Xpath

解析圖片專案

# 指定url
url = 'http://pic.netbian.com/4kyingshi/'
# UA偽裝
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                  'Chrome/91.0.4472.101 Safari/537.36 Edg/91.0.864.48 '
}
# 傳送請求
response = requests.get(url=url, headers=headers)
 
# 獲取頁面文字資訊
page_text = response.text
# 獲取編碼格式
print(response.encoding)
# 解析返回來的內容
tree = etree.HTML(page_text)
# 編寫匹配規則
# Xpath規則:獲取所有節點下的div class屬性值為"slist" 該div下的/ul便籤下的/ul標籤
li_list = tree.xpath('//div[@class="slist"]/ul/li')
print(li_list)
# 開始遍歷獲取src屬性值
for li in li_list:
    # 拼接圖片url
    # Xpath規則:獲取當前目錄下的/a標籤下的img標籤選擇src屬性
 

    img_url = 'http://pic.netbian.com'+li.xpath('./a/img/@src')[0]
    # Xpath規則:原理同上
    # 生成檔名
    img_name = li.xpath('./a/img/@alt')[0]
    # 編碼
    img_name_list = img_name.encode('iso-8859-1').decode('gbk')
    print(img_url, img_name_list)
    # 傳送二次請求，請求圖片的src值
    response_content = requests.get(url= img_url, headers=headers).content
    
 
# 持久化處理
    with open(img_name_list+'.jpg','wb') as fp:
        fp.write(response_content)