python爬取猫眼top10
时间: 2023-12-08 08:39:29 浏览: 179
python爬取猫眼
以下是Python爬取猫眼电影Top10的示例代码:
```python
import requests
import re
import json
def get_one_page(url):
headers = {
'User': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
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)
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]
}
def write_to_file(content):
with open('result.txt', 'a', encoding='utf-8') as f:
f.write(json.dumps(content, ensure_ascii=False) + '\n')
def main(offset):
url = 'https://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)
```
该代码使用requests库发送请求,使用正则表达式解析HTML页面,最后将结果写入文件。运行该代码后,会在当前目录下生成一个result.txt文件,其中包含了猫眼电影Top10的相关信息。
阅读全文