(2, 40):12     #頁面總數為39頁，需要自己先從網頁判斷，也可以從頁面抓取，後續可以完善13     link = urllink + str(n)14     links.append(link)15 links.insert(0, urllink)16 # print(links)17 18 for url in links:19 20     rep = requests.get(url)21     # content = rep.text.encode(rep.encoding).decode('utf-8')22     # # 直接用requests時，中文內容需要轉碼23 24     soup = BeautifulSoup(rep.content, 'html.parser')25 26     # print(soup.prettify())27     # # prettify()28 29     body = soup.body30     data = body.find('div', {'class': 'list_right'})31 32     # table title33     titles = data.find_all('th')34 35     title = []36     for x in titles:37         title.append(x.text)38     # print(title)39 40     quotes = data.find_all('tr')41     quotes1 = quotes[1:len(quotes)]42     # print(quotes1)43 44     list1 = []45     for x in quotes1:46         for y in x.find_all('td'):47             list1.append(y.text)48     # print(list1)  # list為每日資料的總列表49 50     date = []51     volumes = []52     meanprice = []53     totalmoney = []54 55     for i in range(0, len(list1)):56         if i % 4 == 0:57             date.append(list1[i])58         elif i % 4 == 1:59             volumes.append(list1[i])60         elif i % 4 == 2:61             meanprice.append(list1[i])62         else:63             totalmoney.append(list1[i])64 65     # print(date)66     # print(volumes)67     # print(meanprice)68     # print(totalmoney)69 70     final = []71     for i in range(0, len(date)):72         temp = [date[i], volumes[i], meanprice[i], totalmoney[i]]73         final.append(temp)74     # print(final)75     with open('bj_carbon.csv', 'a', errors='ignore', newline='') as f:76         f_csv = csv.writer(f)77         f_csv.writerows(final)