Python爬虫入门（五）股票案例

一、股票案例

import requests
from bs4 import BeautifulSoup
import traceback
import re


def get_html_text(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""


def ge_stock_list(lst, stockURL):
    html = get_html_text(stockURL)
    soup = BeautifulSoup(html, 'html.parser')
    a = soup.find_all('a')
    for i in a:
        try:
            href = i.attrs['href']
            lst.append(re.findall(r"[s][hz]\d{6}", href)[0])
        except:
            continue


def ge_stock_info(lst, stockURL, fpath):
    for stock in lst:
        url = stockURL + stock + ".html"
        html = get_html_text(url)
        try:
            if html == "":
                continue
            infoDict = {