python100题目的爬取

标签：content   requests   ret   ext   .text   bs4   stat   list   exe   

import requests
from bs4 import BeautifulSoup

def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = ‘utf-8‘
        return r.text
    except:
        return ‘‘

def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, ‘html.parser‘)
    meta = soup.find_all(‘meta‘, attrs={‘name‘: ‘description‘})
    ulist.append(meta[0].attrs[‘content‘])


def main():
    start_url = ‘http://www.runoob.com/python/python-exercise-example‘
    uinfo = []
    for i in range(101):
        url = start_url + str(i) +‘.html‘
        try:
            html = getHTMLText(url)
            fillUnivList(uinfo, html)
        except:
            continue
    for i in range(101):
        try:
            with open(‘100.txt‘, ‘a‘) as f:
                f.write(uinfo[i] + ‘\n‘)
        except:
            continue

    print(uinfo)

main()

python100题目的爬取

标签：content   requests   ret   ext   .text   bs4   stat   list   exe   

原文地址：http://www.cnblogs.com/wskzwsj/p/7148303.html