運動相簿之爬蟲－阿藏哥的部落格~不應該阿

寫一個下載大量圖片的案例

import time,os
from urllib.request import urlopen
from selenium import webdriver
from bs4 import BeautifulSoup
from selenium.webdriver.chrome.options import Options

chrome_options = Options()
chrome_options.add_argument("--headless")  # 定義 headless
chrome_path = ".\chromedriver.exe" #chromedriver.exe執行檔所存在的路徑
driver = webdriver.Chrome(chrome_path,chrome_options=chrome_options)



url="https://running.biji.co/index.php?q=album&act=photo_list&album_id=35892&cid=7214&start=1545528000&end=1545528600&type=place&subtitle=%E8%81%96%E8%AA%95%E6%AD%A1%E6%A8%82%E4%B8%BB%E9%A1%8C%E5%9C%98%E8%B7%91-%E8%8F%AF%E7%82%BA%E6%89%8B%E7%92%B0%E9%AB%94%E9%A9%97"
driver.get(url)
driver.implicitly_wait(1)

for i in range(1,101):
    driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
    time.sleep(0.3)

soup=BeautifulSoup(driver.page_source,'html.parser')
title = soup.find('h1','album-title').text.strip()
all_imgs = soup.find_all('img', {"class": "photo_img photo-img"})

images_dir ='d:\\'+ title + "\\"
if not os.path.exists(images_dir):
    os.mkdir(images_dir)

# 處理所有 <img> 標籤
n = 0

for img in all_imgs:
    # 讀取 src 屬性內容
    src = img['src']
    # 讀取 .jpg 檔
    if src != None and ('.jpg' in src):
        # 設定圖檔完整路徑
        full_path = src
        filename = full_path.split('/')[-1]  # 取得圖檔名
        print(full_path)
        # 儲存圖片
        try:
            image = urlopen(full_path)
            with open(os.path.join(images_dir, filename), 'wb') as f:
                f.write(image.read())
            n += 1
            if n >= 1000:  # 最多下載 1000 張
                break
        except:
            print("{} 無法讀取!".format(filename))

print("共下載", n, "張圖片")
driver.quit();  # 關閉瀏覽器並退出驅動程式

==================res===============================

C:\python\authdemo\venv\Scripts\python.exe C:/python/authdemo/test123.py
https://cdntwrunning.biji.co/600_19D03119-4F87-9AB9-BD72-20F3C0407E47.jpg
https://cdntwrunning.biji.co/600_5DC83958-39BF-2863-F3BD-044CB07D032D.jpg
https://cdntwrunning.biji.co/600_917B5FDA-7070-EFB2-7B79-3FA283BF67CC.jpg
https://cdntwrunning.biji.co/600_3144B014-7050-512E-3300-AFDE1604BDFA.jpg
https://cdntwrunning.biji.co/600_706EFB7A-0F0C-1B21-F83B-EB8CEF94A8C6.jpg
https://cdntwrunning.biji.co/600_CAE416DF-2CE0-E1D0-D53F-253E7CD3A17E.jpg
https://cdntwrunning.biji.co/600_9DE5D667-F301-5DCF-5D70-3993DE2D9F47.jpg
https://cdntwrunning.biji.co/600_A72B2286-6AD4-843B-3D92-8A5B6DAB7288.jpg
https://cdntwrunning.biji.co/600_CD7069F1-015C-DA45-1915-ACA3D8034F9F.jpg
https://cdntwrunning.biji.co/600_A99FFF84-8A6D-7505-E2D4-306EF68FBEA2.jpg
https://cdntwrunning.biji.co/600_EA02A5C7-78D3-6CF2-8429-F9A95E35730E.jpg
https://cdntwrunning.biji.co/600_AEBF41D5-1464-36F3-8B55-C7809AEFBE9C.jpg
https://cdntwrunning.biji.co/600_356395DF-0CE9-F756-4B0A-40B51C683965.jpg
https://cdntwrunning.biji.co/600_0271834F-4966-F270-B339-C8DACB148354.jpg
https://cdntwrunning.biji.co/600_4908D482-2487-150C-C74C-152FACDA5B96.jpg
https://cdntwrunning.biji.co/600_3A0D1F3A-5135-6A83-4800-2DC2857B74F2.jpg
https://cdntwrunning.biji.co/600_F0D2D167-4C66-C12F-32A0-A86137ABB072.jpg
https://cdntwrunning.biji.co/600_C47A4113-BE10-60DC-E9A8-1AC4CE9EC5EB.jpg
https://cdntwrunning.biji.co/600_16D89B31-F988-687C-6603-CD8C9C6597A2.jpg
https://cdntwrunning.biji.co/600_6ADE1CC0-42EA-71CB-7AC7-D2A4CD1BE0DB.jpg
https://cdntwrunning.biji.co/600_4F65370C-AC27-AEC0-0631-DA10D58EF1E9.jpg
https://cdntwrunning.biji.co/600_BD3BBDD9-5C0A-AFAE-8116-FFBDFC8A17BA.jpg
https://cdntwrunning.biji.co/600_58357DCA-D6C7-4E5C-41C2-F200587AA5CE.jpg
https://cdntwrunning.biji.co/600_D8092658-90FD-9B43-EC66-76A421FC4457.jpg
https://cdntwrunning.biji.co/600_394681CA-AACE-9B87-31E0-B2FD60153A94.jpg
https://cdntwrunning.biji.co/600_A4C1285D-91DF-628E-25BF-E54BF7A92CD8.jpg
https://cdntwrunning.biji.co/600_D75D1F95-6F68-28FC-F6C7-F8595051CB91.jpg
https://cdntwrunning.biji.co/600_3511041E-58EA-02E8-4C9D-2CCF6208D91C.jpg
https://cdntwrunning.biji.co/600_92F9AB9B-0015-D1AE-2DF4-64E5B2ABB683.jpg
https://cdntwrunning.biji.co/600_02C2842E-81ED-770C-32C2-CFA3475604D4.jpg
https://cdntwrunning.biji.co/600_992A3AC2-2362-4E1E-8851-A8D87348881E.jpg
https://cdntwrunning.biji.co/600_F95C5323-CA8A-2836-9FD3-19C70B9C37A3.jpg
https://cdntwrunning.biji.co/600_F423A52D-7985-2B81-7D25-505F23C40C80.jpg
https://cdntwrunning.biji.co/600_742E4402-54E8-8656-C4C7-E7511AE60FD2.jpg
https://cdntwrunning.biji.co/600_27929637-2035-6725-C7BF-76D7E657E591.jpg
https://cdntwrunning.biji.co/600_53255701-4699-7C72-D1C8-9A9C8D28AD21.jpg
https://cdntwrunning.biji.co/600_DD2A216A-3655-A88B-2348-2B7D195F76B9.jpg
https://cdntwrunning.biji.co/600_2AF81263-A36F-0C4B-19AC-D37FD5065A47.jpg
https://cdntwrunning.biji.co/600_FE8D6214-0E90-E0AF-46F1-D9A6BBBED792.jpg
https://cdntwrunning.biji.co/600_8FC8AA14-D4EC-D2F7-FCDA-1CA0379F8943.jpg
https://cdntwrunning.biji.co/600_E45062FD-3B0A-CC7E-2DC9-9D69D926C011.jpg
https://cdntwrunning.biji.co/600_F9BCA241-8798-E283-2BA9-26A4F9E0DAD8.jpg
https://cdntwrunning.biji.co/600_1FA12DD7-16F3-9CE1-C569-1C2C6B503C82.jpg
https://cdntwrunning.biji.co/600_7988E58E-0CC8-D8E5-937A-03B9AD4F414D.jpg
https://cdntwrunning.biji.co/600_3A756940-8AE7-B13B-87CC-A2B800FED234.jpg
https://cdntwrunning.biji.co/600_E90CC601-6EA0-4210-446C-02D6B980823D.jpg
https://cdntwrunning.biji.co/600_3F28F713-0CED-9B92-E175-52EE565E3270.jpg
https://cdntwrunning.biji.co/600_E7E4D508-8391-6CBC-AED5-99FC15C18023.jpg
https://cdntwrunning.biji.co/600_DC51E5EC-AD43-9C70-F5FF-420EFB83F9A6.jpg
https://cdntwrunning.biji.co/600_BF37DED7-B20E-56DD-4319-F94ACA0F5502.jpg
https://cdntwrunning.biji.co/600_B1D411EF-6ED7-5711-DC22-E2D1E2CAF560.jpg
https://cdntwrunning.biji.co/600_76F9F182-4378-A28C-F477-5D5476DE4345.jpg
https://cdntwrunning.biji.co/600_9E7DBD5D-DE71-CB53-D681-0BA57D519885.jpg
https://cdntwrunning.biji.co/600_82485FFC-B7BE-57E3-034C-5281F4019244.jpg
https://cdntwrunning.biji.co/600_011B65C4-4A64-F2E8-61B7-0685B448E8C5.jpg
https://cdntwrunning.biji.co/600_44ACE25B-61F5-D8A3-A95F-B6249D707E0E.jpg
https://cdntwrunning.biji.co/600_7A893624-826E-AEE9-17E7-EEE8C0EF252F.jpg
共下載 57 張圖片