爬取猫眼电影排名

忧伤，没啥说的，弄了一下午，基本都是copy的，呀，正则泰难弄了，而且其他的一些第三方库也不怎么知道；

还是太垃圾了呀，加油吧

import requests
import time
import json
import re
from requests.exceptions import RequestException
def get_one_page(url):
    try:
        headers = {
                    'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2272.89 Safari/537.36',  }
        response = requests.get(url,headers = headers)
        if response.status_code == 200:
            print("测试点")
            return response.text
        return None
    except RequestException:
        return None
    
def parse_one_page(html):
    pattern = re.compile(
            '<dd>.*?board-index.*?>(d+)</i>.*?data-src="(.*?)".*?name"><a'
            +'.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
            + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)
    print("测试点4")
    items = re.findall(pattern,html)
    print("测试点5")
    for item in items:
        yield{
              '排名': item[0],
            '图片': item[1],
            '电影名': item[2],
            '主演': item[3].strip()[3:],
            '时间': item[4].strip()[5:],
            '分数': item[5] + item[6]
                }
def write_to_file(content):
    with open(r'F:猫眼.txt','a+',encoding = 'utf-8') as f:
        f.write(json.dumps(content,ensure_ascii = False)+'
')
        
def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    print("测试点2")
    for item in parse_one_page(html):
        print("测试点3")
        print(item)
        write_to_file(item)
    
if __name__=="__main__":
    for i in range(10):
        print("测试点")
        main(offset = i *10)
        time.sleep(1)

主要是熟悉正则的使用

源代码：

https://github.com/Python3WebSpider/MaoYan/blob/master/spider.py