Auto commit

douban_top.py

+import requests
+import re
+
+# 抓取豆瓣电影TOP250的电影名称、导演、上映年份、电影评分以及评分人数等信息并保存到csv文件中
+
+def main():
+    headers = {
+        'User-Agent':"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.0.0 Safari/537.36"
+    }
+
+    # step1 提取PageSource
+    f = open("douban_TOP.csv", encoding="utf-8", mode="w")
+    f.write("电影名称,导演,上映年份,电影评分,评分人数\n") # 写入表头
+    for page in range(1, 11):
+        url = f"https://movie.douban.com/top250?start={25 * (page - 1)}"
+        resp = requests.get(url, headers=headers)
+        resp.encoding = "utf-8"  # 确定编码格式
+        PageSource = resp.text
+
+        # step2 编写正则表达式
+        # re.S可以让正则中的.匹配换行符
+        obj = re.compile(
+            r'<div class="item">.*?<span class="title">(?P<name>.*?)</span>.*?<p class="">.*?导演: (?P<director>.*?)&nbsp.*?<br>(?P<year>.*?)&nbsp.*?<span class="rating_num" property="v:average">(?P<score>.*?)</span>.*?<span>(?P<num>.*?)人评价</span>',
+            re.S)
+
+        # step3 提取数据
+        content = obj.finditer(PageSource)
+        for item in content:
+            name = item.group("name")
+            director = item.group("director").strip()
+            year = item.group("year")
+            score = item.group("score")
+            num = item.group("num")
+            f.write(f"{name},{director},{year},{score},{num}\n")  # step4  存储数据
+
+        print(f"已经爬起了第{page}页")
+
+    # step5 收尾工作
+    f.close()
+    resp.close()
+
+if __name__ == '__main__':
+    main()
+