diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index 408edfd..32da4bb 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -4,8 +4,8 @@
-
-
+
+
@@ -27,7 +27,7 @@
-
+
@@ -36,39 +36,44 @@
-
-
-
-
-
-
-
-
-
-
-
+
+
-
-
+
+
-
+
+
+
-
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -107,7 +112,6 @@
-
@@ -118,10 +122,11 @@
-
+
+
@@ -153,10 +158,21 @@
+
@@ -376,11 +392,14 @@
+
+
+
-
+
@@ -392,16 +411,15 @@
-
-
+
-
+
-
+
@@ -409,7 +427,7 @@
-
+
@@ -667,7 +685,7 @@
file://$PROJECT_DIR$/gopup/index/index_baidu.py
- 351
+ 342
@@ -695,11 +713,6 @@
418
-
- file://$PROJECT_DIR$/gopup/index/index_baidu.py
- 256
-
-
file://$PROJECT_DIR$/gopup/event/covid.py
212
@@ -785,6 +798,51 @@
34
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 261
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 262
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 264
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 265
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 266
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 267
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 268
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 295
+
+
+
+ file://$PROJECT_DIR$/gopup/index/index_baidu.py
+ 296
+
+
@@ -956,13 +1014,6 @@
-
-
-
-
-
-
-
@@ -994,40 +1045,52 @@
-
+
-
-
+
+
-
+
-
+
-
+
+
+
+
+
+
+
+
+
+
+
-
-
+
+
-
+
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
diff --git a/README.md b/README.md
index d9f7151..3d2de7b 100644
--- a/README.md
+++ b/README.md
@@ -98,6 +98,9 @@ print(df)
#### 版本更新
+ 0.2.9.1
+ 迭代百度指数解析问题
+
0.2.9
迭代头条指数改为算数指数，分为头条、抖音两套指数
diff --git a/gopup/index/index_baidu.py b/gopup/index/index_baidu.py
index 598f9b7..59a8d0b 100644
--- a/gopup/index/index_baidu.py
+++ b/gopup/index/index_baidu.py
@@ -4,8 +4,9 @@
# @Author : justin.郑 3907721@qq.com
# @File : index_baidu.py
# @Desc : 获取百度指数
-import json
+import json
+import urllib.parse
import pandas as pd
import requests
@@ -254,14 +255,11 @@ def baidu_search_index(word, start_date, end_date, cookie, type="all"):
"Referer": "http://index.baidu.com/v2/main/index.html",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36"
}
- params = {
- "area": 0,
- "word": '[[{"name":"%s","wordType":1}]]' % word,
- "startDate": start_date,
- "endDate": end_date
- }
- url = 'http://index.baidu.com/api/SearchApi/index'
- r = requests.get(url=url, params=params, headers=headers)
+ w = '{"name":"%s","wordType":1}' % word
+
+ url = 'http://index.baidu.com/api/SearchApi/index?area=0&word=[[%s]]&startDate=%s&endDate=%s' % (w, start_date, end_date)
+
+ r = requests.get(url=url, headers=headers)
data = r.json()["data"]
all_data = data["userIndexes"][0][type]["data"]
uniqid = data["uniqid"]
@@ -289,15 +287,12 @@ def baidu_info_index(word, start_date, end_date, cookie):
"Referer": "http://index.baidu.com/v2/main/index.html",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36"
}
- url = 'http://index.baidu.com/api/FeedSearchApi/getFeedIndex'
- params = {
- "area": 0,
- "word": '[[{"name":"%s","wordType":1}]]' % word,
- "startDate": start_date,
- "endDate": end_date
- }
+ w = '{"name":"%s","wordType":1}' % word
+
+ url = 'http://index.baidu.com/api/FeedSearchApi/getFeedIndex?area=0&word=[[%s]]&startDate=%s&endDate=%s' % (
+ w, start_date, end_date)
- r = requests.get(url=url, params=params, headers=headers)
+ r = requests.get(url=url, headers=headers)
data = r.json()["data"]
all_data = data["index"][0]["data"]
uniqid = data["uniqid"]
@@ -325,15 +320,11 @@ def baidu_media_index(word, start_date, end_date, cookie):
"Referer": "http://index.baidu.com/v2/main/index.html",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36"
}
- url = 'http://index.baidu.com/api/NewsApi/getNewsIndex'
- params = {
- "area": 0,
- "word": '[[{"name":"%s","wordType":1}]]' % word,
- "startDate": start_date,
- "endDate": end_date
- }
+ w = '{"name":"%s","wordType":1}' % word
+
+ url = 'http://index.baidu.com/api/NewsApi/getNewsIndex?area=0&word=[[%s]]&startDate=%s&endDate=%s' % (w, start_date, end_date)
- r = requests.get(url=url, params=params, headers=headers)
+ r = requests.get(url=url, headers=headers)
data = r.json()["data"]
all_data = data["index"][0]["data"]
@@ -351,9 +342,9 @@ def baidu_media_index(word, start_date, end_date, cookie):
if __name__ == "__main__":
- cookie = 'BIDUPSID=F7EB2ABF6DC23E3AE0D29AD77AC3A828; PSTM=1550065926; H_WISE_SIDS=135670_136721_137754_138181_138497_114745_128149_139148_120168_138471_138878_137978_137690_131246_132551_118883_118873_118847_118829_118790_138165_138883_136431_138845_138697_136862_138146_138114_139172_139592_136196_137105_139273_139398_139691_133847_137735_138343_137467_138564_134256_131423_139397_139090_139246_137782_138657_136537_110085_137441_127969_139161_138837_139287_139407_127417_137186_136635_138426_139733_138941_139677_139221_138779; bdshare_firstime=1580385892027; BAIDUID=BECC251AF81F5D6642279AA52D2B4069:FG=1; MCITY=-218%3A; BDUSS=NKRHNYcTVELWM4TFd4SGFUYng3ZkRsb3Q2RHRuRVBZRXc4TkVkWk96bUctY0ZmSVFBQUFBJCQAAAAAAAAAAAEAAABU8PMTst24-dauw~cAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIZsml-GbJpfOH; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=32818_1441_33043_33124_33061_31254_33098_33101_32961_31709; delPer=0; PSINO=7; BA_HECTOR=8h0h2h20200420a1s81frgsc10q; BCLID=7269067772028405350; BDSFRCVID=rP4OJexroG3SQbJrxh7TomSUCcpWxY5TDYLEaTkizKrm7S8VJeC6EG0Pts1-dEu-EHtdogKK0gOTH6KF_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF=tR30WJbHMTrDHJTg5DTjhPrMKR0JWMT-MTryKKORLRokq4ndjpOohqtALUbjLbvkJGnRhlRNKxbOjtcoK4Fb0TkZyxomtfQxtNRJQKDE5p5hKq5S5-OobUPUDMJ9LUkqW2cdot5yBbc8eIna5hjkbfJBQttjQn3hfIkj2CKLK-oj-DL4D5Da3e; Hm_lvt_d101ea4d2a5c67dab98251f0b5de24dc=1604039250,1605923360; bdindexid=cd952229an70atuimphot86qs7; Hm_lpvt_d101ea4d2a5c67dab98251f0b5de24dc=1605925273; __yjsv5_shitong=1.0_7_835dba6616d254eab5e9498efc28ecbfaa90_300_1605925103719_27.18.137.244_cf7a6d07; RT="z=1&dm=baidu.com&si=cz6d2xqlt1d&ss=khr1ayg5&sl=i&tt=je0&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&ld=152lb"'
- data = baidu_media_index(word="口罩", start_date='2020-11-01', end_date='2020-11-05', cookie=cookie)
- # data = baidu_atlas_index(word="口罩", cookie=cookie)
+ cookie = 'BIDUPSID=F7EB2ABF6DC23E3AE0D29AD77AC3A828; PSTM=1550065926; bdshare_firstime=1580385892027; BAIDUID=BECC251AF81F5D6642279AA52D2B4069:FG=1; BDUSS=NKRHNYcTVELWM4TFd4SGFUYng3ZkRsb3Q2RHRuRVBZRXc4TkVkWk96bUctY0ZmSVFBQUFBJCQAAAAAAAAAAAEAAABU8PMTst24-dauw~cAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAIZsml-GbJpfOH; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; MCITY=-%3A; bdindexid=1ml7ffmmi4e6qttriofivv8ee2; Hm_lvt_d101ea4d2a5c67dab98251f0b5de24dc=1608859085,1608867185; Hm_lpvt_d101ea4d2a5c67dab98251f0b5de24dc=1608867200; RT="sl=4&ss=kj3pzbnz&tt=41w&bcn=https%3A%2F%2Ffclog.baidu.com%2Flog%2Fweirwood%3Ftype%3Dperf&z=1&dm=baidu.com&si=7g4vsvbj94"; __yjsv5_shitong=1.0_7_835dba6616d254eab5e9498efc28ecbfaa90_300_1608866990636_221.232.19.129_73b13905'
+ # data = baidu_search_index(word="口罩", start_date='2020-12-01', end_date='2020-12-24', cookie=cookie)
+ data = baidu_interest_index(word="口罩", cookie=cookie)
print(data)
diff --git a/setup.py b/setup.py
index 6d5897d..498081d 100644
--- a/setup.py
+++ b/setup.py
@@ -10,7 +10,7 @@
URL = 'https://github.com/justinzm/gopup'
NAME = 'gopup'
-VERSION = '0.2.9'
+VERSION = '0.2.9.1'
DESCRIPTION = 'GoPUP database'
if os.path.exists('README.md'):
with open('README.md', encoding='utf-8') as f: