update 5.20 all data
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
|
||||
# 官方权威统计数据(持续更新:2022-5-18)
|
||||
# 官方权威统计数据(持续更新:2022-5-20)
|
||||
[数据下载 : shell & python](./data/data.md)
|
||||
```markdown
|
||||
收集整理的【官方权威】公开数据
|
||||
@@ -70,7 +70,7 @@
|
||||
|
||||
***
|
||||
## [6.中国信通院](http://www.caict.ac.cn/kxyj/) :+1::+1::+1:
|
||||
- 😄[白皮书:271 个](http://www.caict.ac.cn/kxyj/qwfb/bps) [(下载)](./data/data-caict-bps.md)
|
||||
- 😄[白皮书:273 个](http://www.caict.ac.cn/kxyj/qwfb/bps) [(镜像)](./data/data-caict-bps.md)
|
||||
|
||||
|名称(详情)|发布日期|下载(点击)|
|
||||
|:----|:----|:----|
|
||||
@@ -82,7 +82,7 @@
|
||||
|[**全球数字治理白皮书**](http://www.caict.ac.cn/kxyj/qwfb/bps/202112/t20211223_394423.htm)|2021-12-23|[全球数字治理白皮书.pdf](http://www.caict.ac.cn/kxyj/qwfb/bps/202112/P020211223383085909153.pdf)
|
||||
|
||||
|
||||
- 😄[专题报告:196 个](http://www.caict.ac.cn/kxyj/qwfb) [(下载)](./data/data-caict-ztbg.md)
|
||||
- 😄[专题报告:196 个](http://www.caict.ac.cn/kxyj/qwfb) [(镜像)](./data/data-caict-ztbg.md)
|
||||
|
||||
|名称(详情)|发布日期|下载(点击)|
|
||||
|:----|:----|:----|
|
||||
@@ -90,7 +90,7 @@
|
||||
|[中国第三方数据中心运营商分析报告(2022年)](http://www.caict.ac.cn/kxyj/qwfb/ztbg/202204/t20220408_399556.htm)|2022-04-08|[中国第三方数据中心运营商分析报告(2022年).pdf](http://www.caict.ac.cn/kxyj/qwfb/ztbg/202204/P020220408530633654580.pdf)
|
||||
|[全球云游戏产业深度观察及趋势研判研究报告(2022年)](http://www.caict.ac.cn/kxyj/qwfb/ztbg/202203/t20220317_398029.htm)|2022-03-17|[全球云游戏产业深度观察及趋势研判研究报告(2022年).pdf](http://www.caict.ac.cn/kxyj/qwfb/ztbg/202203/P020220317526747187627.pdf)
|
||||
|
||||
- 😄[权威数据:487 个](http://www.caict.ac.cn/kxyj/qwfb/qwsj/) [(下载)](./data/data-caict-qwsj.md)
|
||||
- 😄[权威数据:487 个](http://www.caict.ac.cn/kxyj/qwfb/qwsj/) [(镜像)](./data/data-caict-qwsj.md)
|
||||
|
||||
|名称(点击下载)|发布日期|
|
||||
|:----|:----|
|
||||
|
||||
131
code/caict-bg.py
Normal file
131
code/caict-bg.py
Normal file
@@ -0,0 +1,131 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding:utf-8 -*-
|
||||
# Author: yiliyas
|
||||
# Date: 2022.5.19
|
||||
|
||||
import re
|
||||
from urllib import request
|
||||
|
||||
|
||||
# 1.获取数据
|
||||
def get_html(url):
|
||||
# https 模拟浏览器头
|
||||
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36'}
|
||||
req = request.Request(url,headers=headers)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
response=request.urlopen(req)
|
||||
content=response.read().decode('utf-8')
|
||||
return content
|
||||
except:
|
||||
content='test2022!'
|
||||
pass
|
||||
|
||||
|
||||
# 2.处理数据(设置匹配条件)
|
||||
def get_url(content):
|
||||
# 根据地址不同,判断设置不同的匹配条件(第一层,文件标题)
|
||||
pattern = re.compile('<td.*?><span.*?>.*?<a href="(.*?)".*?>(.*?)</a>.*?</td>.*?<td.*?><span.*?>(.*?)</span></td>',re.S)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
def get_url2(content):
|
||||
# 根据地址不同,判断设置不同的匹配条件(第2层,文件下载地址)
|
||||
pattern = re.compile('<b>【全文下载】</b>.*?<a href="(.*?)".*?class=kxyj_text>(.*?)</a>',re.S)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# 3.显示数据
|
||||
def show_result(items):
|
||||
# 根据地址不同,判断设置不同的匹配条件
|
||||
# 计数器
|
||||
global tsum
|
||||
tsum = 0
|
||||
# 获取待下载文件的第一层地址:文件标题
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
for item in items:
|
||||
url = item[0]
|
||||
cname = item[1]
|
||||
cdate = item[2]
|
||||
url2 = 'http://www.caict.ac.cn/kxyj/qwfb/ztbg' + str(url).replace('./', '/')
|
||||
strs1 = '|[' + cname + '](' + url2 + ')' + '|' + cdate
|
||||
tsum = tsum + 1
|
||||
# print(strs1)
|
||||
# 获取待下载文件的第二层地址:文件下载地址
|
||||
html2 = get_html(url2)
|
||||
items2 = get_url2(html2)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
for item2 in items2:
|
||||
url3 = item2[0]
|
||||
url3 = str(url3)
|
||||
ss = url3[4:10]
|
||||
url3 = 'http://www.caict.ac.cn/kxyj/qwfb/ztbg/' + ss + str(url3).replace('./', '/')
|
||||
uname = item[1]
|
||||
# markdown格式文本
|
||||
strs2 = strs1 + '|[' + uname + '](' + url3 + ')'
|
||||
print(strs2)
|
||||
except:
|
||||
pass
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# 4.下载数据(写入文件)
|
||||
def get_file(url):
|
||||
file_name = url.split('/')[-1]
|
||||
# 设置下载路径(根据实际情况修改)
|
||||
file_names='E:/download/'+file_name
|
||||
req = request.Request(url)
|
||||
u = request.urlopen(req)
|
||||
f = open(file_names, 'wb')
|
||||
block_sz = 8192
|
||||
while True:
|
||||
buffer = u.read(block_sz)
|
||||
if not buffer:
|
||||
break
|
||||
f.write(buffer)
|
||||
f.close()
|
||||
print ("Sucessful to download" + " " + file_names)
|
||||
|
||||
|
||||
# 下载最新数据
|
||||
url = 'http://www.caict.ac.cn/kxyj/qwfb/ztbg/index.htm'
|
||||
html = get_html(url)
|
||||
items = get_url(html)
|
||||
show_result(items)
|
||||
|
||||
|
||||
# 下载历史数据
|
||||
tsum = 0 #计数器
|
||||
tsums = 0 #累加计数器
|
||||
# 获得总页数(手动调整)
|
||||
for i in range(1,12):
|
||||
url = 'http://www.caict.ac.cn/kxyj/qwfb/ztbg/index_'+str(i)+'.htm'
|
||||
# 获取信息
|
||||
html = get_html(url)
|
||||
# 获取下载地址
|
||||
items = get_url(html)
|
||||
# 下载显示数据
|
||||
show_result(items)
|
||||
# 计数器累加
|
||||
tsums = tsum + tsums
|
||||
psums = str(tsum)+'/'+str(tsums)
|
||||
print(psums)
|
||||
|
||||
|
||||
# 统计总数
|
||||
tsums = '总计: '+str(tsums)+' 个文件'
|
||||
print(tsums)
|
||||
|
||||
131
code/caict-bps.py
Normal file
131
code/caict-bps.py
Normal file
@@ -0,0 +1,131 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding:utf-8 -*-
|
||||
# Author: yiliyas
|
||||
# Date: 2022.5.19
|
||||
|
||||
import re
|
||||
from urllib import request
|
||||
|
||||
|
||||
# 1.获取数据
|
||||
def get_html(url):
|
||||
# https 模拟浏览器头
|
||||
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36'}
|
||||
req = request.Request(url,headers=headers)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
response=request.urlopen(req)
|
||||
content=response.read().decode('utf-8')
|
||||
return content
|
||||
except:
|
||||
content='test2022!'
|
||||
pass
|
||||
|
||||
|
||||
# 2.处理数据(设置匹配条件)
|
||||
def get_url(content):
|
||||
# 根据地址不同,判断设置不同的匹配条件(第一层,文件标题)
|
||||
pattern = re.compile('<td.*?><span.*?>.*?<a href="(.*?)".*?>(.*?)</a>.*?</td>.*?<td.*?><span.*?>(.*?)</span></td>',re.S)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
def get_url2(content):
|
||||
# 根据地址不同,判断设置不同的匹配条件(第2层,文件下载地址)
|
||||
pattern = re.compile('<b>【全文下载】</b>.*?<a href="(.*?)".*?class=kxyj_text>(.*?)</a>',re.S)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# 3.显示数据
|
||||
def show_result(items):
|
||||
# 根据地址不同,判断设置不同的匹配条件
|
||||
# 计数器
|
||||
global tsum
|
||||
tsum = 0
|
||||
# 获取待下载文件的第一层地址:文件标题
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
for item in items:
|
||||
url = item[0]
|
||||
cname = item[1]
|
||||
cdate = item[2]
|
||||
url2 = 'http://www.caict.ac.cn/kxyj/qwfb/bps' + str(url).replace('./', '/')
|
||||
strs1 = '|[' + cname + '](' + url2 + ')' + '|' + cdate
|
||||
tsum = tsum + 1
|
||||
# print(strs1)
|
||||
# 获取待下载文件的第二层地址:文件下载地址
|
||||
html2 = get_html(url2)
|
||||
items2 = get_url2(html2)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
for item2 in items2:
|
||||
url3 = item2[0]
|
||||
url3 = str(url3)
|
||||
ss = url3[4:10]
|
||||
url3 = 'http://www.caict.ac.cn/kxyj/qwfb/bps/' + ss + str(url3).replace('./', '/')
|
||||
uname = item[1]
|
||||
# markdown格式文本
|
||||
strs2 = strs1 + '|[' + uname + '](' + url3 + ')'
|
||||
print(strs2)
|
||||
except:
|
||||
pass
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# 4.下载数据(写入文件)
|
||||
def get_file(url):
|
||||
file_name = url.split('/')[-1]
|
||||
# 设置下载路径(根据实际情况修改)
|
||||
file_names='E:/download/'+file_name
|
||||
req = request.Request(url)
|
||||
u = request.urlopen(req)
|
||||
f = open(file_names, 'wb')
|
||||
block_sz = 8192
|
||||
while True:
|
||||
buffer = u.read(block_sz)
|
||||
if not buffer:
|
||||
break
|
||||
f.write(buffer)
|
||||
f.close()
|
||||
print ("Sucessful to download" + " " + file_names)
|
||||
|
||||
|
||||
# 下载最新数据
|
||||
url = 'http://www.caict.ac.cn/kxyj/qwfb/bps/index.htm'
|
||||
html = get_html(url)
|
||||
items = get_url(html)
|
||||
show_result(items)
|
||||
|
||||
|
||||
# 下载历史数据
|
||||
tsum = 0 #计数器
|
||||
tsums = 0 #累加计数器
|
||||
# 获得总页数(手动调整)
|
||||
for i in range(1,16):
|
||||
url = 'http://www.caict.ac.cn/kxyj/qwfb/bps/index_'+str(i)+'.htm'
|
||||
# 获取信息
|
||||
html = get_html(url)
|
||||
# 获取下载地址
|
||||
items = get_url(html)
|
||||
# 下载显示数据
|
||||
show_result(items)
|
||||
# 计数器累加
|
||||
tsums = tsum + tsums
|
||||
psums = str(tsum)+'/'+str(tsums)
|
||||
print(psums)
|
||||
|
||||
|
||||
# 统计总数
|
||||
tsums = '总计: '+str(tsums)+' 个文件'
|
||||
print(tsums)
|
||||
|
||||
99
code/caict-qwsj.py
Normal file
99
code/caict-qwsj.py
Normal file
@@ -0,0 +1,99 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding:utf-8 -*-
|
||||
# Author: yiliyas
|
||||
# Date: 2022.5.19
|
||||
|
||||
import re
|
||||
from urllib import request
|
||||
|
||||
|
||||
# 1.获取数据
|
||||
def get_html(url):
|
||||
# https 模拟浏览器头
|
||||
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36'}
|
||||
req = request.Request(url,headers=headers)
|
||||
response=request.urlopen(req)
|
||||
# 根据实际地址修改字符集
|
||||
content=response.read().decode('utf-8')
|
||||
return content
|
||||
|
||||
|
||||
# 2.处理数据(设置匹配条件)
|
||||
def get_url(content):
|
||||
# 根据地址不同,判断设置不同的匹配条件
|
||||
pattern = re.compile('<td.*?><span.*?>.*?<a href=\'(.*?)\'.*?>(.*?)</a>.*?</td>.*?<td.*?><span.*?>(.*?)</span></td>',re.S)
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
|
||||
|
||||
# 3.显示数据
|
||||
def show_result(items):
|
||||
# 根据地址不同,判断设置不同的匹配条件
|
||||
# 计数器
|
||||
global tsum
|
||||
tsum = 0
|
||||
for item in items:
|
||||
url = item[0]
|
||||
cname = item[1]
|
||||
cdate = item[2]
|
||||
url2 = 'http://www.caict.ac.cn/kxyj/qwfb/qwsj' + str(url).replace('./', '/')
|
||||
strs1 = cdate+'|'+cname +'|'+ url2
|
||||
# 替换多余字符
|
||||
strs1 = strs1.replace('- ','')
|
||||
# 替换换行符(合并为1行)
|
||||
strs1=strs1.replace('\n','')
|
||||
# 计数器加1
|
||||
tsum = tsum+1
|
||||
print(strs1)
|
||||
# 下载文件
|
||||
get_file(url2)
|
||||
|
||||
|
||||
# 4.下载数据(写入文件)
|
||||
def get_file(url):
|
||||
file_name = url.split('/')[-1]
|
||||
# 设置下载路径(根据实际情况修改)
|
||||
file_names='E:/download/'+file_name
|
||||
req = request.Request(url)
|
||||
u = request.urlopen(req)
|
||||
f = open(file_names, 'wb')
|
||||
block_sz = 8192
|
||||
while True:
|
||||
buffer = u.read(block_sz)
|
||||
if not buffer:
|
||||
break
|
||||
f.write(buffer)
|
||||
f.close()
|
||||
print ("Sucessful to download" + " " + file_names)
|
||||
|
||||
|
||||
|
||||
# 下载最新数据
|
||||
url = 'http://www.caict.ac.cn/kxyj/qwfb/qwsj/index.htm'
|
||||
html = get_html(url)
|
||||
items = get_url(html)
|
||||
show_result(items)
|
||||
|
||||
|
||||
# 下载历史数据
|
||||
tsum = 0 #计数器
|
||||
tsums = 0 #累加计数器
|
||||
for i in range(1,28):
|
||||
url = 'http://www.caict.ac.cn/kxyj/qwfb/qwsj/index_'+str(i)+'.htm'
|
||||
# 获取信息
|
||||
html = get_html(url)
|
||||
# 获取下载地址
|
||||
items = get_url(html)
|
||||
# 下载显示数据
|
||||
show_result(items)
|
||||
# 计数器累加
|
||||
tsums = tsum + tsums
|
||||
psums = str(tsum)+'/'+str(tsums)
|
||||
print(psums)
|
||||
|
||||
|
||||
tsums = '总计: '+str(tsums)+' 个文件'
|
||||
print(tsums)
|
||||
|
||||
|
||||
|
||||
137
code/t500.py
Normal file
137
code/t500.py
Normal file
@@ -0,0 +1,137 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding:utf-8 -*-
|
||||
# Author: yiliyas
|
||||
# Date: 2022.5.19
|
||||
|
||||
import re
|
||||
from urllib import request
|
||||
|
||||
|
||||
# 1.获取数据
|
||||
def get_html(url):
|
||||
# https 模拟浏览器头
|
||||
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36'}
|
||||
req = request.Request(url,headers=headers)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
response=request.urlopen(req)
|
||||
# 设置编码
|
||||
content=response.read().decode('utf-8-sig')
|
||||
return content
|
||||
except:
|
||||
content='test2022!'
|
||||
pass
|
||||
|
||||
|
||||
# 2.处理数据(设置匹配条件)
|
||||
def get_url(content):
|
||||
# 根据地址不同,判断设置不同的匹配条件(第一层,文件标题)
|
||||
pattern = re.compile('<div class="swiper-slide">.*?<a href="(.*?)" data-year=".*?">(.*?)</a>.*?</div>',re.S)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
def get_url2(content,ctype,iyear):
|
||||
# 根据地址不同,判断设置不同的匹配条件(第2层,文件下载地址)
|
||||
# 不同年度数据格式有差异,匹配规则不同
|
||||
#pattern = re.compile('<tr>\n<td>(.*?)</td>\n<td><a.*?>(.*?)</a></td>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td.*?><span>.*?</span></td></tr>',re.S)
|
||||
cyear = str(iyear)
|
||||
# 英文年度榜
|
||||
# 5列
|
||||
if ctype=='en' and cyear in(2020,2021):
|
||||
pattern=re.compile('<tr>\n<td>(.*?)</td>\n<td><a.*?>(.*?)</a></td>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td.*?><span>.*?</span></td></tr>',re.S)
|
||||
# 6列
|
||||
if ctype=='en' and cyear in(2015,2018,2019):
|
||||
pattern = re.compile('<tr>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td><a.*?>(.*?)</a>.*?</td>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td>(.*?)</td></tr>',re.S)
|
||||
# 6列
|
||||
if ctype=='en' and cyear in(2014,2016,2017):
|
||||
pattern = re.compile('<tr><td>(.*?)</td><td>(.*?)</td><td><a.*?>(.*?)</a>.*?</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td></tr>',re.S)
|
||||
# 6列
|
||||
if ctype=='en' and cyear == 2013:
|
||||
pattern = re.compile('<tr>\n.*?<td>(.*?)</td>\n.*?<td>(.*?)</td>\n.*?<td><a.*?>(.*?)</a>.*?</td>\n.*?<td>(.*?)</td>\n.*?<td>(.*?)</td>\n.*?<td>(.*?)</td>\n.*?</tr>',re.S)
|
||||
# 6列
|
||||
if ctype=='en' and cyear == 2012:
|
||||
pattern = re.compile('<tr><td.*?>(.*?)</td><td.*?>(.*?)</td><td.*?><a.*?>(.*?)</a>.*?</td><td.*?>(.*?)</td><td.*?>(.*?)</td><td.*?>(.*?)</td></tr>',re.S)
|
||||
# 6列
|
||||
if ctype=='en' and cyear==2011:
|
||||
pattern = re.compile('<tr>\n<td.*?>(.*?)</td>\n<td.*?>(.*?)</td>\n<td.*?><a.*?>(.*?)</a></td>\n<td.*?>(.*?)</td>\n<td.*?>(.*?)</td>\n<td.*?>(.*?)</td></tr>',re.S)
|
||||
# 5列
|
||||
if ctype=='en' and cyear==2010:
|
||||
pattern = re.compile('<tr>\n<td>(.*?)</td>\n<td>(.*?)</td>\n<td><a.*?>(.*?)</a></td>\n<td>(.*?)</td>\n<td>(.*?)</td></tr>',re.S)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
items = re.findall(pattern,content)
|
||||
return items
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# 3.显示数据
|
||||
def show_result(items):
|
||||
# 根据地址不同,判断设置不同的匹配条件
|
||||
# 计数器
|
||||
global tsum
|
||||
tsum = 0
|
||||
# 获取待下载数据列表
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
for item in items:
|
||||
url=item[0]
|
||||
uname=item[1]
|
||||
strs=uname+'|'+url
|
||||
print(strs)
|
||||
# 获取载数据:文件下载地址(不同年度数据格式有差异,匹配规则不同)
|
||||
ctype = 'en'
|
||||
iyear = int(uname)
|
||||
html2 = get_html(url)
|
||||
items2 = get_url2(html2,ctype,iyear)
|
||||
# 处理异常,忽略错误,继续执行
|
||||
try:
|
||||
for item2 in items2:
|
||||
c1=item2[0]
|
||||
c2=item2[1]
|
||||
c3=item2[2]
|
||||
c4=item2[3]
|
||||
c5=item2[4]
|
||||
# markdown 表格格式
|
||||
# if ctype=='cn':
|
||||
cstr='|'+c1+'|'+c2+'|'+c3+'|'+c4+'|'+c5
|
||||
print(cstr)
|
||||
except:
|
||||
pass
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# 4.下载数据(写入文件)
|
||||
def get_file(url):
|
||||
file_name = url.split('/')[-1]
|
||||
# 设置下载路径(根据实际情况修改)
|
||||
file_names='E:/download/'+file_name
|
||||
req = request.Request(url)
|
||||
u = request.urlopen(req)
|
||||
f = open(file_names, 'wb')
|
||||
block_sz = 8192
|
||||
while True:
|
||||
buffer = u.read(block_sz)
|
||||
if not buffer:
|
||||
break
|
||||
f.write(buffer)
|
||||
f.close()
|
||||
print ("Sucessful to download" + " " + file_names)
|
||||
|
||||
|
||||
# 下载最新数据
|
||||
# 《财富》世界500强排行榜
|
||||
url = 'https://www.fortunechina.com/fortune500/index.htm'
|
||||
# 《财富》中国500强排行榜
|
||||
#url = 'https://www.fortunechina.com/fortune500/node_4302.htm'
|
||||
|
||||
html = get_html(url)
|
||||
items = get_url(html)
|
||||
show_result(items)
|
||||
|
||||
@@ -1,10 +1,12 @@
|
||||
- [**返回**](../README.md) | [**下载**](./data.md)
|
||||
|
||||
## [中国信通院](http://www.caict.ac.cn/kxyj/) :+1::+1::+1:
|
||||
- [白皮书:271 个](http://www.caict.ac.cn/kxyj/qwfb/bps/)
|
||||
- [白皮书:273 个](http://www.caict.ac.cn/kxyj/qwfb/bps/)
|
||||
|
||||
|名称(详情)|发布日期|下载(点击)|
|
||||
|:----|:----|:----|
|
||||
|[信息无障碍白皮书(2022年)](http://www.caict.ac.cn/kxyj/qwfb/bps/202205/t20220518_401483.htm)|2022-05-18|[信息无障碍白皮书(2022年)](http://www.caict.ac.cn/kxyj/qwfb/bps/202205/P020220518510041281463.pdf)
|
||||
|[信息通信业营商环境发展报告(2022年)](http://www.caict.ac.cn/kxyj/qwfb/bps/202205/t20220517_401445.htm)|2022-05-17|[信息通信业营商环境发展报告(2022年)](http://www.caict.ac.cn/kxyj/qwfb/bps/202205/P020220517553182355269.pdf)
|
||||
|[**数据中心白皮书(2022年)**](http://www.caict.ac.cn/kxyj/qwfb/bps/202204/t20220422_400391.htm)|2022-04-22|[数据中心白皮书(2022年).pdf](http://www.caict.ac.cn/kxyj/qwfb/bps/202204/P020220422707354529853.pdf)
|
||||
|[**人工智能白皮书(2022年**)](http://www.caict.ac.cn/kxyj/qwfb/bps/202204/t20220412_399752.htm)|2022-04-12|[人工智能白皮书(2022年).pdf](http://www.caict.ac.cn/kxyj/qwfb/bps/202204/P020220412613255124271.pdf)
|
||||
|[数字建筑发展白皮书(2022年)](http://www.caict.ac.cn/kxyj/qwfb/bps/202203/t20220330_398996.htm)|2022-03-30|[数字建筑发展白皮书(2022年).pdf](http://www.caict.ac.cn/kxyj/qwfb/bps/202203/P020220330512284345397.pdf)
|
||||
|
||||
@@ -1,10 +1,15 @@
|
||||
- [**返回**](../README.md) | [**下载**](./data.md)
|
||||
|
||||
## [中国信通院](http://www.caict.ac.cn/kxyj/) :+1::+1::+1:
|
||||
- [权威数据:485 个](http://www.caict.ac.cn/kxyj/qwfb/qwsj/)
|
||||
- [权威数据:490 个](http://www.caict.ac.cn/kxyj/qwfb/qwsj/)
|
||||
|
||||
|名称(点击下载)|发布日期|
|
||||
|:----|:----|
|
||||
|[2022年3月国内手机市场运行分析报告(英文版)](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202205/P020220516573130476905.pdf)|2022-05-16
|
||||
|[2022年3月国内手机市场运行分析报告(中文版)](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202205/P020220516626693122213.pdf)|2022-05-16
|
||||
|[国内增值电信业务许可情况报告(2022.4)](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202205/P020220516441534931186.pdf)|2022-05-16
|
||||
|[2022年一季度我国互联网上市企业运行情况](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202205/P020220512490343897406.pdf)|2022-05-12
|
||||
|[2022年第一季度5G云测平台监测报告](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202205/P020220505407978078250.pdf)|2022-05-05
|
||||
|[信息无障碍动态(2022年第4期)](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202204/P020220429558681182263.pdf)|2022-04-29
|
||||
|[2022年一季度钢铁行业运行数据报告](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202204/P020220429554100941624.pdf)|2022-04-29
|
||||
|[2022年一季度医药行业运行数据报告](http://www.caict.ac.cn/kxyj/qwfb/qwsj/202204/P020220429540151096778.pdf)|2022-04-29
|
||||
|
||||
@@ -56,12 +56,12 @@
|
||||
|互联网|[2021年1-11月份互联网和相关服务业运行情况](https://www.miit.gov.cn/gxsj/tjfx/hlw/art/2021/art_c11f934d11e0405cbb5777fd57a7517f.html)|12-30
|
||||
|互联网|[2021年1-10月份互联网和相关服务业运行情况](https://www.miit.gov.cn/gxsj/tjfx/hlw/art/2021/art_746966fb05bf429cb40924dac8971ff0.html)|12-01
|
||||
|互联网|[2020年互联网和相关服务业年度统计数据](https://www.miit.gov.cnhttps://www.miit.gov.cn/hlwnj/hlw.html)|11-09
|
||||
|网络安全|[5月9日-5月15日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_eab8b28c504e4a12a18997eb1067b18b.html)|05-18
|
||||
|网络安全|[5月2日-5月8日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_654d1ba90cce43748a3a636ded32d568.html)|05-12
|
||||
|网络安全|[4月25日-5月1日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_85c63a64ac4b4064b25c7afae7f0f5a4.html)|04-29
|
||||
|网络安全|[4月18日-4月24日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_8faf9bd9e4f946acba45d6243adcd25e.html)|04-26
|
||||
|网络安全|[4月11日-4月17日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_42754bc87e8e403da54717d9ed28a849.html)|04-20
|
||||
|网络安全|[4月4日-4月10日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_15498ca01c4c4f93a0f991d26474e4a7.html)|04-13
|
||||
|网络安全|[3月28日-4月3日网络安全信息与动态周报](https://www.miit.gov.cn/gxsj/tjfx/wlaq/art/2022/art_f5a7fa4b0d7041fda437f6990c2efdbc.html)|04-07
|
||||
|
||||
### [原材料工业](https://www.miit.gov.cn/gxsj/tjfx/yclgy/index.html) —— 钢铁 有色 石化化工 建材 稀土
|
||||
|
||||
|
||||
10
data/data.md
10
data/data.md
@@ -1,4 +1,4 @@
|
||||
# 官方权威统计数据(更新日期:2022-5-18)
|
||||
# 官方权威统计数据(更新日期:2022-5-20)
|
||||
|
||||
|数据名称|本地镜像|shell下载|python下载|说明|
|
||||
|:----|:----|:----|:----|:----|
|
||||
@@ -7,10 +7,10 @@
|
||||
|[3.工信数据(工业和信息化部)](https://www.miit.gov.cn/gxsj/index.html) |[镜像](./data-miit.md)| |[python](../code/miit.py)|八大行业:原材料工业,装备工业,消费品工业,通信业,电子信息制造业,软件业,互联网,网络安全|
|
||||
|[4.中国互联网络发展状况统计报告](http://www.cnnic.net.cn/hlwfzyj/hlwxzbg/index.htm)|[镜像](./data-internet.md)|[shell](../code/internet.md)|[python](../code/internet.py)|1998-2022年,24年官方权威数据
|
||||
|[5.中国政府网](http://www.gov.cn/shuju/index.htm)|[镜像](./data-gov.md)| | |GDP、CPI、PPI |
|
||||
|[6.中国信通院](http://www.caict.ac.cn/kxyj/) |[镜像](./data-caict-bps.md)|[shell](../code/test.md)|[python](../code/test.py)||
|
||||
|😄[白皮书:271 个](http://www.caict.ac.cn/kxyj/qwfb/bps)|[镜像](./data-caict-bps.md)| |[python](../code/test.py)|权威发布:ICT行业白皮书|
|
||||
|😄[专题报告:196 个](http://www.caict.ac.cn/kxyj/qwfb)|[镜像](./data-caict-ztbg.md)| |[python](../code/test.py)|权威发布:ICT行业专题报告|
|
||||
|😄[权威数据:487 个](http://www.caict.ac.cn/kxyj/qwfb/qwsj/)|[镜像](./data-caict-qwsj.md)| |[python](../code/test.py)|权威发布:ICT行业权威数据|
|
||||
|[6.中国信通院](http://www.caict.ac.cn/kxyj/) |[镜像](./data-caict-bps.md)| | |ICT行业数据 |
|
||||
|😄[白皮书:273 个](http://www.caict.ac.cn/kxyj/qwfb/bps)|[镜像](./data-caict-bps.md)| |[python](../code/caict-bps.py)|权威发布:ICT行业白皮书|
|
||||
|😄[专题报告:196 个](http://www.caict.ac.cn/kxyj/qwfb)|[镜像](./data-caict-ztbg.md)| |[python](../code/caict-bg.py)|权威发布:ICT行业专题报告|
|
||||
|😄[权威数据:490 个](http://www.caict.ac.cn/kxyj/qwfb/qwsj/)|[镜像](./data-caict-qwsj.md)| |[python](../code/caict-qwsj.py)|权威发布:ICT行业权威数据|
|
||||
|[7.财富FORTUNE 500强](https://www.fortunechina.com/rankings/node_11663.htm)|[镜像](../top/t500.md)|[shell](../code/test.md)|[python](../code/test.py)|世界500强,中国500强|
|
||||
|8.上海数据|[镜像](./data-sh.md)| | |统计公报,统计年签,社会民生数据|
|
||||
|[上海统计公报](http://tjj.sh.gov.cn/tjgb/index.html)|[镜像](./data-sh.md)|[shell](../code/test.md)|[python](../code/test.py)|2002-2021年,20年官方权威数据|
|
||||
|
||||
Reference in New Issue
Block a user