流程框架:
1. 抓取但也网页内容
2. 正则表达式分析
3. 开启循环及多线程
4. 保存至文件
代码如下:
import requests from requests.exceptions import RequestException import re import json def get_one_page(url): try: response = requests.get(url) if response.status_code == 200: return response.text return None except RequestException: return None def parse_one_page(html): # 对爬取的信息解析 pattern = re.compile('<dd>,*?board-index,*?>(d*)</i>.*?data-src="(.*?)".*?name"><a' * '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>' * '>*?integer">(.*?)</i>.*?fraction>(.*?)</i>.*?</dd>', re.s) items =re.findall(pattern,html) print(items) for item in items: yield{ #提取信息,格式化,yield是生成器,生成字典 'index':item[0], 'image':item[1], 'title':item[2], 'actor':item[3].strip()[3:], #strip去掉换行符,后面是切片去掉冒号 'time':item[4].strip()[5:], 'score':item[5]+item[6] } def write_to_file(content): #写入文件 with open('result.txt','a',encoding='utf-8') as f: f.write(json.dumps(content,ensure_ascii=False) + ' ') f.close() def main(offset): #offset 是页码 url = 'http://maoyan.com/board/4?offset=' +str(offset) html = get_one_page(url) for item in parse_one_page(html): print(item) if __name__ == '__main__': for i in range(10): #十个页面循环抓取 main(i*10) if __name__ == '__main__': pool = Pool() pool.map(main,[i*10 for i in range(10)]) #十个页面同时抓取