真正完全独立没参考任何代码没进行任何搜索的第一个爬虫,网站无robots.txt:
import requests
import time
import re
from bs4 import BeautifulSoup
from random import random
# get the whole information of html page from the index page.
def get_html_text(url, code='utf-8'):
kv = {'User-Agent': 'Mozilla/5.0'}
try:
res = requests.get(url, timeout=60, headers=kv)
res.raise_for_status()
res.encoding = code
return res.text
except BaseException:
return ''
# get the excel file and store from the detailed page.
def get_excel_store(url, filepath='d:/'):
try:
time.sleep(random())
r = get_html_text(url)
soup = BeautifulSoup(r, 'html.parser')
# span is a special tag in this resource page with a style5 property
span = soup.find_all('span', attrs={'class': 'STYL