-
python连接测试URL
导入库
from requests import get
有关request库的函数
| 函数 | 说明 |
| get(url [, timeout=n]) | 对应HTTP的GET方式，设定请求超时时间为n秒 |
| post(url, data={'key':'value'}) | 对应HTTP的POST方式，字典用于传输客户数据 |
| delete(url) | 对应HTTP的DELETE方式 |
| head(url) | 对应HTTP的HEAD方式 |
| options(url) | 对应HTTP的OPTIONS方式 |
| put(url, data={'key':'value'}) | 对应HTTP的PUT方式，字典用于传输客户数据 |
设定url，，运用get函数请求页面
url = "https://hao.360.cn/" r = get(url, timeout=3) print("获得响应的状态码：", r.status_code) print("响应内容的编码方式：", r.encoding)
运行结果
获得响应的状态码： 200
响应内容的编码方式： ISO-8859-1
获取网页内容
r.encoding = "utf-8" url_text = r.text print("网页内容：", r.text) print("网页内容长度：", len(url_text))
运行结果
网页内容： <!DOCTYPE html> <!--STATUS OK--><html> <head> ... 意见反馈</a> 京ICP证030173号 <img src=//www.baidu.com/img/gs.gif> </p> </div> </div> </div> </body> </html>
网页内容长度： 2287
-
连接网站20次
在上面的基础上加上一个循环结构即可
""" Spyder Editor This is a temporary script file. """ import requests def getHTMLText(url): try: r=requests.get(url,timeout=30) r.raise_for_status() r.encoding='utf-8' return r.text except: return "F" url="https://www.google.com.hk/" print(getHTMLText(url)) for i in range(20): getHTMLText(url) print(i+1)
3.获取网页中的标签内容
选取一个网站用于演示
URL=https://www.baidu.com/
先获取网站内容
# -*- coding: utf-8 -*-
"""
Spyder Editor
"""
Spyder Editor
This is a temporary script file.
"""
"""
from requests import get def getText(url): try: r = get(url, timeout=5) r.raise_for_status() r.encoding = 'utf-8' return r.text except Exception as e: print("Error:", e) return ''
运用beautifulsoup库
from bs4 import BeautifulSoup
创建一个beautifulsoup对象
url = "https://www.baidu.com/" html = getText(url) soup = BeautifulSoup(html)
现在就可以来有选择的获取网站内容了
获取head
print("head:", soup.head) print("head:", len(soup.head))
获取title的标签和内容
print("title:", soup.title) print("title_string:", soup.title.string)
摘取所有的中文字符
import re def getChinese(text): text_unicode = text.strip() # 将字符串进行处理, 包括转化为unicode string = re.compile('[^u4e00-u9fff]') # 中文编码范围是 u4e00-u9ffff # 中文、数字编码范围是 u4e00-u9fa50 chinese = "".join(string.split(text_unicode)) return chinese
print("Chinese:", getChinese(html))
以上就是获取网站特定内容的方式了，我们也可以在其他网址使用。
4.爬取大学排名
# -*- coding: utf-8 -*- """ Spyder Editor zyp26 This is a temporary script file. """ import pandas import requests from bs4 import BeautifulSoup from requests import get# 获得网站数据 def getText(url): try: r = get(url, timeout=5) r.raise_for_status() r.encoding = 'utf-8' return r.text except Exception as e: print("Error:", e) return '' url=http://www.zuihaodaxue.com/zuihaodaxuepaiming2017.html# 选择2017年的大学排名 def fillTabelList(soup): # 获取表格的数据 tabel_list = [] # 存储整个表格数据 Tr = soup.find_all('tr') for tr in Tr: Td = tr.find_all('td') if len(Td) == 0: continue tr_list = [] # 存储一行的数据 for td in Td: tr_list.append(td.string) tabel_list.append(tr_list) return tabel_list # 可视化展示数据 def PrintTableList(tabel_list, num): # 输出前num行数据 print("{1:^2}{2:{0}^10}{3:{0}^5}{4:{0}^5}{5:{0}^8}".format(chr(12288), "排名", "学校名称", "省市", "总分", "生涯质量")) for i in range(num): text = tabel_list[i] print("{1:{0}^2}{2:{0}^10}{3:{0}^5}{4:{0}^8}{5:{0}^10}".format(chr(12288), *text)) #储存为csv格式 def saveAsCsv(filename, tabel_list): FormData = pandas.DataFrame(tabel_list) FormData.columns = ["排名", "学校名称", "省市", "总分", "生涯质量", "培养结果", "科研规模", "科研质量", "顶尖成果", "顶尖人才", "科研服务", "产学研合作", "成果转化"] FormData.to_csv(filename) if __name__ == "__main__": url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2017.html" html = getHTMLText(url) soup = BeautifulSoup(html, features="html.parser") data = fillTabelList(soup) PrintTableList(data, 10) # 输出前10行数据 saveAsCsv("D:\University_Rank.csv", data