python爬虫慕课基础1
test_urllib2.py
import http.cookiejar from urllib import request url = "http://www.baidu.com" print('第一种方法') response1 = request.urlopen(url) print(response1.getcode()) print(len(response1.read())) print("第二种方法") req = request.Request(url) req.add_header("user-agent","Mozilla/5.0") response2 = request.urlopen(req) print(response2.getcode()) print(len(response2.read())) print('第三种方法') cj = http.cookiejar.CookieJar() opener = request.build_opener(request.HTTPCookieProcessor(cj)) request.install_opener(opener) response3 = request.urlopen(url) print(response3.getcode()) print(cj) print(response3.read())
test_bs4.py:
import re from bs4 import BeautifulSoup # 文档字符串 html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> <p class="title"><b>The Dormouse's story</b></p> <p class="story">Once upon a time there were three little sisters; and their names were <a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>, <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; and they lived at the bottom of a well.</p> <p class="story">...</p> """ soup = BeautifulSoup(html_doc, 'html.parser') # python3 缺省的编码是unicode, 再在from_encoding设置为utf8, 会被忽视掉, 故去掉，否则会报错 # 第一种方法 print('获取所有的链接') links = soup.find_all('a') for link in links: print(link.name, link['href'], link.get_text()) # 第二种方法 print('获取lacie的链接') link_node = soup.find('a', href='http://example.com/lacie') print(link_node.name, link_node['href'], link_node.get_text()) # 第三种方法 print('正则匹配') link_node = soup.find('a', href=re.compile(r'ill')) print(link_node.name, link_node['href'], link_node.get_text()) # 第四种方法 print('获取p段落文字') p_node = soup.find('p', class_='title') print(p_node.name, p_node.get_text())
