SimonChen

import rematch = re.search(r'[1-9]\d{5}', 'BIT 100081')if match: print(match.group(0))

from bs4 import BeautifulSoupimport requestsr = requests.get("http://www.baidu.com")demo = r.textsoup = BeautifulSoup(demo,"html.parser")print(soup.prettify())

# 加载requests库import requests# 加载正则表达式模块import re# 爬取网页内容模块def get_html_text(url): # 获取要访问的网址 try: r = requests.get(url, timeout=30) # 把爬取后的内容赋给r，等待时间对多30秒 r.raise_for_stat...

import requeststry: kv = {'q':'Python'}#关键词键值对，要搜索Python r = requests.get("http://www.so.com/s",params=kv) print(r.status_code) print(r.request.url) r.raise_for_status() print...

import requestsfrom bs4 import BeautifulSoupimport tracebackimport redef getHTMLText(url):try:r = requests.get(url)r.raise_for_status()r.encoding = r.apparent_encodingreturn r.textexcept:re...