抓取糗事百科內容及評論，不包含圖片信息。user-agent填入瀏覽器的即可。user-agent對應的value，360極速瀏覽器的話，可以在地址欄輸入about:version，回車，用戶代理後面的一長串就是需要填入‘‘裏面的內容。其他的可以自行百度

import urllib.request
import re
from urllib import request
from bs4 import BeautifulSoup

#1.獲取網頁源代碼
def get_html(url):
    headers = {
        ‘User-Agent‘: ‘‘,
    }
    req 
 
= request.Request(headers=headers,url=url)
    response = urllib.request.urlopen(req)
    content = response.read().decode(‘utf-8‘)
    return content

#獲取評論鏈接
def get_comment_link(content,comment_url_base):
    soup = BeautifulSoup(content,‘html.parser‘)
    articleFloor = 1
    for string in soup.find_all(attrs=re.compile(r"
 
article block untagged mb15.*?")):
        comment = str(string.get(‘id‘)).strip().split("_")[2]
        comment_url = comment_url_base % comment#評論鏈接
        get_comment_content(comment_url,articleFloor)#獲取評論內容
        articleFloor += 1

#獲取糗事內容及評論內容
def get_comment_content(comment_url,articleFloor):
    commentPage 
 
= get_html(comment_url)
    commentFloor = 1
    soupComment = BeautifulSoup(commentPage,‘html.parser‘)
    for item in soupComment.find_all(‘div‘,class_=‘content‘):
        print(articleFloor,".",item.get_text().strip())#獲取糗事內容
    for comment in soupComment.find_all(attrs="body"):
        print("      ",commentFloor,"樓回復：",comment.get_text())#獲取評論內容
        commentFloor += 1

def command():
    while True:
        raw = input("點擊enter查看或者輸入exit退出，請輸入你的選擇：")
        if raw==‘enter‘:
            main()
            break
        else:
            break


def main():
    article_url_base = ‘https://www.qiushibaike.com/8hr/page/%d/‘#文章地址
    comment_url_base = ‘https://www.qiushibaike.com/article/%s‘#評論地址
    article_url = article_url_base % 2
    content = get_html(article_url)
    get_comment_link(content,comment_url_base)

if __name__ == ‘__main__‘:
    command()

bs4抓取糗事百科