爬虫学习-第八篇

"""
Version: 0.1
Author: freshbin
Date: 2019年8月26日
"""

print("=================================抓取猫眼电影榜单 start================================================")

import requests
import re
import json
import time
from requests.exceptions import RequestException

def get_one_page(url):
    try:
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'
        }

        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('
.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name">(.*?).*?star">(.*?)
.*?releasetime">(.*?)
'
                          + '.*?integer">(.*?).*?fraction">(.*?).*?
', re.S)
    items = re.findall(pattern, html) # 如果解析失败的话，这里会卡着不动了

    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2].strip(),
            'actor': item[3].strip()[3:] if len(item[3]) > 3 else '',
            'time': item[4].strip()[5:] if len(item[4]) > 5 else '',
            'score': item[5].strip() + item[6].strip()
        }

def write_to_file(content):
    with open('result1.txt', 'a', encoding='utf-8') as f:
        print(type(json.dumps(content)))
        f.write(json.dumps(content, ensure_ascii=False) + '\n')

def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print(item)
        write_to_file(item)

if __name__ == '__main__':
    for i in range(10):
        main(offset=i * 10)
        time.sleep(1)

print("=================================抓取猫眼电影榜单 end================================================")