download_pics.py 文件源码

def down_allpic(html_file):
    urls = []
    id_pattern = re.compile(r' data-clipboard-text="(.*?)"', re.MULTILINE)
    with open(html_file, encoding='utf-8') as f:
        content = f.read()
    for m in id_pattern.finditer(content):
        urls.append(m.group(1))
    print(len(urls))
    down_dir = r'D:/download/20170304/'
    for u in urls:
        if (u.endswith('.zip') or u.endswith('/')):
            continue
        print(u)
        # ?????????
        r = requests.get(u, stream=True)
        # ??????????????
        chunk_size = 1024
        with open(os.path.join(down_dir, os.path.split(u)[1]), 'wb') as fd:
            for chunk in r.iter_content(chunk_size):
                fd.write(chunk)
    return urls