# 引入庫和請(qǐng)求頭文件import requestsfrom bs4 import BeautifulSoupheaders = {  'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}# 定義主體函數(shù)。函數(shù)主體由四部分組成：#1.請(qǐng)求網(wǎng)址#2.解析網(wǎng)頁，形成可查找的html格式#3.通過soup.select或者sopu.find_all查找需要的標(biāo)簽#4.通過zip()代碼將多個(gè)內(nèi)容合并在一起def get_content(url):  res = requests.get(url,headers = headers)  res.encoding = 'utf-8'  soup = BeautifulSoup(res.text,'html.parser')  contents = soup.find_all('div','bbs-content')  authors = soup.find_all('a','js-vip-check')  for author,content in zip(authors,contents):    data = {    'author':author.get_text().strip(),    'content': content.get_text().strip()  }    print(data)# 在這里構(gòu)造一個(gè)兩層鏈接結(jié)構(gòu)：帖子的1、2、3、4頁和帖子的詳情頁的關(guān)系在這里實(shí)現(xiàn)if __name__ == '__main__':  urls = ['http://bbs.tianya.cn/post-develop-2271894-{}.shtml'.format(str(i)) for i in range (1,5)] # 要注意，這里的‘5'是不包括在范圍里的  for url in urls:    get_content(url)