36 lines
1.2 KiB
Python
36 lines
1.2 KiB
Python
import requests
|
|
from bs4 import BeautifulSoup as bs
|
|
import json
|
|
headers = {
|
|
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
|
|
"AppleWebKit/537.36 (KHTML, like Gecko)"
|
|
"Chrome/129.0.0.0 Safari/537.36"
|
|
}
|
|
url = "https://exam.detr.top/exam-b/movies"
|
|
data = []
|
|
resp = requests.get(url, headers=headers)
|
|
resp.encoding = 'utf-8'
|
|
html_content = resp.text
|
|
with open("movies.html", "w", encoding="utf-8") as f:
|
|
f.write(html_content)
|
|
soup = bs(html_content, "html.parser")
|
|
movies = []
|
|
table = soup.find("table")
|
|
rows = table.find_all("tr")[1:]
|
|
for row in rows:
|
|
cols = row.find_all("td")
|
|
movie = {
|
|
"id": int(cols[0].text.strip()),
|
|
"title": cols[1].text.strip(),
|
|
"director": cols[2].text.strip(),
|
|
"year": int(cols[3].text.strip()),
|
|
"rating": float(cols[4].text.strip()),
|
|
"duration": int(cols[5].text.strip()),
|
|
"genre": cols[6].text.strip(),
|
|
"actors_count": int(cols[7].text.strip())
|
|
}
|
|
movies.append(movie)
|
|
with open("movies.json", "w", encoding="utf-8") as f:
|
|
json.dump({"data_id": 1, "movies": movies}, f, ensure_ascii=False, indent=4)
|
|
#数据标注要下载pip install label-studio
|
|
# 第二步打开 label-studio start |