python爬取猫眼电影top100榜

「爱情、让人受尽委屈。」 2022-05-31 01:29 292阅读 0赞

**python版本：3.6**  
**代码如下**

import json
 from multiprocessing.pool import Pool
 
 from requests.exceptions import RequestException
 import re
 import urllib.request
 
 
 # 获取页面
 def get_one_page(url):
 try:
 req = urllib.request.Request(url)
 req.add_header('User-Agent',
 'Mozilla/4.0(compatible;MSIE7.0;WindowsNT5.1;Trident/4.0;SE2.XMetaSr1.0;SE2.XMetaSr1.0;.NETCLR2.0.50727;SE2.XMetaSr1.0)')
 response = urllib.request.urlopen(req)
 html = response.read().decode('utf-8')
 # response = requests.get(url, data={ 
 # 'User-Agent': 'Mozilla/4.0(compatible;MSIE7.0;WindowsNT5.1;Trident/4.0;SE2.XMetaSr1.0;SE2.XMetaSr1.0;.NETCLR2.0.50727;SE2.XMetaSr1.0)'})
 if html != None:
 return html
 return None
 except RequestException:
 return None
 
 
 # 解析页面
 def parse_on_page(html):
 pattern = re.compile('<dd>.*?board-index.*?>(\d+).*?data-src="(.*?)".*?name"><a'
 + '.*?">(.*?)</a>.*?star">(.*?).*?releasetime">(.*?)'
 + '.*?integer">(.*?).*?fraction">(.*?).*?</dd>', re.S)
 items = re.findall(pattern, html)
 for item in items:
 yield {
 'index': item[0],
 'image': item[1],
 'title': item[2],
 'actor': item[3].strip()[3:],
 'time': item[4].strip()[5:],
 'score': item[5] + item[6]
 }
 
 
 # 写入文件
 def write_to_file(content):
 with open('result.txt', 'a', encoding='utf-8') as f:
 f.write(json.dumps(content, ensure_ascii=False) + '\n')
 f.close()
 
 # 配置启动函数
 def main(offset):
 url = 'http://maoyan.com/board/4?offset=' + str(offset)
 html = get_one_page(url)
 for item in parse_on_page(html):
 print(item)
 write_to_file(item)
 
 
 if __name__ == '__main__':
 # 多线程
 pool = Pool()
 pool.map(main, [i * 10 for i in range(10)]) # 前10页

**运行结果**  
![这里写图片描述][SouthEast]

**参考视频**  
网易云课堂：[Python3爬虫三大案例实战分享][Python3]

[SouthEast]: /images/20220531/9a09d5af0b124d65991b3a0b27f86c60.png
[Python3]: http://study.163.com/course/courseMain.htm?courseId=1003735019