31 lines
895 B
Python
31 lines
895 B
Python
import requests
|
||
import re
|
||
|
||
headers = {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
|
||
}
|
||
|
||
url = "https://movie.douban.com/top250"
|
||
|
||
try:
|
||
response = requests.get(url=url, headers=headers, timeout=10)
|
||
response.raise_for_status()
|
||
page_source = response.text
|
||
print("页面请求成功！")
|
||
except Exception as e:
|
||
print(f"请求失败：{e}")
|
||
exit()
|
||
|
||
pattern = re.compile(r'<span class="title">([^&]+?)</span>', re.S)
|
||
movie_names = pattern.findall(page_source)
|
||
|
||
target_names = movie_names[:10]
|
||
with open("movies.txt", "w", encoding="utf-8") as f:
|
||
for name in target_names:
|
||
f.write(name + "\n")
|
||
|
||
print(f"成功爬取{len(target_names)}部电影名，已保存到movies.txt！")
|
||
|
||
print("\n爬取结果预览：")
|
||
for i, name in enumerate(target_names, 1):
|
||
print(f"{i}. {name}") |