我的博客

from urllib.request import urlopenfrom urllib.error import HTTPErrorfrom urllib.error import URLErrorfrom bs4 import BeautifulSoupdef getHTML(url): try: html = urlopen(url) exc

findAll(tag, attributes, recursive, text, limit, keywords)find(tag, attributes, recursive, text, keywords)标签参数tag ：传一个标签的名称或多个标签名称组成的 Python 列表做标签参数属性参数attributes 是用一个 Python 字典封装一个标签的若干属性和对应的属性

http://blog.youkuaiyun.com/drdairen/article/details/51134816

from urllib.request import urlopenfrom urllib.error import HTTPErrorfrom urllib.error import URLErrorfrom bs4 import BeautifulSoupimport urllib.requestimport reimport osdef get_html(url):

def get_html(url): try: html = urlopen(url) except HTTPError as e: print(e) return None except URLError as e: print(e) return None try:

from urllib.request import urlopenfrom urllib.request import urlretrievefrom bs4 import BeautifulSoupimport requestsimport reimport osurl = "http://www.qiushibaike.com/imgrank/"path = "D:/2/"

import requestsfrom http.cookiejar import CookieJarfrom bs4 import BeautifulSoupurlBefore = "http://cas.swust.edu.cn/authserver/login"def getResopnseAfterLogin(): head ={ "User-Agent":"M

import reimport requestsfrom bs4 import BeautifulSoupurl = "http://passport.youkuaiyun.com/account/login"def Login(): head={ "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36