5.30

pythonProject/cf..py

@@ -1,25 +0,0 @@
-import requests
-
-url = 'https://codeforces.com/search?by='
-
-name = input()
-
-params = {
-    'query' : name
-}
-
-headers = {
-    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0'
-}
-
-response = requests.get(url=url, params=params, headers=headers)
-
-page_text = response.text
-
-File = name + '.html'
-
-with open(File, 'w', encoding='utf-8') as fp:
-    fp.write(page_text)
-
-
-

pythonProject/db_log.txt

@@ -0,0 +1 @@
+2024-05-29 18:05:36,839 ERROR connect Error

pythonProject/dp.py

@@ -50,6 +50,12 @@ class DBHelper:
             return False
         return True
 
+    def fetchCount(self, sql, params=None):
+        if not self.connect():
+            return False
+        self.execute(sql, params)
+        return self.cur.fetchone()
+
     def close(self):
         self.cur.close()
         self.conn.close()
@@ -57,7 +63,6 @@ class DBHelper:
 if __name__ == '__main__':
     db = DBHelper()
     sql = 'create table films(title varchar(50), actor varchar(200), time varchar(100));'
-    db.execute(sql)
+    db.connect()
+    logger.removeHandler(file_handler)
 
-    db.close()
-    logger.removeHandler(file_handler)

pythonProject/films.py

@@ -0,0 +1,110 @@
+import requests
+import dp
+from lxml import etree
+# 进程池和管理工具
+from multiprocessing import Pool, Manager
+import functools
+import matplotlib.pyplot as plt
+import logging
+
+plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体
+plt.rcParams['axes.unicode_minus'] = False # 解决保存图像时负号'-'显示为方块的问题
+
+# 获取logger的实例
+logger = logging.getLogger("films_log.txt")
+
+# 指定logger的输出格式
+formatter = logging.Formatter('%(asctime)s %(levelname)s %(message)s')
+
+# 文件日志 终端日志
+file_handler = logging.FileHandler('films_log.txt')
+file_handler.setFormatter(formatter)
+
+logger.setLevel(logging.INFO)
+logger.addHandler(file_handler)
+
+def getPage(url):
+    headers = {
+        'User-Agent':'Mozilla/5.0(Macintosh;Intel Mac OS X 10_11_4)AppleWebKit/537.36(KHTML,like Gecko)Chrome/52.0.2743.116 Safari/537.36'
+    }
+    response = requests.get(url, headers=headers)
+    if response.status_code == 200:
+        return response.text
+    return None
+
+def insertInfo(item):
+    db = dp.DBHelper()
+    _title = item['item']
+    _actor = item['actor']
+    _time = item['time']
+    sql = 'insert into films(title, actor, time) values (%s, %s, %s);'
+    params = (_title, _actor, _time)
+    ok = db.execute(sql, params)
+
+    if ok == False:
+        logger.error(str(sql))
+        logger.error('params: ', str(params))
+        logger.error('插入失败')
+        print('插入失败')
+
+def parse(html):
+    items = []
+    tree = etree.HTML(html)
+    titles = tree.xpath('/html/body/div[4]/div/div/div[1]/dl/dd/div/div/div[1]/p[1]/a/text()')
+    actors = tree.xpath('/html/body/div[4]/div/div/div[1]/dl/dd/div/div/div[1]/p[2]/text()')
+    times = tree.xpath('/html/body/div[4]/div/div/div[1]/dl/dd/div/div/div[1]/p[3]/text()')
+
+    for i in range(len(titles)):
+        title = titles[i].strip()
+        actor = actors[i].strip()
+        time = times[i].strip()
+        items.append({
+            'title': title,
+            'actor': actor[3:],
+            'time': time[5:]
+        })
+
+    print(items)
+    return items
+
+def analysisCounry():
+    # 从数据库表中查询每个国家的电影数量来做分析
+    db = dp.DBHelper()
+
+    total = db.fetchCount("select count(*) from films;")
+    Am = db.fetchCount('select count(*) from films where time like "%美国%";')
+    Ch = db.fetchCount('select count(*) from films where time like "%中国%";')
+    Jp = db.fetchCount('select count(*) from films where time like "%日本%";')
+    Other = total[0] - Am[0] - Ch[0] - Jp[0]
+    sizes = Am[0], Ch[0], Jp[0], Other
+    labels = 'America', 'China', 'Japan', 'Others'
+    colors = 'cyan', 'red', 'yellow', 'lightgreen'
+    explode = 0, 0, 0, 0
+
+    # 画出统计表的饼状图
+    plt.title("热门电影分类信息图")
+    plt.pie(sizes, explode=explode, labels=labels, colors=colors,
+            autopct='%d%%', shadow=True)
+
+    plt.show()
+
+def CrawlMovieInfo(lock, offset):
+    # 抓取电影名，主演，上映时间
+    url = 'https://www.maoyan.com/board/4?offset=' + str(offset)
+    # 抓取当前页面
+    html = getPage(url)
+
+    for item in parse(html):
+        lock.acquire()  # 获取锁定，使线程进入同步阻塞状态
+        insertInfo(item)
+        lock.release() # 释放锁
+
+if __name__ == '__main__':
+    lock = Manager().Lock()
+    partial_CrawlMovieInfo = functools.partial(CrawlMovieInfo, lock)
+    pool = Pool() # 创建一个进程池
+    pool.map(partial_CrawlMovieInfo, [i * 10 for i in range(10)]) # 并行处理
+    pool.close()
+    pool.join()
+    logger.removeHandler(file_handler)
+    analysisCounry()

pythonProject/test.py

@@ -1,34 +0,0 @@
-import requests
-from lxml import etree
-
-url = 'https://www.maoyan.com/board/4?offset=0'
-
-
-
-headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0'
-}
-
-response = requests.get(url=url, headers=headers)
-
-tree = etree.HTML(response.text)
-
-titles = tree.xpath('/html/body/div[4]/div/div/div[1]/dl/dd/div/div/div[1]/p[1]/a/text()')
-actors = tree.xpath('/html/body/div[4]/div/div/div[1]/dl/dd/div/div/div[1]/p[2]/text()')
-times = tree.xpath('/html/body/div[4]/div/div/div[1]/dl/dd/div/div/div[1]/p[3]/text()')
-
-items = []
-
-for i in range(len(titles)):
-    title = titles[i].strip()
-    actors = actors[i].strip()
-    times = times[i].strip()
-
-    items.append({
-        'title': titles,
-        'actor': actors[3:],
-        'time': times[5:]
-        })
-
-for i in items:
-    print(i)