xpath之圖片數據解析與爬取

# 需求 ：圖片數據解析http://pic.netbian.com/4kmeinv/
import requests
import os
from lxml import etree
if __name__ == "__main__":

    # 爬取頁面源碼數據
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    }   # UA偽裝
    url = 'http://pic.netbian.com/4kmeinv/'
    page_text = requests.get(url=url,headers = headers).text
    # 手動設定響應數據的編碼格式
    # res = requests.get(url=url,headers = headers)
    # res.encoding = 'utf-8'
    # page_text = res.text

    # 頁面數據解析
    tree = etree.HTML(page_text)
    # 創建一個文件夾
    if not os.path.exists('./girlpiclib'):
        os.mkdir('./girlpiclib')
    li_list = tree.xpath('//div[@class="slist"]//li')
    for li in li_list:
        #局部解析 獲取src 與 alt
        img_src = li.xpath('./a/img/@src')[0]
        img_name = li.xpath('./a/img/@alt')[0]+'.jpg'

        # 通用處理中文亂碼的解析方式
        img_name = img_name.encode('iso-8859-1').decode('gbk')

        url = 'http://pic.netbian.com/'+img_src
        # 爬取圖片數據content
        pic_content = requests.get(url= url,headers = headers).content

        #持久化存儲
        img_path = 'girlpiclib/' + img_name
        fp = open(img_path,'wb')
        fp.write(pic_content)
        print(img_name,'下載成功')