# python爬蟲-大奇蹟日

#### 會用到requests 跟 美麗的湯(BeautifulSoup)
#### 先使用pip install requests， pip install BeautifulSoup

import requests
from bs4 import BeautifulSoup
#### 今天是大奇蹟日，所以我們要爬台股的頂梁柱: 半導體類股[](https://)https://www.cnyes.com/twstock/index2real.aspx?stockType=T&groupId=24&stitle=%e5%8d%8a%e5%b0%8e%e9%ab%94

#### 透過requests.get前往該網頁，由於要把我們假裝成真的使用者，在headers裡添加一些混淆視聽的 "User-Agent"
response = requests.get(
"https://www.cnyes.com/twstock/index2real.aspx?stockType=T&groupId=24&stitle=%e5%8d%8a%e5%b0%8e%e9%ab%94",
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36"
})
#### 以Beautiful Soup 解析 HTML 程式碼
soup = BeautifulSoup(response.text, "html.parser")
data = soup.select("table tr td")
#### 在網頁畫面開啟開發人員工具(F12)，可得知我們要爬的資料，在html的標籤裡的table > tr > td
#### data = soup.select("table tr td") 選取到我們要的欄位
#### print(data)出來看看
[<td>13:30:00</td>, <td><a href="/twstock/profile/2302.htm">2302</a></td>, <td>.....]

#### 設a為空字串，對data做for迴圈，由於每11筆會得到完整一檔股票的資料，增加以下判斷式，利用字串串接，最後print出來

a = ''
for i in range(len(data)):
if (i+1) % 11 == 0:
a = a + data[i].text + ' '
print(a)
a = ''
else:
a = a + data[i].text + ' '

#### 結果如下

#### 完整程式碼
import requests
from bs4 import BeautifulSoup

response = requests.get(
"https://www.cnyes.com/twstock/index2real.aspx?stockType=T&groupId=24&stitle=%e5%8d%8a%e5%b0%8e%e9%ab%94",
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36"
})
soup = BeautifulSoup(response.text, "html.parser")
data = soup.select("table tr td")

a = ''
for i in range(len(data)):
if (i+1) % 11 == 0:
a = a + data[i].text + ' '
# if a.split(' ')[1] == '2330':
print(a)
a = ''
else:
a = a + data[i].text + ' '

#### 只想看台股不死鳥台積電，可將# if a.split(' ')[1] == '2330'註解打開