From 0c6941f5b48bc2ad6a6fb1ec3a4e0d0abf0af3fc Mon Sep 17 00:00:00 2001
From: LiBo <1139217246@qq.com>
Date: Thu, 30 May 2024 16:30:27 +0800
Subject: [PATCH] 5.30

---
 pythonProject/__pycache__/dp.cpython-312.pyc | Bin 0 -> 2911 bytes
 pythonProject/cf..py                         |  25 -----
 pythonProject/db_log.txt                     |   1 +
 pythonProject/dp.py                          |  11 +-
 pythonProject/films.py                       | 110 +++++++++++++++++++
 pythonProject/test.py                        |  34 ------
 6 files changed, 119 insertions(+), 62 deletions(-)
 create mode 100644 pythonProject/__pycache__/dp.cpython-312.pyc
 delete mode 100644 pythonProject/cf..py
 create mode 100644 pythonProject/films.py
 delete mode 100644 pythonProject/test.py

diff --git a/pythonProject/__pycache__/dp.cpython-312.pyc b/pythonProject/__pycache__/dp.cpython-312.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..4e91af82a3f96ffd91cc9230a88440392b350043
GIT binary patch
literal 2911
zcmaJ@O>7%g5Ps`jdw1RSPvStFKvFj$C>Et^8(OJQAtjXbM<E~)q1visw%$!*V|$&q
zo2E7vN>QXHP)H*V2|rSMBnlEo;DmYuaiAuy>@K}=f|DT!s-Boxd)IE0FtX>p`FTG(
z^Udu3;`4b4(7O-bnf}y6$R8-!#5E^7IfjsRq7a42ka%Nc;*5)^OxpIb*TAT_w!j}L
z&RRY~Lu%&=>-e}WAF18in78f2t9-g+w}<MscVURirbBypFzK${+Q(LP@3yOa%fm&^
z5`|kLihIk|@Qh2UPw~7rObC4e?k;ULH;DTcJ|0m0=|j7Bw0*354(_(MpIBfDOjP(2
zohFN3<#HmU%^WeV8pWZZVOdWasjM2+BSXU(^@^Iw$xSJ%>bg7wmSp?x%`1}~xGkhm
zC2>X}ahKvzm?b98Dy}6G=M)|ukcqn$H%OiW8x>69%-A_KlUHdHK;aPX#=?JR8rV81
zF(s04j3pMNX5tAcaUj{Jlad=GTxn6s1(E|Cg@EL?ZI<MmSs<ItWRy3#Sxq-gZeCZZ
zDdc5cU(l#xx|GW%m)9s*l3FfjvdMWG^_ZNlW~M0*JJJKl5PnodhEUgW^N2-{`p&$3
zDPJ&VwOn&}i)v{#X<SnBNAd+zNF-9Zl#xgjJM3^Au~mo~eFWGdsda^yxf`NAgd-sN
zYMos$@V2t)66#*&J`r|c8A&>!0s${;1-2iw>qI1mV@*3j#8nL{k-h2;v`*k`Pe=qw
z?@@oCwd%g*hcnRbQHS3!Tg~)9qVT2`fv?}5x5o5St+_q3u@9>;9~Kq3LBbFtXv=%m
zZma$o5+eonDjOpUOw>IYb?=+qq7RV(DU7^MsYb`AqLRty3)zA`mofRKZQs=tpWgI9
zz0Cm7+$wHidH_|rMyU^Mn+(N=)-gK~8URkQy%d8EKJ4SsYZlldsk=C_=Rx@3t-$Aj
zucy9^ZN|Qz`Z4xH?5C+;V?W34%4${4mF3)BeW9us%X+aAet-GQjq`PZbcNSXt(~fd
z2Fszr?a&b5NvH)v59^`}Hk3M7Csrml4pyY-{ZROkj#vM1v}1IH+!^T}li10mQ*U5F
zU|0b2TL6RPIRFDolk7z4(11h)!yeG1W1x3x*Io&6IJvhz?Et3b3w^_7H&bSxbJAF_
zPmp~-h7?>Dd>ja;F*#3=f$6cR#MtfJ9xXsIO+c}e029GVqy+#g(<ZN8Rg?3E3i;Qv
z*_1&M+4N~(CaW7X%34T(IRML(m#Li9b&N1{mIg3-L1+U;bGs;LtriV^BM@3Gt(0zj
zPz#0YE|1uQio!>Qjj3A~zqnWncC8C*LNypE2P3ybx2G$?7f~m!i49#PH~<(4c0H`~
zEj)Y`+IaiRa77w$F!9-_e{_J{8HkK=>|;I0Y33QY5;Sv?hVe;Cw}Yr@Y^7nJl>hIV
z0-*>-h#%(6bSE<!bag~84FhX0tq90Pf2*|6^91_z1B3Vp(yFi`tom2{6(Nk0xFW6w
zRs#2g9*SQJQMV~(w4|KDw@2zPIK$+qrWvN^*zu8<PMkE^xrMpLZFp?<_%2N(Om8BQ
z)s*=R&ZR_RZeF(DvWW!6cGbWMCYMHlZ4&FKM#`}+C^CeJj%<nSxOjK?pHAN0wbSVZ
z7IwLN8%xj;kIl-d9K2)RNK#cc)QBNp&Zv>;R3@tr8z}?kS7e%;mFe(_qtU|=IcaFr
zQ5`>uI{YMXRL4LSeI?pS@pH)Jv6-cEGp0DB8WUDyvyg0x;~LG%h5?OEoOY%M##0&f
zoSaiKpqJnhYGT%wbk%6B5kQ*24-k_(KRN!U>6I0wxz36J9fH%X7cT9?8MaB&N7bx$
z#onLdH%TjckA%~Wu)j(%$=ILt?|{`=hGBjue)!cr#QV&0cU9~yi@h7Cx5eQ_59oaT
z%V(=nUs>wA+yDBuG`=W;GB~)rPz?-}0|U2DZwHPpN}ywWRnk)?JsZ&qc@Aa%df-~%
zCciGNNfpv(X{w~7Oge5Ju8@QOa)+4SzX`DVI72vTx%eB~b6@QExOZ`^=8Y}BR^vR^
cFI>B@G*RQcRW4lS!W+-t<DRdJglpvZKR@y;{r~^~

literal 0
HcmV?d00001

diff --git a/pythonProject/cf..py b/pythonProject/cf..py
deleted file mode 100644
index 0cff032..0000000
--- a/pythonProject/cf..py
+++ /dev/null
@@ -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)
-
-
-
diff --git a/pythonProject/db_log.txt b/pythonProject/db_log.txt
index e69de29..192c3d2 100644
--- a/pythonProject/db_log.txt
+++ b/pythonProject/db_log.txt
@@ -0,0 +1 @@
+2024-05-29 18:05:36,839 ERROR connect Error
diff --git a/pythonProject/dp.py b/pythonProject/dp.py
index 1cce2ac..0787d48 100644
--- a/pythonProject/dp.py
+++ b/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)
\ No newline at end of file
diff --git a/pythonProject/films.py b/pythonProject/films.py
new file mode 100644
index 0000000..177e8b6
--- /dev/null
+++ b/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()
diff --git a/pythonProject/test.py b/pythonProject/test.py
deleted file mode 100644
index 5376f0b..0000000
--- a/pythonProject/test.py
+++ /dev/null
@@ -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)
\ No newline at end of file