import requests
from lxml import etree
from bs4 import BeautifulSoup
import time
import pandas as pd
import json
hd = {
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36",
"Accept": "application/json",
"Cache-Control": "no-cache"
}
link="https://www.dtc.capital/portfolio"
resp = requests.get(link,headers=hd)
total = []
print(resp.status_code)
html = BeautifulSoup(resp.text, "lxml")
#print(html)
total = []
temp = html.find_all("div", class_="_1vNJf")
print(len(temp))
#print(temp[0:2])
for i in temp:
try:
name1 = i.find("span", style="text-decoration:underline").text.strip()
link = i.find("a",)['href'].strip()
total.append([name1, link])
except Exception as e:
pass
try:
name2 = i.find("span", style="text-decoration:underline;").text.strip()
link = i.find("a",)['href'].strip()
total.append([name2, link])
except Exception as e:
pass
ns = pd.DataFrame(total)
date = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
path = "/Users/paul/jpn traffic/ana/dtc/"
ns.to_csv(path + date + '.csv', index=None)
print("dtc finished")
quit()
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='www.dtc.capital', port=443): Max retries exceeded with url: /portfolio (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:1129)')))
During handling of the above exception, another exception occurred:
requests.exceptions.SSLError: HTTPSConnectionPool(host='www.dtc.capital', port=443): Max retries exceeded with url: /portfolio (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:1129)')))