Python-爬虫-抓取头条街拍图片-1.1

  1 #今日头条街拍数据抓取，将图片存入文件目录，将文件目录存放至mysql数据库
  2 import requests
  3 import  time
  4 from urllib.parse import urlencode
  5 import urllib.parse
  6 import os
  7 from requests import Request, Session
  8 import pymysql
  9 class TouTiaoDeep:
 10     def __init__(self):
 11         self.url=‘https://www.toutiao.com/search_content/‘
 12         self.imagePath=‘D:/toutiao/images/‘
 13         self.headers={
 14             ‘Accept‘:‘application/json, text/javascript‘,
 15             ‘Accept-Encoding‘:‘gzip, deflate, br‘,
 16             ‘Content-Type‘:‘application/x-www-form-urlencoded‘,
 17             ‘Host‘: ‘www.toutiao.com‘,
 18             ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:64.0) Gecko/20100101 Firefox/64.0‘,
 19             ‘X-Requested-With‘: ‘XMLHttpRequest‘
 20         }
 21         self.param={
 22             ‘offset‘:0,
 23             ‘format‘:‘json‘,
 24             ‘keyword‘:  ‘街拍‘,
 25             ‘autoload‘:‘true‘,
 26             ‘count‘:20,
 27             ‘cur_tab‘:1,
 28             ‘form‘:‘search_tab‘,
 29             ‘pd‘:‘synthesis‘
 30          }
 31         self.filePath="D:/toutiaoImages"
 32         self.imgDict={} #{rows:[{title:‘‘,pathName:‘‘,images:[{name:‘‘,desc:‘‘,date:‘‘,downloadUrl:‘‘}...},...] ]}
 33 
 34     def getImgDict(self,offset):
 35         self.param[‘offset‘]=offset#偏移量
 36         session=Session()
 37         req=Request(method=‘GET‘,url=self.url ,params=self.param,headers=self.headers  )
 38         prep =  session.prepare_request(req)
 39         res = session.send(prep)
 40         #print(res.status_code)
 41         if res.status_code==200:
 42             json=res.json()
 43             #print(json)
 44             for i in range(len(json[‘data‘])):
 45                 if  ‘has_image‘ in json[‘data‘][i].keys() and json[‘data‘][i][‘has_image‘]:#其中有视频列表组，因此排除那些视频组
 46                     # print("标题：",json[‘data‘][i][‘title‘])
 47                     # print("图库：",json[‘data‘][i][‘image_list‘])
 48                     # print("图库简介：",json[‘data‘][i][‘abstract‘])
 49                     # print("图片个数：",(len(json[‘data‘][i][‘image_list‘])))
 50                     yield {
 51                         ‘group_id‘:json[‘data‘][i][‘group_id‘],
 52                         ‘groupTitle‘:json[‘data‘][i][‘title‘],
 53                         ‘groupImages‘:json[‘data‘][i][‘image_list‘],
 54                         ‘total‘:len(json[‘data‘][i][‘image_list‘]),
 55                         ‘abstract‘:json[‘data‘][i][‘abstract‘],
 56                         ‘large_image_url‘:json[‘data‘][i][‘large_image_url‘][:json[‘data‘][i][‘large_image_url‘].rindex(‘/‘)]
 57                         # 例如：http://p3-tt.bytecdn.cn/large/pgc-image/2dc7e3cd2e0c46f69ee67c11c13ff58e  最后一个是图片id，前面是大图片地址（每一组大图片地址不同）
 58                         # print(item[‘large_image_url‘][:item[‘large_image_url‘].rindex(‘/‘)])#获取组大图片的地址url
 59                     }
 60     def imagesDownLoad(self,offset):
 61         # 获得当前时间时间戳
 62         now = int(time.time())
 63         #转换为其他日期格式,如:"%Y-%m-%d %H:%M:%S"
 64         timeStruct = time.localtime(now)
 65         strTime = time.strftime("%Y-%m-%d %H:%M:%S", timeStruct)
 66 
 67         datas=self.getImgDict(offset)
 68         for item in datas:
 69             #print(item)
 70             #下载图片信息
 71             groupImages=item[‘groupImages‘]
 72             print(item[‘groupTitle‘])
 73             for i in groupImages:
 74                 #print(i[‘url‘][(i[‘url‘].rindex(‘/‘)):])截取图片id即，图片地址最有一个namespace
 75                 imgURL=item[‘large_image_url‘]+i[‘url‘][(i[‘url‘].rindex(‘/‘)):]#拼成完成的image URL
 76                 print(imgURL)
 77                 #创建存储文件夹,组id命名
 78                 if not os.path.exists(self.imagePath+item[‘group_id‘]):
 79                     os.makedirs(self.imagePath+item[‘group_id‘])
 80                 #获取图片存上面指定目录中
 81                 try:
 82                     a = urllib.request.urlopen(imgURL)
 83                 except :
 84                       a=urllib.request.urlopen("http://p1.pstatp.com/origin/pgc-image/"+i[‘url‘][(i[‘url‘].rindex(‘/‘)):])#注意有一部分图片url路径是：http://p1.pstatp.com/origin/pgc-image/7290e8fcfdbc4a458d8ed7a6c1581283[前面的p1 可以任意换成p任意数字即可]
 85                       #注意；改程序在二十左右页抓取会出现图片路径资源错误 
 86                 try:
 87                     f = open(self.imagePath+item[‘group_id‘]+"/"+i[‘url‘][(i[‘url‘].rindex(‘/‘)):]+‘.jpg‘, "wb")
 88                     f.write(a.read())
 89                     f.close()
 90                     #持久化图片信息
 91                     rows_1={
 92                         ‘imageId‘: i[‘url‘][(i[‘url‘].rindex(‘/‘)):],
 93                         ‘imagesource‘: imgURL,
 94                         ‘imageName‘:i[‘url‘][(i[‘url‘].rindex(‘/‘)):]+‘.jpg‘,
 95                         ‘imageDesc‘: ‘无‘,
 96                         ‘groupid‘: item[‘group_id‘]
 97                     }
 98                     self.imageInfPersistent(rows_1)
 99                 except:
100                     print(‘文件下载失败‘)
101             #持久化图片组信息
102             rows_2 = {
103                 ‘groupid‘:item[‘group_id‘],
104                 ‘grouptitle‘:item[‘groupTitle‘],
105                 ‘groupdesc‘:item[‘abstract‘],
106                 ‘path‘:‘toutiao/images/‘+item[‘group_id‘],
107                 ‘createTime‘:strTime
108             }
109             self.imgGroupPersistent(rows_2)
110 
111 
112 
113     #mysql数据库持久化
114     def mysqlPersistent(self,tableName,data):
115         db = pymysql.connect(host=‘localhost‘, user=‘root‘, password=‘admin‘, port=3306, db=‘test‘)
116         cursor = db.cursor()
117         try:
118             columns = ‘,‘.join(data.keys())
119             values = ‘,‘.join([‘%s‘] * len(data))
120             sql =  ‘insert into {table}({keys}) VALUES ({values}) ‘.format(table=tableName, keys=columns, values=values)
121             cursor.execute(sql, tuple(data.values()))
122             db.commit()
123         except:
124             db.rollback()
125         finally:
126             db.close()
127 
128     #持久化图片组信息
129     def imgGroupPersistent(self,groupDict):
130         #图组信息表：组id、组标题、组简介、本地存储路径、创建时间
131        self.mysqlPersistent(‘imageGroup‘,groupDict)
132 
133     #持久化图片信息
134     def imageInfPersistent(self,imageInfDict):
135         #图片信息表：图片id、来源地址、简介、所属组id
136         self.mysqlPersistent(‘imageInfo‘, imageInfDict)
137 
138     #创建表
139     def createImgTable(self):
140         sql_imgGroup= ‘create table imageGroup(groupid varchar(50) primary key,grouptitle varchar(200)  ,groupdesc text,path varchar(500),createTime varchar(50))‘
141         sql_imgInf=‘create table imageInfo(imageId varchar(50) primary key,imagesource varchar(200) ,imageName varchar(100),imageDesc text,groupid varchar(50) )‘
142         db = pymysql.connect(host=‘localhost‘, user=‘root‘, password=‘admin‘, port=3306, db=‘test‘)
143 
144         cursor = db.cursor()
145         try :
146             cursor.execute(sql_imgGroup)
147             cursor.execute(sql_imgInf)
148         except:
149             print(‘表创建失败！‘)
150         finally:
151             cursor.close()
152 
153     #删除表
154     def dropImgTables(self):
155         sql_dropImageGroup = ‘ drop table if exists  imageGroup ‘
156         sql_dropImageInfo = ‘  drop table if exists   imageInfo ‘
157         db = pymysql.connect(host=‘localhost‘, user=‘root‘, password=‘admin‘, port=3306, db=‘test‘)
158 
159         cursor = db.cursor()
160         try:
161             cursor.execute(sql_dropImageGroup)
162             cursor.execute(sql_dropImageInfo)
163         except:
164             print(‘表删除失败！‘)
165         finally:
166             cursor.close()
167 
168 
169 if __name__==‘__main__‘:
170     deep=TouTiaoDeep()
171     deep.dropImgTables()#删除表
172     deep.createImgTable()#创建表
173     #print(deep.getImgDict())
174     for i in range(0,10*20,10):
175         deep.imagesDownLoad(i)
176     #deep.createImgTable()