抓取相簿¶

練習¶

抓取底下相簿內的圖片：

http://jimmyts.pixnet.net/album/set/2374457-pokemon-go

In [ ]:

import requests
from bs4 import BeautifulSoup

import requests from bs4 import BeautifulSoup

In [ ]:

url = "http://jimmyts.pixnet.net/album/set/2374457-pokemon-go"

url = "http://jimmyts.pixnet.net/album/set/2374457-pokemon-go"

In [ ]:

# 抓取網站原始檔
r = requests.get(url)

# 抓取網站原始檔 r = requests.get(url)

In [ ]:

# 使用BeautifulSoup做剖析網站原始檔
soup = BeautifulSoup(r.text)

# 使用BeautifulSoup做剖析網站原始檔 soup = BeautifulSoup(r.text)

In [ ]:

# 使用 css selector 選取相簿內的圖片
image_list = soup.select('ul.photo-grid-list li a img')

# 使用 css selector 選取相簿內的圖片 image_list = soup.select('ul.photo-grid-list li a img')

In [ ]:

# 檢查一下有沒有抓到圖片的 URL
for i, img in enumerate(image_list):
    print(i, "==>", img.get('src'))

# 檢查一下有沒有抓到圖片的 URL for i, img in enumerate(image_list): print(i, "==>", img.get('src'))

In [ ]:

# 將圖片存成圖片檔
for i, img in enumerate(image_list):
    with open('{}.jpg'.format(i), 'wb') as f:
        r = requests.get(img.get('src'))
        f.write(r.content)

# 將圖片存成圖片檔 for i, img in enumerate(image_list): with open('{}.jpg'.format(i), 'wb') as f: r = requests.get(img.get('src')) f.write(r.content)