Python request+BeautifulSoup爬取云南省统计局xls文件

之前写了一个，但是效率较低，为了温习及加强爬虫基础，又重写了一遍，同时换成lxml解析器。另外，学习了PEP8，发现跟之前自己习惯居然差不多，偷笑~~~

 

import requests
import re
from bs4 import BeautifulSoup


def get_text(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.62 Safari/537.36'}
    try:
        r = requests.get(url, headers=headers)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except BaseException:
        return ''


def url_list(html):
    soup = BeautifulSoup(html, 'html.parser')
    q = r'/\d{6}/t\d{8}_\d{6}.html'
    urls = re.findall(q, str(soup))
    url_ls = ['http://www.stats.yn.gov.cn/tjsj/jdsj' + url for url in urls]
    return url_ls


def get_excel(url):
    try:
        r = get_text(url)
        so