期末

期末/爬豆瓣

@@ -2,32 +2,39 @@ 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/91.0.4472.124 Safari/537.36'}
-url="https://movie.douban.com/top250?start=25"
-data=[]
-resp = requests.get(url, headers = headers)
-resp.encoding='uft-8'
-soup= bs(resp.text,"html.parser")
-items= soup.find_all("div",class_="item")
-#print(items[0])
-for i in range(len(items)):
-    print(i)
-    title=items[i].find("span",class_="title").get_text()
+urls = [
+    "https://movie.douban.com/top250?start=0",   # 第1页（1-25）
+    "https://movie.douban.com/top250?start=25",  # 第2页（26-50）
+]
+data = []
 
-    actors=items[i].find("div",class_="bd").get_text().strip()
-    try:
-        actors=actors.split("主演:")[1].split("\n")[0]
-    except:
-        actors="无"
-    try:
-        quote=items[i].find("div", class_="bd").find("p",class_="quote").get_text().strip()
-    except:
-        quote="无"
-    data.append({
-        "title":title,
-        "actor":actors,
-        "quote":quote
-    })
+for url in urls:
+    resp = requests.get(url, headers=headers)
+    resp.encoding = 'utf-8'  # 修复了拼写：uft-8 → utf-8
+    soup = bs(resp.text, "html.parser")
+    items = soup.find_all("div", class_="item")
+
+    for i in range(len(items)):
+        print(i)
+        title = items[i].find("span", class_="title").get_text()
+
+        actors = items[i].find("div", class_="bd").get_text().strip()
+        try:
+            actors = actors.split("主演:")[1].split("\n")[0]
+        except:
+            actors = "无"
+
+        try:
+            quote = items[i].find("div", class_="bd").find("p", class_="quote").get_text().strip()
+        except:
+            quote = "无"
+
+        data.append({
+            "title": title,
+            "actor": actors,
+            "quote": quote
+        })
 print(data)
 
 with open("movie.json","w",encoding="utf-8") as f:
-    json.dump(data,f,ensure_ascii=False,indent=4)
+    json.dump(data,f,ensure_ascii=False,indent=4)