python爬虫抓取猫眼电影top10
时间: 2023-11-30 16:04:06 浏览: 94
以下是使用Python爬虫抓取猫眼电影top10的代码:
```python
import requests
import re
import json
def get_html(url):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
try:
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
return None
except requests.exceptions.RequestException as e:
print(e)
return None
def parsing_html(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():
for i in range(10):
offset = i * 10
url = 'http://maoyan.com/board/4?offset=' + str(offset)
html = get_html(url)
for item in parsing_html(html):
print(item)
write_to_file(item)
if __name__ == '__main__':
main()
```
阅读全文