import requests, re, json

def request_dangdang(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
    except requests.RequestException:
        return None

def parse_result(html):
    pattern = re.compile('<li>.*?list_num.*?(\d+).</div>.*?<img src="(.*?)".*?class="name".*?title="(.*?)">.*?class="star">.*?class="tuijian">(.*?)</span>.*?class="publisher_info">.*?target="_blank">(.*?)</a>.*?class="biaosheng">.*?<span>(.*?)</span></div>.*?<p><span\sclass="price_n">&yen;(.*?)</span>.*?</li>
 
',re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'range': item[0],
            'title': item[2],
            'price': item[6]
        }

def write_file(item):
    print('開始寫入資料 ====> ' + str(item))
    with open('book.txt', 'a', encoding='UTF-8') as f:
        f.write(json.dumps(item, ensure_ascii
 
=False) + '\n')
        f.close()

def main(page):
    url = 'http://bang.dangdang.com/books/fivestars/1-' + str(page)
    html = request_dangdang(url)
    items = parse_result(html)

    for item in items:
        write_file(item)


if __name__ == "__main__":
    for i in range(1,11):
        main(i)