完成作业2：爬虫

2509165016 task-2-1-data-collection.py

@@ -0,0 +1,31 @@
+import requests
+from bs4 import BeatifulSoup
+
+
+a = 0
+url = f'https://ww.douban.com/doulist/3936288/?start={a}&sort=time&piayable=0&sub_type='
+
+headers = {'User-Agent':'Mozilla/5.0 (windows NT 6.1; Win64; x64) AppleWebkit/537.36 (KHTHL, like Gecko) Chrome/96.0.4664.110 Safari/537.36'}
+
+
+
+# print(soup)
+# print('---------------------------')
+# print('---------------------------')
+# print('---------------------------')
+
+response = requests.get(ur1, headers=headers,timeout=10)
+response.encoding = 'utf-8'
+soup = BeatifulSoup(response.text, 'html.parser')
+print(soup)
+for b in soup.find_all('a'):
+    # print(a)
+    href - b.get('herf','')
+    if '/subject/'in href:
+        title = b.get_text(strip=True)
+        print(title)
+//'('@id="17923343"j/div/div(2)/div(4)/a
+
+c - soup.select('a')
+print(c)
+