From 652dda759acea11ef6d5d81c34d1cd9fb1f1f14d Mon Sep 17 00:00:00 2001
From: puvg6ilma <3296155167@qq.com>
Date: Mon, 17 Jun 2024 11:08:22 +0800
Subject: [PATCH] ADD file via upload

---
 33lxj.py | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 33lxj.py

diff --git a/33lxj.py b/33lxj.py
new file mode 100644
index 0000000..f43a1ad
--- /dev/null
+++ b/33lxj.py
@@ -0,0 +1,42 @@
+import requests
+from bs4 import BeautifulSoup
+import csv
+
+url='https://movie.douban.com/subject/1306809/comments?status=P'
+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'
+    }
+response = requests.get(url, headers=headers)
+source=response.text
+#print(source)
+soup = BeautifulSoup(source, 'lxml')
+comments = soup.find_all('div', class_='comment-item')
+
+run=[]
+
+for comment in comments:
+    title=comment.select(".comment-info>a")
+    for t1 in title:
+        print(t1.get_text())
+        t2=t1.get_text(strip=True)
+        run.append([t2])
+
+    time=comment.select(".comment-time")
+    for m1 in time:
+        print(m1.get_text())
+        m2=m1.get_text(strip=True)
+        run.append([m2])
+
+    content = comment.select('p>span')
+    for p1 in content:
+        print(p1.get_text())
+        p2=p1.get_text(strip=True)
+        run.append([p2])
+
+    with open('生化危机.csv',mode='w',encoding='utf-8',newline='') as f:
+        csv_writer = csv.writer(f)
+        for c1 in run:
+            csv_writer.writerow(c1)
+print("下载完成")
+
+