requests bs4 爬取 資訊 圖片

#!/usr/bin/env python
# Version = 3.5.2
# __auth__ = '無名小妖'
import requests
from bs4 import BeautifulSoup
import uuid


response = requests.get(
    url='http://www.autohome.com.cn/news/'
)
response.encoding = response.apparent_encoding  # 使用原頁面的編碼進行解析
# response.status_code 狀態碼
# 將頁面字符串轉化成bs對象，features 是轉化方式，此處用的html.parser，而生產中用的是lxml，性能較好
soup = BeautifulSoup(response.text, features='html.parser')
# 獲取id爲'auto-channel-lazyload-article' 的標籤
target = soup.find(id='auto-channel-lazyload-article')
# 在此標籤下找到全部的li標籤
li = target.find_all('li')
# 獲取每一個li標籤下的a標籤
for i in li:
    a = i.find('a')
    if a:
        # print(a.attrs.get('href'))
        txt = a.find('h3').text
        # 獲取圖片的地址
        img_url = a.find('img').attrs.get('src')
        if not img_url.startswith("http:"):
            img_url = "http:" + img_url
        # 下載圖片
        img_response = requests.get(url=img_url)
        h = img_url.split('.')
        jpg_name = '{}.{}'.format(uuid.uuid4(), h[-1])
        with open(jpg_name, 'wb') as f:
            f.write(img_response.content)