goodinfo

import requests

from bs4 import BeautifulSoup

import pandas

# GoodInfo損益表--累計季表

url = "https://goodinfo.tw/StockInfo/StockFinDetail.asp"

url_paras = {'RPT_CAT': 'IS_M_QUAR_ACC', 'STOCK_ID': '2330'}

url_headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'}

r = requests.get(url, params=url_paras, headers=url_headers)

r.encoding = "utf-8"

root = BeautifulSoup(r.text, "lxml")

#print(root.title.string)

for head in root.select('.solid_1_padding_4_4_tbl'):

df = pd.read_html(str(head.parent.parent.parent.parent), encoding = "UTF-8")

print(df[4])

df[4].to_csv('123.csv', encoding='utf_8_sig')

import requests

from bs4 import BeautifulSoup

import pandas

# GoodInfo損益表--累計季表

url = "https://goodinfo.tw/StockInfo/StockList.asp"

url_paras = {'INDUSTRY_CAT': '公司總市值最高@@公司總市值@@公司總市值最高', 'MARKET_CAT': '熱門排行', 'SHEET': '公司基本資料' }

#INDUSTRY_CAT: 公司總市值最高@@公司總市值@@公司總市值最高

#MARKET_CAT: 熱門排行

#SHEET: 公司基本資料

url_headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36'}

r = requests.get(url, params=url_paras, headers=url_headers)

r.encoding = "utf-8"

for head in root.select('.solid_1_padding_4_1_tbl'):

df = pd.read_html(str(head.parent.parent.parent.parent), encoding = "UTF-8")

print(df[4])

df[4].to_csv('345.csv', encoding='utf_8_sig')