（２）请用requests库的get()函数访问如下一个网站２０次，打印返回状态，text()内容，计算text()属性和content属性所返回网页内容的长度。（不同学号选做如下网页，必做及格）
import requests url = "https://www.baidu.com/" for i in range(20): response = requests.get(url) print("第{}次访问：".format(i + 1)) print("返回状态：", response.status_code) print("text()内容：", response.text) print("text()内容长度：", len(response.text)) print("content属性所返回网页内容长度：", len(response.content)) print("")
（３）这是一个简单的html页面,请保持为字符串，完成后面的计算要求。（良好）
from bs4 import BeautifulSoup html_doc = """ <!DOCTYPE html> <html> <head> <meta charset="utf-8"> <title>菜鸟教程(runoob.com)</title> </head> <body> <h1>我的第一个标题</h1> <p id="first">我的第一个段落。</p> </body> <table border="1"> <tr> <td>row 1, cell 1</td> <td>row 1, cell 2</td> </tr> <tr> <td>row 2, cell 1</td> <td>row 2, cell 2</td> </tr> </table> </html> """ print("学号:26") soup = BeautifulSoup(html_doc, 'html.parser') print("a:", soup.head) print("b:", soup.body) first_element = soup.find(id="first") print("c:", first_element) chinese_characters = "".join([char for char in html_doc if '\u4e00' <= char <= '\u9fff']) print("d:", chinese_characters)
(4) 爬中国大学排名网站内容，
https://www.shanghairanking.cn/rankings/bcur/201811
import requests from bs4 import BeautifulSoup import csv # 请求网页内容 url = "https://www.shanghairanking.cn/rankings/bcur/201611" response = requests.get(url) response.encoding = 'utf-8' html_content = response.text # 解析网页内容 soup = BeautifulSoup(html_content, 'html.parser') table = soup.find('table', {'class': 'rk-table'}) rows = table.find_all('tr')[1:] # 跳过表头 # 提取大学名称和序号 data = [] for row in rows: cols = row.find_all('td') university_name = cols[1].find('a', class_='name-cn').text.strip() university_rank = cols[0].text.strip() data.append([university_name, university_rank]) # 保存为csv文件 with open('university_ranking_2016.csv', 'w', newline='', encoding='utf-8') as csvfile: writer = csv.writer(csvfile) writer.writerow(['大学名称', '排序']) # 写入表头 writer.writerows(data) # 写入数据
