TA的每日心情 | 擦汗 4 天前 |
---|
签到天数: 532 天 [LV.9]以坛为家II
版主
- 积分
- 1215
|
就很糟心 写完了 才看到有个一个专门的库去处理这种问题会简单很多。。。
过几天重写一下⑧
先记录一下这个代码
- import requests
- import re
- def get_stroy():
- url = 'http://book.sbkk8.com/gushihui/taijiaogushi/'
- headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36'}
- res = requests.get(url=url,headers=headers)
- res.encoding = 'gbk'
- name_list1 = re.compile(r'.html" target="_blank">(.*?)</a>').findall(res.text)
- #print(name_list1)
- name_list=[]
- #爬出来的名字中有的有其他的符号 在这里我们对他进行替换掉
- for i in range(len(name_list1)):
- a=name_list1[i].replace('<b>','')
- b=a.replace('</b>','')
- name_list.append(b)
- print(name_list)#到这里我们就得到了正确的故事标题 name_list
- #我们开始获取URL链接
- url_list1 = re.compile(r'mululist"> <a href="(.*?)" target="_blank">').findall(res.text)
- print(url_list1)
- url_list=[]
- for i in range(len(url_list1)):#循环对url进行拼接
- url_list.append(url_list1[i].replace('/gushihui/','http://book.sbkk8.com/gushihui/'))
- print(url_list)
- #到这里我们就有了所有的标题和url链接,
- #进入url取出故事内容
- story=[]
- for i in range(len(url_list)):
- url=url_list[i]
- res_story = requests.get(url)
- res_story.encoding = 'gbk'
- # print(res_story.text)
- res_story = re.compile(
- r'</span><p>.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*\s.*').findall(
- res_story.text)[0]
- # print(res_story)
- a = res_story.replace('<br style="color: rgb(34, 34, 34); font-family: sans-serif, 宋体, 微软雅黑, arial, ', '')
- a = a.replace('<u>一</u>', '')
- a = a.replace('”', '"')
- a = a.replace('</p></div>', '')
- a = a.replace(', Helvetica; line-height: 24px;" />', '')
- a = a.replace("'Helvetica Neue'", '')
- a = a.replace('“', '"')
- a = a.replace('</span><p>', '')
- a = a.replace('</html>', '')
- a = a.replace('</body>', '')
- a = a.replace('<script src="http://book.sbkk8.com/js/foot.js" type="text/javascript"></script>', '')
- a = a.replace('</div>', '')
- a = a.replace(
- '<p>声明 :本网站尊重并保护知识产权,根据《信息网络传播权保护条例》,如果我们转载的作品侵犯了您的权利,请通知我们,我们会及时删除。联系Q-Q:2-8-1-6-4-1-1-4-9-5</p>', '')
- a = a.replace('<p>2016 <b><a href="http://book.sbkk8.com">book.sbkk8.com</a></b> - 版权所有</p>', '')
- a = a.replace('<div id="footer"> ', '')
- a = a.replace(' <script src="http://book.sbkk8.com/js/pinglun.js" type="text/javascript"></script>', '')
- a = a.replace('<script src="http://book.sbkk8.com/js/adBottom.js" type="text/javascript"></script>', '')
- a = a.replace('<div class="sohuCmt1">', '')
- a = a.replace('<div class="adBottom">', '')
- a = a.replace('>【下一篇】<i>:</i></a></span>', '')
- a = a.replace("'pagedaohang'", '')
- a = a.replace('class=', '')
- a = a.replace("'/gushihui/taijiaogushi/92709.html'", '')
- a = a.replace('</span><span "toup1"><a href=', '')
- a = a.replace('<script src="http://book.sbkk8.com/js/adBottom_sougou.js" type="text/javascript"></script>', '')
- a = a.replace(
- '>【第一篇】</a></span><span "tomenu"><a href="/gushihui/taijiaogushi/" title="胎教故事" "returnIndex">【回目录】</a>',
- '')
- a = a.replace(" 'pagedaohang pagedaohang1'", '')
- a = a.replace('<div "prenext prenext1"><span "todown1"><a', '')
- a = a.replace('<p>', '')
- a = a.replace('</p>', '')
- a = a.replace('"', '"')
- a = a.replace('……', '')
- story.append(a)
- print(len(story))
- for i in range(len(story)):
- with open(name_list[i]+'.txt','w') as f:
- f.write(story[i])
- print(name_list[i]+' 已爬取!')
- if __name__ == "__main__":
- get_stroy()
复制代码
|
|