67 lines
2.0 KiB
Python
67 lines
2.0 KiB
Python
import requests
|
||
import re
|
||
import csv
|
||
import json
|
||
|
||
url = "https://movie.douban.com/top250"
|
||
headers = {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36"
|
||
}
|
||
|
||
response = requests.get(url, headers=headers)
|
||
html = response.text
|
||
|
||
pattern = re.compile(
|
||
r'<em class="">(\d+)</em>.*?'
|
||
r'<span class="title">(.*?)</span>.*?'
|
||
r'<span class="other">(.*?)</span>.*?'
|
||
r'<span class="rating_num".*?>(.*?)</span>.*?'
|
||
r'<span>(\d+人评价)</span>.*?'
|
||
r'<span class="inq">(.*?)</span>?',
|
||
re.S
|
||
)
|
||
|
||
movies = pattern.findall(html)[:10]
|
||
|
||
movie_list = []
|
||
for m in movies:
|
||
rank = m[0]
|
||
title = m[1]
|
||
en_title = m[2].replace("/", "").strip()
|
||
rating = m[3]
|
||
people = m[4]
|
||
quote = m[5] if len(m) > 5 else ""
|
||
movie_list.append({
|
||
"rank": int(rank),
|
||
"title": title,
|
||
"en_title": en_title,
|
||
"rating": rating,
|
||
"people": people,
|
||
"quote": quote
|
||
})
|
||
|
||
with open("movies.txt", "w", encoding="utf-8") as f:
|
||
for m in movie_list:
|
||
f.write(m["title"] + " | " + m["quote"] + "\n")
|
||
|
||
|
||
with open("movies.csv", "w", encoding="utf-8-sig", newline="") as f:
|
||
writer = csv.writer(f)
|
||
|
||
writer.writerow(["排名", "中文名", "英文名", "评分", "评价人数", "经典评语"])
|
||
for m in movie_list:
|
||
writer.writerow([m["rank"], m["title"], m["en_title"], m["rating"], m["people"], m["quote"]])
|
||
print("✅ 练习1完成：已保存到 movies.csv")
|
||
|
||
with open("movies.json", "w", encoding="utf-8") as f:
|
||
json.dump(movie_list, f, ensure_ascii=False, indent=4)
|
||
print("✅ 练习2完成：已保存到 movies.json")
|
||
|
||
|
||
print("\n--- 练习3：JSON统计 ---")
|
||
with open("movies.json", "r", encoding="utf-8") as f:
|
||
data = json.load(f)
|
||
|
||
ratings = [float(m["rating"]) for m in data]
|
||
avg = sum(ratings) / len(ratings)
|
||
print(f"平均分：{avg:.2f}") |