下載捧腹網圖片
阿新 • • 發佈:2017-06-09
bsp open 表示 meta dal content png images -type
# 鎖薇,捧腹網 import urllib.request, re# , sys # 獲取網頁源碼 def page(pg): url = ‘https://www.pengfu.com/index_%s.html‘%pg # 頁面是utf8編碼,所有解碼成unicode html = urllib.request.urlopen(url).read().decode(‘utf8‘) # <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> # print(html) return html # 獲取標題 def title(html): reg = re.compile(r‘<h1 class="dp-b"><a href=".*?" target="_blank">(.*?)</a>‘) # r表示防止轉義 item = re.findall(reg, html) # print(item) return item # 獲取圖片url def content(html): # html = page(1) reg = r‘<img src="(.*?)" width=‘ item = re.findall(reg, html) # print(item) return item def download(url, name): path = ‘image\%s.jpg‘%name#.decode(‘utf-8‘).encode(‘gbk‘) # win下只識別gbk urllib.request.urlretrieve(url, path) for i in range(5,9): html = page(i) title_list = title(html) content_list = content(html) for m, n in zip(title_list, content_list): # 把標題和圖片對個對應 print(‘正在下載>>>>>:‘ + m, n) download(n, m)
下載捧腹網圖片