Python 爬取热词并进行分类数据分析-[拓扑数据]

　　setAttr("value","人工智能")方法并不能实现input的value属性值变为想要的“人工智能”，我采用的是sendKeys("人工智能")方法来实现，不过这样又有了一个问题，每一次sendKeys（）相当于再input内部又附加了这样的字符，比如原本input里有“茄子”字样，之后使用sendKeys(“蔬菜”)，input里就变成了“茄子蔬菜”！这个问题就导致了我不能实现页面直接跳转。如何解决呢？

　　我从它的方法里找到了clear()方法，亲测可用（在sendKeys之前使用）。

　　我在这里提供测试类代码：

  1 import parsel
  2 from urllib import request
  3 import codecs
  4 from selenium import webdriver
  5 import time
  6 
  7 
  8 # [ 对字符串的特殊处理方法-集合 ]
  9 class StrSpecialDealer:
 10     # 取得当前标签内的文本
 11     @staticmethod
 12     def getReaction(stri):
 13         strs = StrSpecialDealer.simpleDeal(str(stri))
 14         strs = strs[strs.find('>')+1:strs.rfind('<')]
 15         return  strs
 16 
 17     # 去除基本的分隔符
 18     @staticmethod
 19     def simpleDeal(stri):
 20         strs = str(stri).replace(" ", "")
 21         strs = strs.replace("	", "")
 22         strs = strs.replace("
", "")
 23         strs = strs.replace("
", "")
 24         return strs
 25 
 26     # 删除所有标签标记
 27     @staticmethod
 28     def deleteRe(stri):
 29         strs = str(stri)
 30         st = strs.find('<')
 31         while(st!=-1):
 32             str_delete = strs[strs.find('<'):strs.find('>')+1]
 33             strs = strs.replace(str_delete,"")
 34             st = strs.find('<')
 35 
 36         return strs
 37 
 38     # 删除带有 日期 的句子
 39     @staticmethod
 40     def de_date(stri):
 41         lines = str(stri).split("。")
 42         strs = ""
 43         num = lines.__len__()
 44         for i in range(0,num):
 45             st = str(lines[i])
 46             if (st.__contains__("年") | st.__contains__("月")):
 47                 pass
 48             else:
 49                 strs += st + "。"
 50         strs = strs.replace("。。", "。")
 51         return strs
 52 
 53     # 取得带有 日期 的句子之前的句子
 54     @staticmethod
 55     def ut_date(stri):
 56         lines = str(stri).split("。")
 57         strs = ""
 58         num = lines.__len__()
 59         for i in range(0, num):
 60             st = str(lines[i])
 61             if (st.__contains__("年")| st.__contains__("月")):
 62                 break
 63             else:
 64                 strs += st + "。"
 65         strs = strs.replace("。。","。")
 66         return strs
 67 
 68     @staticmethod
 69     def beat(stri,num):
 70         strs = str(stri)
 71         for i in range(0,num):
 72             strs = strs.replace("["+str(i)+"]","")
 73 
 74         return  strs
 75 
 76 
 77 # [ 连续网页爬取的对象 ]
 78 class WebConnector:
 79     profile = ""
 80     sw = ""
 81 
 82     # ---[定义构造方法]
 83     def __init__(self):
 84         self.profile = webdriver.Firefox()
 85         self.profile.get('https://baike.baidu.com/')
 86 
 87     # ---[定义释放方法]
 88     def __close__(self):
 89         self.profile.quit()
 90 
 91     # 获取 url 的内部 HTML 代码
 92     def getHTMLText(self):
 93         a = self.profile.page_source
 94         return a
 95 
 96     # 获取页面内的基本链接
 97     def getFirstChanel(self):
 98         index_html = self.getHTMLText()
 99         index_sel = parsel.Selector(index_html)
100         links = index_sel.css('.lemma-summary').extract()[0]
101         tpl = StrSpecialDealer.simpleDeal(str(links))
102         tpl = StrSpecialDealer.beat(tpl,20)
103         tpl = StrSpecialDealer.deleteRe(tpl)
104         tpl = StrSpecialDealer.ut_date(tpl)
105         return tpl
106 
107     def getMore(self,refers):
108         self.profile.find_element_by_id("query").clear()
109         self.profile.find_element_by_id("query").send_keys(refers)
110         self.profile.find_element_by_id("search").click()
111         time.sleep(1)
112 
113 
114 def main():
115     wc = WebConnector()
116     wc.getMore("人工智能")
117     s = wc.getFirstChanel()
118     print(s)
119     wc.getMore("5G")
120     t = wc.getFirstChanel()
121     print(t)
122     wc.__close__()
123 
124 
125 main()

test.py

　　嗯，然后我继续整合，将数据导入成文件批处理

　　对应代码：

  1 import parsel
  2 from urllib import request
  3 import codecs
  4 from selenium import webdriver
  5 import time
  6 
  7 
  8 # [ 整理后的数据 ]
  9 class Info:
 10 
 11     # ---[ 方法区 ]
 12     # 构造方法
 13     def __init__(self,name,num,more):
 14         self.name = name
 15         self.num = num
 16         self.more = more
 17 
 18     def __toString__(self):
 19         return (self.name+"	"+str(self.num)+"	"+self.more)
 20 
 21     def __toSql__(self,table):
 22         return ("Insert into "+table+" values ('"+self.name+"',"+self.num+",'"+self.more+"');")
 23 
 24     # ---[ 数据区 ]
 25     # 名称
 26     name = ""
 27     # 频数
 28     num = 0
 29     # 中文解释
 30     more = 0
 31 
 32 
 33 # [写文件的方法集合]
 34 class FileToWebAndContent:
 35 
 36     fileReaderPath = ""
 37     wc = ""
 38     sw = ""
 39 
 40     def __init__(self,r,w):
 41         self.fileReaderPath = r
 42         self.wc = WebConnector()
 43         self.sw = StringWriter(w)
 44         self.sw.makeFileNull()
 45 
 46     def __free__(self):
 47         self.wc.__close__()
 48 
 49     def __deal__(self):
 50         fw = open(self.fileReaderPath, mode='r', encoding='utf-8')
 51         lines = fw.readlines()
 52         num = lines.__len__()
 53         for i in range(0,num):
 54             str_line = lines[i]
 55             gr = str_line.split("	")
 56             name_b = StrSpecialDealer.simpleDeal(gr[0])
 57             num_b = StrSpecialDealer.simpleDeal(gr[1])
 58             if(int(num_b)<=2):
 59                 break
 60             self.wc.getMore(name_b)
 61             more_b = self.wc.getFirstChanel()
 62             if(more_b==""):
 63                 continue
 64             info = Info(name_b,num_b,more_b)
 65             self.sw.write(info.__toString__())
 66 
 67 
 68 # [ 对字符串的特殊处理方法-集合 ]
 69 class StrSpecialDealer:
 70     # 取得当前标签内的文本
 71     @staticmethod
 72     def getReaction(stri):
 73         strs = StrSpecialDealer.simpleDeal(str(stri))
 74         strs = strs[strs.find('>')+1:strs.rfind('<')]
 75         return  strs
 76 
 77     # 去除基本的分隔符
 78     @staticmethod
 79     def simpleDeal(stri):
 80         strs = str(stri).replace(" ", "")
 81         strs = strs.replace("	", "")
 82         strs = strs.replace("
", "")
 83         strs = strs.replace("
", "")
 84         return strs
 85 
 86     # 删除所有标签标记
 87     @staticmethod
 88     def deleteRe(stri):
 89         strs = str(stri)
 90         st = strs.find('<')
 91         while(st!=-1):
 92             str_delete = strs[strs.find('<'):strs.find('>')+1]
 93             strs = strs.replace(str_delete,"")
 94             st = strs.find('<')
 95 
 96         return strs
 97 
 98     # 删除带有 日期 的句子
 99     @staticmethod
100     def de_date(stri):
101         lines = str(stri).split("。")
102         strs = ""
103         num = lines.__len__()
104         for i in range(0,num):
105             st = str(lines[i])
106             if (st.__contains__("年") | st.__contains__("月")):
107                 pass
108             else:
109                 strs += st + "。"
110         strs = strs.replace("。。", "。")
111         return strs
112 
113     # 取得带有 日期 的句子之前的句子
114     @staticmethod
115     def ut_date(stri):
116         lines = str(stri).split("。")
117         strs = ""
118         num = lines.__len__()
119         for i in range(0, num):
120             st = str(lines[i])
121             if (st.__contains__("年")| st.__contains__("月")):
122                 break
123             else:
124                 strs += st + "。"
125         strs = strs.replace("。。","。")
126         return strs
127 
128     @staticmethod
129     def beat(stri,num):
130         strs = str(stri)
131         for i in range(0,num):
132             strs = strs.replace("["+str(i)+"]","")
133 
134         return  strs
135 
136 
137 # [写文件的方法集合]
138 class StringWriter:
139     filePath = ""
140 
141     def __init__(self,str):
142         self.filePath = str
143         pass
144 
145     def makeFileNull(self):
146         f = codecs.open(self.filePath, "w+", 'utf-8')
147         f.write("")
148         f.close()
149 
150     def write(self,stri):
151         f = codecs.open(self.filePath, "a+", 'utf-8')
152         f.write(stri + "
")
153         f.close()
154 
155 
156 # [ 连续网页爬取的对象 ]
157 class WebConnector:
158     profile = ""
159     sw = ""
160 
161     # ---[定义构造方法]
162     def __init__(self):
163         self.profile = webdriver.Firefox()
164         self.profile.get('https://baike.baidu.com/')
165         # self.sw = StringWriter("../testFile/rc/moreinfo.txt")
166         # self.sw.makeFileNull()
167 
168     # ---[定义释放方法]
169     def __close__(self):
170         self.profile.quit()
171 
172     # 获取 url 的内部 HTML 代码
173     def getHTMLText(self):
174         a = self.profile.page_source
175         return a
176 
177     # 获取页面内的基本链接
178     def getFirstChanel(self):
179         try:
180             index_html = self.getHTMLText()
181             index_sel = parsel.Selector(index_html)
182             links = index_sel.css('.lemma-summary').extract()[0]
183             tpl = StrSpecialDealer.simpleDeal(str(links))
184             tpl = StrSpecialDealer.beat(tpl, 20)
185             tpl = StrSpecialDealer.deleteRe(tpl)
186             tpl = StrSpecialDealer.ut_date(tpl)
187             return tpl
188         except:
189             return ""
190 
191     def getMore(self,refers):
192         self.profile.find_element_by_id("query").clear()
193         self.profile.find_element_by_id("query").send_keys(refers)
194         self.profile.find_element_by_id("search").click()
195         time.sleep(1)
196 
197 
198 def main():
199     ftwac = FileToWebAndContent("../testFile/rc/output.txt", "../testFile/rc/moreinfo.txt")
200     ftwac.__deal__()
201     ftwac.__free__()
202 
203 
204 main()

MoreInfo.py

　　对应得到文件截图：

Python 爬取 热词并进行分类数据分析-[拓扑数据]

Python 爬取热词并进行分类数据分析-[拓扑数据]