requests+正则表达式爬猫眼电影TOP100

爬取下来的Html中发现有提示：很抱歉，您的访问被禁止了。

需要伪装成浏览器，在headers中添加’User-Agent’字典：

headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
    }

然后再爬取，并保存到文本文件中：

import requests
from requests.exceptions import RequestException
import re
import json
def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
    }
    try:
        response = requests.get(url,headers=headers)
        if response.status_code==200:
            return response.text
        return None
    except RequestException:
        return None
def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(.*?)</i>.*?title="(.*?)".*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            'index':item[0],
            'title':item[1],
            'actors':item[2].strip()[3:],
            'time':item[3][5:],
            'score':item[4]+item[5]
        }
def write_to_file(content):
    with open('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')
        #json.dumps 序列化时对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False
        # .dumps 将dict转换成str格式，
        # .loads 将str转换成dict格式
        f.close()
def main():
    for offset in range(0,100,10):
        url = 'http://maoyan.com/board/4?offset={}'.format(offset)
        html = get_one_page(url)
        for item in parse_one_page(html):
            write_to_file(item)
if __name__=='__main__':
    main()