爬取徵信中國某公司詳情頁各項

2021-09-21 17:30:03 字數 2652 閱讀 1007

**如下：

import requests


from bs4 import beautifulsoup


import time


keyword = input('請輸入要查詢的公司名稱:')


# url = ''%(kewword)


headers = 


page = 1


while true:


try:


url = '' % (keyword,page)


response = requests.get(url=url,headers = headers)


# text = response.content.decode('utf-8')


text = response.json()


# print(text)


# with open('xinyong.html','w',encoding='utf-8') as fp:


#     fp.write(text)


data = text['data']['results']


# print(data)


if data:


for i in data:


headers = 


name = i['name']


encrystr = i['encrystr'].split('\n')[0]


# # 資訊概覽


link = ''+encrystr


response1 = requests.get(url =link,headers= headers)


text1 = response1.json()


# print(text1)


print('公司名稱:',text1['result']['entname'])


print('工商註冊號:',text1['result']['regno'])


print('法人資訊:',text1['result']['legalperson'])


print('成立日期:',text1['result']['esdate'])


print('企業型別:',text1['result']['enttype'])


print('登記機關:',text1['result']['regorg'])


with open('xinyong.txt','a',encoding='utf-8') as fp:


fp.write('公司名稱:'+text1['result']['entname']+'工商註冊號:'+text1['result']['regno']+'法人資訊:'+text1['result']['legalperson']+'成立日期:'+text1['result']['esdate']+'企業型別:'+text1['result']['enttype']+'登記機關:'+text1['result']['regorg']+'\n')


# # 行政許可


# link1 =''%(name)


# response2 = requests.get(url=link1,headers=headers)


# text2 = response2.json()


# print(text2)


# # print('行政許可:',text2['result']['results'])


# # 行政處罰


# link3 = ''%(name)


# response3 = requests.get(url=link3, headers=headers)


# text3 = response3.json()


# # print(text3)


# # print('行政處罰:',text3['result']['result'])


## # 守信紅名單


# link4 = ''%(encrystr)


# response4 = requests.get(url=link,headers =headers)


# text4 = response4.json()


# # print(text4)


# # print('守信紅名單',text4['result'])##


# # 重點關注名單


# link5 = ''%(encrystr)


# response5 = requests.get(url = link5,headers =headers)


# text5 = response5.json()


# # print(text5)


# # print('重點關注名單',text5['result'])


## # 黑名單


# link6 =''%(encrystr)


# response6 = requests.get(url=link6,headers=headers)


# text6 = response6.json()


# print(text6)


# print('黑名單',text6['result'])


# time.sleep(1)


page+=1


else:


print('沒有資料了')


break


except exception as e:


print('爬取失敗',e)

爬取中國天氣

import requests from bs4 import beautifulsoup def parser page url headers response requests.get url,headers headers text response.content.decode utf 8...

中國災害預警爬取解析

有獲取災害資訊提醒的需求，但是發現並沒有開發的api 已有的api都需要付錢。天氣預報api，可以看知乎的這邊文章。網上的天氣 api 哪乙個更加可靠？裡面的普通的天氣預報部分免費，但是災害預警的api都是需要收費的。於是自己去摸索了。最後通過發f12發現了中國天氣網中可用的請求 順便寫了下解析使用...

豆瓣影評爬取 中國機長

10月大火的中國機長相信大家都看過了吧 悄悄的說，我還有二刷?超級超級超級超級喜歡袁泉姐姐，溫柔又堅定，真誠又勇敢！import requests from bs4 import beautifulsoup import time import pandas as pd import os def ...