Try   HackMD
tags: python

擷取網站資料

webbrowser模組：呼叫瀏覽器連到指定網址

根據指定網址開啟網頁




import webbrowser

webbrowser.open('http://www.yahoo.com.tw')

透過list開啟多個網頁










import webbrowser
locations = [
    '台北車站',
    '台中車站',
    '台北市中華路一段174-1號'
]

for i in locations:
    webbrowser.open('https://www.google.com/maps/search/' + i)

根據關鍵字找到google地圖所在位置





import webbrowser

add = input('請輸入要找尋的地點: ')
webbrowser.open('http://www.google.com/maps/search/' + add)

練習一

請根據以上範例修改
讓使用者輸入股票代號
開啟yahoo股市該代號的網頁（顯示開盤、收盤等資訊）

根據關鍵字顯示youtube影片列表





import webbrowser

keyword = input('請輸入要找尋的影片: ')
webbrowser.open('https://www.youtube.com/results?search_query=' + keyword)

requests模組：下載指定網址的網頁資料

pip3 install requests

根據網址下載網頁內容

















import requests

url1 = 'http://www.grandtech.info'
htmlfile1 = requests.get(url1)

print(htmlfile1)
print(htmlfile1.status_code)
print(htmlfile1.text)


url2 = 'http://www.grandtech.info/ddd'
htmlfile2 = requests.get(url2)

print(htmlfile2)
print(htmlfile2.status_code)
print(htmlfile2.text)

不同網址下的處理狀況





















import requests

url = 'http://www.grandtech.info'
# url = 'http://www.grandtech.info/dddd'
# url = 'http://abc.com.kk'

try:
    htmlfile = requests.get(url)

    print(htmlfile)
    print(htmlfile.status_code)
    print(htmlfile.text)


    if htmlfile.status_code == requests.codes.ok:
        print('取回網頁資料', len(htmlfile.text))
    else:
        print('網頁資料取得失敗')
except Exception as e:
    print('網頁取得失敗', e)

偽裝成一般瀏覽器抓取


















import requests

url = 'http://aaa.24ht.com.tw'

htmlfile = requests.get(url)

# headers = {
#     'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) \
#     AppleWebKit/537.36 (KHTML, Gecko) Chrome/45.0.2454.101 \
#     Safari/537.36'
# }
# htmlfile = requests.get(url, headers=headers)
htmlfile.encoding = 'utf8'

htmlfile.raise_for_status()

print(htmlfile.text)

透過網頁擷取資料存成檔案











import requests

url = 'https://www.yahoo.co.jp'

htmlfile = requests.get(url)

file_name = 'webpage.html'

with open(file_name, 'w', encoding='utf-8') as file_obj:
    file_obj.write(htmlfile.text)












import requests

url = 'https://www.google.com.tw/search?q={0}+food&oq={0}'

keyword = input('請輸入要找的關鍵字: ')
htmlfile = requests.get(url.format(keyword))

file_name = 'webpage.html'

with open(file_name, 'w', encoding='utf-8') as file_obj:
    file_obj.write(htmlfile.text)

下載PDF檔














import requests

url = 'https://www.taiwandns.com/wp-content/plugins/post2pdf-converter/post2pdf-converter-pdf-maker.php?id=4720&file=id&font=droidsansfallback&monospaced=droidsansfallback&fontsize=13&subsetting=0&ratio=1.35&header=1&title=1&wrap_title=0&logo=1&logo_file=logo.png&logo_width=60&footer=1&filters=1&shortcode=parse&ffamily=0'

htmlfile = requests.get(url)

file_name = 'webpage.pdf'

with open(file_name, 'wb') as file_obj:
    for content in htmlfile.iter_content(1024):
        size = file_obj.write(content)
        print(size)

pytube：下載youtube影片

pip install pytube




from pytube import YouTube

YouTube('http://youtube.com/watch?v=9bZkp7q19f0').streams.first().download()

下載成指定的影片格式(webm, mp4, 3gpp)




from pytube import YouTube

YouTube('https://www.youtube.com/watch?v=axHKi38q8ag').streams.filter(progressive=True, file_extension='mp4').first().download()

BeautifulSoup模組：解析html語法



pip install beautifulsoup4
pip install lxml

取得youtube指定關鍵字影片網址#1




















import requests
from bs4 import BeautifulSoup

youtube_url = 'https://www.youtube.com'
url = 'https://www.youtube.com/results?search_query='

keyword = input('請輸入要找的音樂關鍵字')
response = requests.get(url + keyword)
html_doc = response.text
soup = BeautifulSoup(html_doc, "lxml")

# print(soup.prettify()) # 把排版後的 html 印出來

div_result = soup.find('div', id='content')

a_result = div_result.find_all('a')

for a in a_result:
    print(youtube_url + a['href'], a.text)

取得youtube指定關鍵字影片網址#2 (改善結果）























import re
import requests
from bs4 import BeautifulSoup

youtube_url = 'https://www.youtube.com'

keyword = input('請輸入要找的歌曲關鍵字: ')
resp = requests.get('https://www.youtube.com/results?search_query=' + keyword)

soup = BeautifulSoup(resp.text, 'lxml')

# print(soup.prettify())
# print(soup.title)
# print(soup.title.name)
# print(soup.title.string)

# print(soup.a)
# print(soup.a['id'])

div_result = soup.find_all('a', 'yt-uix-tile-link')
for div in div_result:
    print(youtube_url + div['href'], div.string)

取得PTT指定版名的文章標題、文章網址
















































import requests
from bs4 import BeautifulSoup

base_url = 'https://www.ptt.cc'
template_url = base_url + '/bbs/{0}/index.html'
groups = {
    '八卦板': 'Gossiping',
    '電影板': 'Movie'
}


def get_dom(group):
    resp = requests.get(
        url=template_url.format(groups[group]),
        cookies={'over18': '1'}
    )
    if resp.status_code != 200:
        print('網址不正確:', resp.url)
        return None
    else:
        return resp.text

def get_title(dom):
    titles = []
    soup = BeautifulSoup(dom, "lxml")
    div_result = soup.find_all('div', 'r-ent')

    for div in div_result:
        res = div.find('div', 'title').find('a')

        if res:
            titles.append({
                'title': res.string,
                'url': base_url + res['href']
            })

    return titles


if __name__ == '__main__':
    dom = get_dom('電影板')
    
    if dom:
        titles = get_title(dom)

        for t in titles:
            print(t['url'], t['title'])

抓取yahoo股票資料
































import re
import requests
from bs4 import BeautifulSoup

yahoo_url = 'https://tw.stock.yahoo.com/q/q?s='

def convert_string(x):
    return x.string


keyword = input('請輸入要找的股票代號: ')

resp = requests.get(yahoo_url + keyword)

soup = BeautifulSoup(resp.text, 'lxml')

table_result = soup.find("table", width="750", border="2")



trs = table_result.find_all("tr")

ths = trs[0].find_all("th")
ths = map(convert_string, ths)

tds = trs[1].find_all("td")
tds = map(convert_string, tds)

stock_info = dict(zip(ths, tds))

print(stock_info)

產生有登入功能的簡易網站（額外補充，請略過）

參考網站：Create a simple login
範例檔案下載

1. 安裝套件及設定環境變數

pip3 install flask

2. 登入頁面（login.html）

請放到templates資料夾中










<!DOCTYPE html>
<form action="" method="post">
    帳號: <input type="text",  name="username", value= "">
    密碼: <input type="text",  name="password", value= "">
    <p><input type="submit" value="登入""></p>
    {% if error %}
       <b> 錯誤: </b> {{error}}
    {% endif %}
</form>

3. 登入成功頁面（secret.html）

請放到templates資料夾中







<!DOCTYPE html>
<html>
<p>歡迎登入本系統</p>
 
<a href="logout">登出</a>
</html>

4. 主程式（blog.py）

































from flask import * 

SECRET_KEY = 'this is a screct'

app = Flask(__name__) 
app.config.from_object(__name__)

@app.route("/login", methods = ['GET', 'POST'])    
def login():
    error = None
    if request.method == 'POST':
        if request.form['username'] == "amos" or request.form['password'] == 'python':
            session['logged_in'] = True
            return redirect(url_for('secret'))
        else:
            error = "使用者帳號或密碼錯誤"
 
    return render_template("login.html", error=error)


@app.route("/secret")    
def secret():
    return render_template("secret.html")
 
@app.route('/logout')
def logout():
    session.pop('logged_in', None)
    return redirect(url_for('login'))


if __name__ == '__main__':
      app.run(host='0.0.0.0', port=9000)

5. 啟用網站

在命令列執行以下程式

python3 blog.py

6. 打開瀏覽器登入此網站

  • localhost:9000/login

7. 測試擷取需要帳密的網頁














import requests

payload = {
    'username': 'amos',
    'password': 'python',
}

r = requests.post('http://localhost:8080/login', data=payload)

print(r.status_code) # 狀態碼
print(r.headers['content-type']) # 
print(r.encoding) # 文字編碼
print(r.text) # 取得網頁內容

補充

  • 若要讓其他電腦連到此網站，請先確認本電腦IP
    • ipconfig(windows)
    • ifconfig(linux)
  • 防火牆要打開指定的port(這裡是8080）
  • 若要讓區域網路以外可以連到此電腦，對外固定IP要設定轉址到本電腦

補充資料

網頁開發人員應了解的 HTTP 狀態碼
[Python] Requests 教學
給初學者的 Python 網頁爬蟲與資料分析 (1) 前言
Python 使用 Beautiful Soup 抓取與解析網頁資料，開發網路爬蟲教學
[Python] Beautifulsoup4 教學
Beautiful Soup 4 Cheatsheet

Last changed by 
 
amos tsai
python lover
0
3
3207
Published on HackMD