1 import time
2 import traceback
3 import requests
4 from lxml import etree
5 import re
6 from bs4 import BeautifulSoup
7 from lxml.html.diff import end_tag
8 import json
9 import pymysql
10 #连接数据库 获取游标
11 def get_conn():
12 \"\"\"
13 :return: 连接,游标
14 \"\"\"
15 # 创建连接
16 conn = pymysql.connect(host=\"82.157.112.34\",
17 user=\"root\",
18 password=\"root\",
19 db=\"MovieRankings\",
20 charset=\"utf8\")
21 # 创建游标
22 cursor = conn.cursor() # 执行完毕返回的结果集默认以元组显示
23 if ((conn != None) & (cursor != None)):
24 print(\"数据库连接成功!游标创建成功!\")
25 else:
26 print(\"数据库连接失败!\")
27 return conn, cursor
28 #关闭数据库连接和游标
29 def close_conn(conn, cursor):
30 if cursor:
31 cursor.close()
32 if conn:
33 conn.close()
34 return 1
35 def get_iqy():
36 # 获取数据库总数据条数
37 conn, cursor = get_conn()
38 sql = \"select count(*) from movieiqy\"
39 cursor.execute(sql) # 执行sql语句
40 conn.commit() # 提交事务
41 all_num = cursor.fetchall()[0][0] #cursor 返回值的类型是一个元祖的嵌套形式 比如( ( ) ,)
42 pagenum=int(all_num/48)+1 #这里是计算一个下面循环的起始值 每48个电影分一组
43 print(pagenum)
44 print(\"movieiqy数据库有\", all_num, \"条数据!\")
45
46
47 url = \"https://pcw-api.iqiyi.com/search/recommend/list?channel_id=1&data_type=1&mode=11&page_id=1&ret_num=48&session=ee4d98ebb4e8e44c8d4b14fa90615fb7\"
48 headers = {
49 \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36\"
50 }
51 # response=requests.get(url=url,headers=headers)
52 # response.encoding=\"utf-8\"
53 # page_text=response.text
54 # print(page_text)
55 \"\"\"
56 \"\"\"
57 #
58 temp_list = [] #暂时存放单部电影的数据
59 dataRes = [] #每次循环把单部电影数据放到这个list
60 for i in range(pagenum+1, pagenum+100): #循环100-1次
61 url = \"https://pcw-api.iqiyi.com/search/recommend/list?channel_id=1&data_type=1&mode=11&page_id=1&ret_num=48&session=ee4d98ebb4e8e44c8d4b14fa90615fb7\"
62 url_0 = \"https://pcw-api.iqiyi.com/search/recommend/list?channel_id=1&data_type=1&mode=11&page_id=\"
63 url_0 = url_0 + str(i) + \"&ret_num=48&session=ad1d98bb953b7e5852ff097c088d66f2\"
64 print(url_0) #输出拼接好的url
65 response = requests.get(url=url_0, headers=headers)
66 response.encoding = \"utf-8\"
67 page_text = response.text
68 #解析json对象
69 json_obj = json.loads(page_text)
70 #这里的异常捕获是因为 测试循环的次数有可能超过电影网站提供的电影数 为了防止后续爬到空的json对象报错
71 try:
72 json_list = json_obj[\'data\'][\'list\']
73 except KeyError:
74 return dataRes #json为空 程序结束
75 for j in json_list: # 开始循环遍历json串
76 # print(json_list)
77 name = j[\'name\'] #找到电影名
78 print(name)
79 temp_list.append(name)
80 #异常捕获,防止出现电影没有评分的现象
81 try:
82 score = j[\'score\'] #找到电影评分
83 print(score)
84 temp_list.append(score)
85 except KeyError:
86 print( \"KeyError\")
87 temp_list.append(\"iqy暂无评分\") #替换字符串
88
89 link = j[\'playUrl\'] #找到电影链接
90 temp_list.append(link)
91 # 解析播放状态
92 state = []
93 pay_text = j[\'payMarkUrl\'] #因为播放状态只有在一个图片链接里有 所以需要使用re解析出类似vip和only(独播)的字样
94 if (len(pay_text) == 0): #如果没有这个图片链接 说明电影是免费播放
95 state=\"免费\"
96 else:
97 find_state = re.compile(\"(.*?).png\")
98 state = re.findall(find_state, pay_text) #正则匹配链接找到vip
99 if(len(state)!=0): #只有当链接不为空再执行
100 # print(state)
101 # 再次解析
102 state = state[0][0:3] #字符串分片
103
104 # 这里只输出了三个字符,如果是独播,页面显示的是only,我们设置为”独播“
105 if (state == \"onl\"):
106 state = \"独播\"
107 else:
108 state = \"VIP\"
109 # print(state)
110 # 添加播放状态
111 temp_list.append(state)
112 dataRes.append(temp_list)
113 # print(temp_list)
114 temp_list = []
115
116 print(\'___________________________\')
117 return dataRes
118
119 def insert_iqy():
120 cursor = None
121 conn = None
122 try:
123 count=0
124 list = get_iqy()
125 print(f\"{time.asctime()}开始插入爱奇艺电影数据\")
126 conn, cursor = get_conn()
127 sql = \"insert into movieiqy (id,name,score,path,state) values(%s,%s,%s,%s,%s)\"
128 for item in list:
129 print(item)
130 count = count + 1
131 if (count % 48 == 0):
132 print(\'___________________________\')
133 #异常捕获,防止数据库主键冲突
134 try:
135 cursor.execute(sql, [0, item[0], item[1], item[2], item[3] ])
136 except pymysql.err.IntegrityError:
137 print(\"重复!跳过!\")
138
139 conn.commit() # 提交事务 update delete insert操作
140 print(f\"{time.asctime()}插入爱奇艺电影数据完毕\")
141 except:
142 traceback.print_exc()
143 finally:
144 close_conn(conn, cursor)
145 return;
146
147 if __name__ == \'__main__\':
148 # get_iqy()
149 insert_iqy()
来源:https://www.cnblogs.com/rainbow-1/p/14727905.html
图文来源于网络,如有侵权请联系删除。