百度指数中这些折线上的点是是通过两个字符串加密过的
其中，数据接口会返回一个data值作为e值，和一个uniqid用作去请求t值
当得到这两个之后会进行一个处理函数decrypt
通过带入t和e到decrypt测试，就是我们想要的，python版如下
def decrypt_py(t,e):
"""
:param t:
:param e:
:return: 解析出来的数据
"""
a=dict()
length=int(len(t)/2)
for o in range(length):
a[t[o]] = t[length + o]
r="".join([a[each]for each in e ]).split(",")
return r对于省份和城市的名字是存在一个字典中来调用的
#baidu_id.py
city={1:"济南",2:"贵阳",3:"黔南",4:"六盘水",5:"南昌",6:"九江",7:"鹰潭",8:"抚州",9:"上饶",10:"赣州",11:"重庆",13:"包头",14:"鄂尔多斯",15:"巴彦淖尔",16:"乌海",17:"阿拉善盟",19:"锡林郭勒盟",20:"呼和浩特",21:"赤峰",22:"通辽",25:"呼伦贝尔",28:"武汉",29:"大连",30:"黄石",31:"荆州",32:"襄阳",33:"黄冈",34:"荆门",35:"宜昌",36:"十堰",37:"随州",38:"恩施",39:"鄂州",40:"咸宁",41:"孝感",42:"仙桃",43:"长沙",44:"岳阳",45:"衡阳",46:"株洲",47:"湘潭",48:"益阳",49:"郴州",50:"福州",51:"莆田",52:"三明",53:"龙岩",54:"厦门",55:"泉州",56:"漳州",57:"上海",59:"遵义",61:"黔东南",65:"湘西",66:"娄底",67:"怀化",68:"常德",73:"天门",74:"潜江",76:"滨州",77:"青岛",78:"烟台",79:"临沂",80:"潍坊",81:"淄博",82:"东营",83:"聊城",84:"菏泽",85:"枣庄",86:"德州",87:"宁德",88:"威海",89:"柳州",90:"南宁",91:"桂林",92:"贺州",93:"贵港",94:"深圳",95:"广州",96:"宜宾",97:"成都",98:"绵阳",99:"广元",100:"遂宁",101:"巴中",102:"内江",103:"泸州",104:"南充",106:"德阳",107:"乐山",108:"广安",109:"资阳",111:"自贡",112:"攀枝花",113:"达州",114:"雅安",115:"吉安",117:"昆明",118:"玉林",119:"河池",123:"玉溪",124:"楚雄",125:"南京",126:"苏州",127:"无锡",128:"北海",129:"钦州",130:"防城港",131:"百色",132:"梧州",133:"东莞",134:"丽水",135:"金华",136:"萍乡",137:"景德镇",138:"杭州",139:"西宁",140:"银川",141:"石家庄",143:"衡水",144:"张家口",145:"承德",146:"秦皇岛",147:"廊坊",148:"沧州",149:"温州",150:"沈阳",151:"盘锦",152:"哈尔滨",153:"大庆",154:"长春",155:"四平",156:"连云港",157:"淮安",158:"扬州",159:"泰州",160:"盐城",161:"徐州",162:"常州",163:"南通",164:"天津",165:"西安",166:"兰州",168:"郑州",169:"镇江",172:"宿迁",173:"铜陵",174:"黄山",175:"池州",176:"宣城",177:"巢湖",178:"淮南",179:"宿州",181:"六安",182:"滁州",183:"淮北",184:"阜阳",185:"马鞍山",186:"安庆",187:"蚌埠",188:"芜湖",189:"合肥",191:"辽源",194:"松原",195:"云浮",196:"佛山",197:"湛江",198:"江门",199:"惠州",200:"珠海",201:"韶关",202:"阳江",203:"茂名",204:"潮州",205:"揭阳",207:"中山",208:"清远",209:"肇庆",210:"河源",211:"梅州",212:"汕头",213:"汕尾",215:"鞍山",216:"朝阳",217:"锦州",218:"铁岭",219:"丹东",220:"本溪",221:"营口",222:"抚顺",223:"阜新",224:"辽阳",225:"葫芦岛",226:"张家界",227:"大同",228:"长治",229:"忻州",230:"晋中",231:"太原",232:"临汾",233:"运城",234:"晋城",235:"朔州",236:"阳泉",237:"吕梁",239:"海口",241:"万宁",242:"琼海",243:"三亚",244:"儋州",246:"新余",253:"南平",256:"宜春",259:"保定",261:"唐山",262:"南阳",263:"新乡",264:"开封",265:"焦作",266:"平顶山",268:"许昌",269:"永州",270:"吉林",271:"铜川",272:"安康",273:"宝鸡",274:"商洛",275:"渭南",276:"汉中",277:"咸阳",278:"榆林",280:"石河子",281:"庆阳",282:"定西",283:"武威",284:"酒泉",285:"张掖",286:"嘉峪关",287:"台州",288:"衢州",289:"宁波",291:"眉山",292:"邯郸",293:"邢台",295:"伊春",297:"大兴安岭",300:"黑河",301:"鹤岗",302:"七台河",303:"绍兴",304:"嘉兴",305:"湖州",306:"舟山",307:"平凉",308:"天水",309:"白银",310:"吐鲁番",311:"昌吉",312:"哈密",315:"阿克苏",317:"克拉玛依",318:"博尔塔拉",319:"齐齐哈尔",320:"佳木斯",322:"牡丹江",323:"鸡西",324:"绥化",331:"乌兰察布",333:"兴安盟",334:"大理",335:"昭通",337:"红河",339:"曲靖",342:"丽江",343:"金昌",344:"陇南",346:"临夏",350:"临沧",352:"济宁",353:"泰安",356:"莱芜",359:"双鸭山",366:"日照",370:"安阳",371:"驻马店",373:"信阳",374:"鹤壁",375:"周口",376:"商丘",378:"洛阳",379:"漯河",380:"濮阳",381:"三门峡",383:"阿勒泰",384:"喀什",386:"和田",391:"亳州",395:"吴忠",396:"固原",401:"延安",405:"邵阳",407:"通化",408:"白山",410:"白城",417:"甘孜",422:"铜仁",424:"安顺",426:"毕节",437:"文山",438:"保山",456:"东方",457:"阿坝",466:"拉萨",467:"乌鲁木齐",472:"石嘴山",479:"凉山",480:"中卫",499:"巴音郭楞",506:"来宾",514:"北京",516:"日喀则",520:"伊犁",525:"延边",563:"塔城",582:"五指山",588:"黔西南",608:"海西",652:"海东",653:"克孜勒苏柯尔克孜",654:"天门仙桃",655:"那曲",656:"林芝",657:"None",658:"防城",659:"玉树",660:"伊犁哈萨克",661:"五家渠",662:"思茅",663:"香港",664:"澳门",665:"崇左",666:"普洱",667:"济源",668:"西双版纳",669:"德宏",670:"文昌",671:"怒江",672:"迪庆",673:"甘南",674:"陵水黎族自治县",675:"澄迈县",676:"海南",677:"山南",678:"昌都",679:"乐东黎族自治县",680:"临高县",681:"定安县",682:"海北",683:"昌江黎族自治县",684:"屯昌县",685:"黄南",686:"保亭黎族苗族自治县",687:"神农架",688:"果洛",689:"白沙黎族自治县",690:"琼中黎族苗族自治县",691:"阿里",692:"阿拉尔",693:"图木舒克"}
province={901:"山东",902:"贵州",903:"江西",904:"重庆",905:"内蒙古",906:"湖北",907:"辽宁",908:"湖南",909:"福建",910:"上海",911:"北京",912:"广西",913:"广东",914:"四川",915:"云南",916:"江苏",917:"浙江",918:"青海",919:"宁夏",920:"河北",921:"黑龙江",922:"吉林",923:"天津",924:"陕西",925:"甘肃",926:"新疆",927:"河南",928:"安徽",929:"山西",930:"海南",931:"台湾",932:"西藏",933:"香港",934:"澳门"}这个省份和城市可以通过js文件获取，点击人群画像时候在network中搜索一个地名，会查到一个js文件，点进去之后再次进行查询，就有好多好多城市了。
然后就可以动手了，需要登录一下取到游览器中的cookie,
已经根据接口更改修改了，5.20
然后看见有的小伙伴看见接口变了就不知道怎么做，推荐一个编码转换的网站，可以把它先解码，就会容易得多
http://tool.chinaz.com/tools/urlencode.aspx
import requests
import datetime
from utils.baidu_id import province, city
def getIndex(word="我和我的祖国"):
"""
搜索指数
:param word:
:return:
"""
insert_word = """[[{"name":"%s","wordType":1}]]""" % word
url = f"http://index.baidu.com/api/SearchApi/index?word={insert_word}&area=0&days=30"
rep_json = get_rep_json(url)
generalRatio = rep_json['data']['generalRatio']
uniqid = rep_json['data']['uniqid']
all_index_e = rep_json['data']['userIndexes'][0]['all']['data']
pc_index_e = rep_json['data']['userIndexes'][0]['pc']['data']
wise_index_e = rep_json['data']['userIndexes'][0]['wise']['data']
t = getPtbk(uniqid)
startDate = rep_json['data']['userIndexes'][0]['wise']['startDate']
all_news = getTopNews(decrypt_py(t, all_index_e), startDate, word)
pc_news = getTopNews(decrypt_py(t, pc_index_e), startDate, word)
wise_news = getTopNews(decrypt_py(t, wise_index_e), startDate, word)
for each in (all_news, pc_news, wise_news):
print(each)
return None
def getFeedIndex(word="我和我的祖国"):
"""
:param word: 关键词
:return: 资讯指数
"""
insert_word="""[[{"name":"%s","wordType":1}]]"""%word
url = "http://index.baidu.com/api/FeedSearchApi/getFeedIndex?word=%s&area=0&days=30" % insert_word
feed_index_data = get_rep_json(url)
uniqid = feed_index_data['data']['uniqid']
data = feed_index_data["data"]['index'][0]
generalRatio = data['generalRatio'] # 资讯指数概览
e = data['data']
t = getPtbk(uniqid)
return decrypt_py(t, e)
def getNewsDate(word="我和我的祖国"):
"""
:param word:
:return: 媒体指数的峰顶新闻
"""
insert_word = """[[{"name":"%s","wordType":1}]]""" % word
url = f"http://index.baidu.com/api/NewsApi/getNewsIndex?area=0&word={insert_word}&days=30"
res_json = get_rep_json(url)['data']
generalRatio = res_json["index"][0]['generalRatio']
e = res_json['index'][0]['data']
start_date = res_json['index'][0]['startDate']
t = getPtbk(res_json['uniqid'])
news = getTopNews(decrypt_py(t, e), start_date, word)
return news
def getTopNews(numList: list, start_date, word):
"""
找到当前指数列表中的峰值
转换成日期字符串
将合成的日期字符串带入到请求数据接口中
返回新闻数据
:param numList: 指数列表
:param start_date: 起始日期
:param word:
:return: 峰值新闻
"""
start_date = string_toDatetime(start_date)
hill_tops = getHilltop(numList)
hill_tops_date = [datetime_toString(start_date + datetime.timedelta(days=index)) for index in hill_tops]
news = getNews(",".join(hill_tops_date), word)["data"][word]
return news
def getNews(dts, word):
"""
获取媒体指数接口数据
:param dts:用,连接的时间字符串，例：dts=2019-10-06,2019-10-10,2019-10-12,2019-10-16,2019-10-21,2019-10-24
:param word:
:return:接口传回的数据
"""
url = f"http://index.baidu.com/api/NewsApi/checkNewsIndex?dates[]={dts}&type=day&words={word}"
return get_rep_json(url)
def getHilltop(numList: list):
"""
:param numList:一组数值数组
:return:峰值的序号列表
"""
numList = list(map(lambda x: float(x) if x else 0, numList))
hillTops = [index for index, each in enumerate(numList) if
index and index < len(numList) - 1 and each > numList[index - 1] and each > numList[index + 1]]
return hillTops
def getMulti(word="我和我的祖国"):
"""需求图谱
pv搜索热度；ratio搜索变化率；sim相关性
"""
url = f"http://index.baidu.com/api/WordGraph/multi?wordlist%5B%5D={word}"
word_data = get_rep_json(url)['data']['wordlist'][0]
if word_data['keyword']:
print(word_data['wordGraph'])
def getRegion(word="我和我的祖国", startDate='2019-09-17', endDate='2019-10-17'):
"""地域分布"""
url = f"http://index.baidu.com/api/SearchApi/region?region=0&word={word}&startDate={startDate}&endDate={endDate}"
region = get_rep_json(url)['data']['region'][0]
region_city = [{'city': city[int(city_n)], 'number': region['city'][city_n]} for city_n in region['city']]
region_prov = [{'prov': province[int(prov_n)], 'number': region['prov'][prov_n]} for prov_n in region['prov']]
print(region_city, region_prov)
def getBaseAttributes(word="我和我的祖国"):
"""人群属性"""
url = f"http://index.baidu.com/api/SocialApi/baseAttributes?wordlist[]={word}"
rep_data = get_rep_json(url)['data']['result']
return rep_data
def getInterest(word="我和我的祖国"):
"""兴趣分布"""
url = f"http://index.baidu.com/api/SocialApi/interest?wordlist[]={word}"
rep_data = rep_data = get_rep_json(url)['data']['result']
return rep_data
def string_toDatetime(string):
# 把字符串转成datetime
return datetime.datetime.strptime(string, "%Y-%m-%d")
def datetime_toString(dt):
# 把datetime转成字符串
return dt.strftime("%Y-%m-%d")
def getPtbk(uniqid):
url = f"http://index.baidu.com/Interface/ptbk?uniqid={uniqid}"
return get_rep_json(url)['data']
def decrypt_py(t, e):
"""
:param t:
:param e:
:return: 解析出来的数据
"""
a = dict()
length = int(len(t) / 2)
for o in range(length):
a[t[o]] = t[length + o]
r = "".join([a[each] for each in e]).split(",")
print(r)
return r
def get_rep_json(url):
"""
获取json
:param url: 请求接口
:return:
"""
hearder = {
"Cookie": '', # 请填写游览器中的cookie
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36"
}
response = requests.get(url, headers=hearder)
response_data = response.json()
# print(response_data)
return response_data
def main():
getFeedIndex()
getNewsDate()
getIndex()
getRegion()
getBaseAttributes()
getInterest()
if __name__ == "__main__":
main()还有主题的，接口找了一下，东西都一样，有兴趣可以自己搞一下
主题：
主题搜索指数：http://insight.baidu.com/base/search/trend/general?id=23734&dateType=30&filterType=1&source=0
&filterType=1&source=1#pc
&source=2#移动
主题资讯和主题视频
"http://index.baidu.com/Interface/Newwordgraph/getTopicFeed?nodeid=23935";"http://index.baidu.com/Interface/api/ptbkTopic?uniqid=5dad242a566a46.43359139";;;;"/api/videoIndex/getVideoIndex?nodeid=23935";"http://index.baidu.com/Interface/api/ptbkTopic?uniqid=5dad242a71d612.53363283"
品牌关注
http://insight.baidu.com/base/search/topic/attentionBrand?id=23734
搜索地域分布：http://insight.baidu.com/base/search/region/general?id=23734&dateType=30&filterType=1&pageSize=40
人群属性：
http://insight.baidu.com/base/search/Topic/baseAttributes?nodeid=23734
兴趣分布：
http://insight.baidu.com/base/search/Topic/interest?nodeid=23734&typeid=模拟登录完成旋转验证码
现在的我已经不是从前的我了，现在的我已经可以完成它了。
世界上没有爬不过去的山，如果有，那么可以站在巨人的肩膀上，再爬一次。
我来了我来了，我带着模型走来了，同学们你们是否还在为旋转验证码而苦恼，从现在开始你可以换个苦恼的问题了！！！
来来来，看成果
怎么样，是不是很快乐，因为这篇篇幅已经挺长不够我输出彩虹屁了，所以我写到另外一篇博客了
有什么不对的地方还是希望同学们能指出来！好嘞，快乐就完事了！