您现在的位置是：首页 > 建站建站

WAP网站是啥？wap是移动端还是手机端？

cc博主2022-04-12【建站】672人已围观

WAP网站是啥？wap是移动端还是手机端？python百度下拉框关键词采集源码：

01#百度下拉框关键词采集
02import requests
03import json
04import urllib
05
06def get_keywords(word): #获取下拉词json数据并返回数组
07    url=f"https://www.baidu.com/sugrec?pre=1&ie=utf-8&json=1&prod=pc&wd={word}"
08    html=requests.get(url)
09    html=html.json()
10    #print(html)
11    #print(html['g'])
12    key_words=[]
13    for key_word in html['g']:
14        print(key_word['q'])
15        key_words.append(key_word['q'])
16    #print(key_words)
17    return key_words
18
19def get_sug(word): #获取下拉词json数据并返回数组2
20    url = 'https://sp0.baidu.com/5a1Fazu8AA54nxGko9WTAnF6hhy/su?wd=%s&sugmode=2&json=1&p=3&sid=1427_21091_21673_22581&req=2&pbs=%%E5%%BF%%AB%%E6%%89%%8B&csor=2&pwd=%%E5%%BF%%AB%%E6%%89%%8B&cb=jQuery11020924966752020363_1498055470768&_=1498055470781' % word
21    r = requests.get(url, verify=False)  # 请求API接口，取消了HTTPS验证
22    cont = r.content  # 获取返回的内容
23    res = cont[41: -2].decode('gbk')  # 只取返回结果中json格式一段，并且解码为unicode
24    res_json = json.loads(res)  # json格式转换
25    return res_json['s']  # 返回关键词列表
26
27def get_word(word): #获取下拉词json数据并返回数组3
28    url=f'http://suggestion.baidu.com/su?wd={word}&sugmode=3&json=1'
29    html=requests.get(url).text
30    html=html.replace("window.baidu.sug(",'')
31    html = html.replace(")", '')
32    html = html.replace(";", '')
33    #print(html)
34    html = json.loads(html)
35    key_words=html['s']
36    #print(key_words)
37    return key_words
38
39def get_word_scv(): #获取下拉词json数据并写入excel
40    opencsv=open('word.csv','a+')
41    for word in open('gjc.txt',encoding='utf-8'):
42        print(urllib.parse.quote_plus(word))
43        url='https://sp0.baidu.com/5a1Fazu8AA54nxGko9WTAnF6hhy/su?wd=%s&sugmode=2&json=1&p=3&sid=1427_21091_21673_22581&req=2' % urllib.parse.quote_plus(word)
44        html=requests.get(url).text
45        html=html.replace('window.baidu.sug(','')
46        html=html.replace(');','')
47        #print (html)
48        html=json.loads(html)
49        #print (html['s'])
50        for i in html['s']:
51            print (i)
52            opencsv.write('%s\n'%i)
53
54def get_more_word(word): #查询所以下拉词并去除重复
55    more_word=[]
56    for i in 'abcdefghijklmnopqrstuvwxyz':
57        more_word.extend(get_keywords('%s%s'%(word,i)))
58    print(more_word)
59    print(len(more_word))
60    print(len(list(set(more_word))))
61    return list(set(more_word))  #去重操作
62
63
64def get_more_sug(word): #查询所以下拉词并去除重复
65    all_words = []
66    for i in 'abcdefghijklmnopqrstuvwxyz':
67        all_words += get_sug(word+i)  # 遍历字母表 | 利用了上一个函数
68    print(len(list(set(all_words))))
69    return list(set(all_words))  # 去重