Python百行で韓服サークルの画像クロールを実現する

	public String toString() {
		// The schemaMappings are initialized in getSchemaMappings()
		return "EntityResolver using mappings " + getSchemaMappings();
	}

def get_page(url, headers):
    """
    Get the image address based on the subpage link, then package it for download
    params: url subURL
    """
    r = requests.get(url, headers=headers)
    if r.status_code == 200:
        r.encoding = r.apparent_encoding
        html = etree.HTML(r.text)
        html = etree.tostring(html)
        html = etree.fromstring(html)
        # Get the title
        title = html.xpath(r'//*[@id="main_article"]/header/h1/text()')
        # Get the image address
        img = html.xpath(r'//div[@class="arc_body"]//figure/img/@src')
        # title preprocessing 
        title = ''.join(title)
        title = re.sub(r'[|]', '', title)
        print(title)
        save_img(title, img, headers)

def save_img(title, img, headers):
    """
    Create subfolders based on titles
    Download all img links and choose to change the quality size
    params: title : title
    params: img : image address
    """
    if not os.path.exists(title):
        os.mkdir(title)
    # Download
    for i, j in enumerate(img): # iterate through the list of URLs
        r = requests.get(j, headers=headers)
        if r.status_code == 200:
            with open(title + '//' + str(i) + '.png', 'wb') as fw:
                fw.write(r.content)
        print(title, 'The first of ', str(i), 'The download is complete!')

if __name__ == '__main__':
    """ 
    Find one page at a time
    params : None
    """
    path = '/Users/********/Hanbok/'
    if not os.path.exists(path):
        os.mkdir(path)
        os.chdir(path)
    else:
        os.chdir(path)
    # url = 'http://www.aihanfu.com/zixun/tushang-1/'
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'
                             ' AppleWebKit/537.36 (KHTML, like Gecko)'
                             ' Chrome/81.0.4044.129 Safari/537.36'}
    for _ in range(1, 50):
        url = 'http://www.aihanfu.com/zixun/tushang-{}/'.format(_)
        for _ in get_menu(url, headers):
            get_page(_, headers) # Get a page