# 實例操作-1 爬取系網教授gmail
### 1.先檢查robots.txt

import requests
from bs4 import BeautifulSoup

url = "https://www.che.nthu.edu.tw/robots.txt"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
print(soup)

> output:
>See http://www.robotstxt.org/wc/norobots.html for documentation on how to use the robots.txt file
>To ban all spiders from the entire site uncomment the next >two lines:
>User-agent: *
>Disallow: /

### 2.開始爬取資料

import requests
from bs4 import BeautifulSoup

f = open("Professors_Gmail", "w")

#系網教授簡介共有3頁
for page in range(1,4):
    #觀察網址變化跟page有關，將其代碼取下
    response = requests.get("https://www.che.nthu.edu.tw/zh_tw/Members/Appointed?page_no=" + str(page) + "&") 
    #轉成HTML形式
    soup = BeautifulSoup(response.text, "html.parser")
    #選取特定資料
    sel_names = soup.select("span.i-member-value member-data-value-name a")
    sel_gmails = soup.select("span.i-member-value member-data-value-email a")

    #寫入檔案
    for i in range(len(sel_gmails)):
        f.write(sel_names[i].text + ":" + sel_gmails[i].text + '\n')

f.close()

>Professors_Gmail:
>
>蔡德豪 De-Hao Tsai: [e-mail]
黃振煌 Jen-Huang （Tony） Huang: [e-mail]
宋信文 Hsing-Wen Sung: [e-mail]
汪上曉 David Shan-Hill Wong: [e-mail]
呂世源 Shih-Yuan Lu: [e-mail]
胡育誠 Yu-Chen Hu: [e-mail]
何榮銘 Rong-Ming Ho: [e-mail]
胡啟章 Chi-Chang Hu: [e-mail]
陳信文 Sinn-Wen Chen: [e-mail]
陳信龍 Hsin-Lung Chen: [e-mail]
陳壽安 Show-An Chen: [e-mail]
劉英麟 Ying-Ling Liu: [e-mail]
鄭西顯 Shi-Shang Jang: [e-mail]
段興宇 Hsing-Yu Tuan: [e-mail]
堀江正樹 Masaki Horie: [e-mail]
姚遠 Yuan Yao: [e-mail]
衛子健 Tzu-Chien Wei: [e-mail]
王潔 Jane Wang: [e-mail]
沈若樸 Claire Roa-Pu Shen: [e-mail]
區迪頤John Ou: [e-mail]
周鶴修 Ho-Hsiu Chou: [e-mail]
潘詠庭 Yung-Tin （Frank） Pan: [e-mail]
楊東翰Tung-Han Yang: [e-mail]
林育正Yu-Jeng Lin: [e-mail]
林昆翰 Kun-Han Lin: [e-mail]