网络数据采集（爬虫基础）

260324+2509165020.py/260324+2509165020.txt

@@ -0,0 +1,29 @@
+import requests
+from bs4 import BeautifulSoup
+import time
+BASE_URL = "https://xxx.com/list?page=" 
+START_PAGE = 1                          
+END_PAGE = 100                          
+HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+}
+
+def crawl_page(page):
+    url = f"{BASE_URL}{page}"
+    try:
+        resp = requests.get(url, headers=HEADERS, timeout=10)
+        resp.raise_for_status()
+        soup = BeautifulSoup(resp.text, "html.parser")
+        items = soup.find_all("div", class_="item")
+        for item in items:
+            title = item.find("h3").get_text(strip=True)
+            print(title) 
+        print(f"<22><> {page} ҳ<><D2B3>ȡ<EFBFBD><C8A1><EFBFBD><EFBFBD>")
+
+    except Exception as e:
+        print(f"<22><> {page} ҳ<><D2B3><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{e}")
+
+if __name__ == "__main__":
+    for page in range(START_PAGE, END_PAGE + 1):
+        crawl_page(page)
+        time.sleep(1) 

爬虫3.24/douban.py.py

@@ -1,14 +0,0 @@
-import requests
-from bs4 import BeautifulSoup
-
-headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'
-}
-
-url = 'https://www.douban.com/doulist/3936288/'
-response = requests.get(url, headers=headers)
-soup = BeautifulSoup(response.text, 'html.parser')
-
-titles = soup.select('.title a')
-for t in titles:
-    print(t.text.strip())