爬虫实例：当当网书籍介绍

import json
import re
import requests
from requests import RequestException


def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            # print('2sas')
            print(response.text)
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    #  加上re.S后, .将会匹配换行符
    pattern = re.compile('<li>.*?list_num.*?>(.*?)</div>.*?pic.*?src="(.*?)".*?/></a>.*?name"><a.*?title="(.*?)">.*?tuijian">(.*?)</span>.*?publisher_info.*?title="(.*?)".*?biaosheng.*?<span>(.*?)</span>.*?</li>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            'index':item[0],
            'iamge':item[1],
            'title':item[2],
            'tuijian':item[3],
            'author':item[4],
            'times':item[5],
        }

def write_content_to_file(content):
    with open('book.txt', 'a', encoding='UTF-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '
')
        f.close()

def main(page):
    url = "http://bang.dangdang.com/" 
          "books/fivestars/01.00.00.00.00.00-recent30-0-0-1-" + str(page)
    html = get_one_page(url)
    parse_one_page(html)
    for item in parse_one_page(html):
        print(item)
        write_content_to_file(item)

if __name__ == "__main__":
    for i in range(1,2):
        main(i)