Python下载网页

颜色下载 财政部会计准则委员会 的网页

 

import requests
from bs4 import BeautifulSoup

requestsSession = requests.Session()  # if you’re making several requests to the same host, the underlying TCP connection will be reused, which can result in a significant performance increase


def downloadPage(url, encoding='utf8'):
    response = requestsSession.get(url)  # queryDict,如果文件不存在，那么就用0代表本地更新时间（一定下载文件）
    response.encoding = encoding
    if response.status_code == 200:  # 没有更新就是304
        soup = BeautifulSoup(response.text, "html.parser")
        print(soup.title)  # type(r.json())  r.url, r.headers r.status_code,  , r.history, r.text,lastChild
        with open(str(soup.title.text) + '.shtml', 'w', encoding=encoding) as file:
            file.write(response.text)


for pageNo in range(202776, 202819):
    print(pageNo)
    downloadPage("https://www.casc.org.cn/2018/0815/{}.shtml".format(pageNo))


for pageNo in range(202761, 202776):  #
    print(pageNo)
    downloadPage("https://www.casc.org.cn/2018/0814/{}.shtml".format(pageNo))