1from bs4 import BeautifulSoup
2import requests,os,re
3
4
5
6
7#获取小说章节与链接
8if name == "main":
9 server = "https://www.abcxs.com"</span><br><span class="linenum hljs-number" style="font-size: inherit; line-height: inherit; margin: 0px; padding: 0px; color: rgb(174, 135, 250); padding-right: 20px; word-spacing: 0px; word-wrap: inherit !important; word-break: inherit !important;">10 url = "https://www.abcxs.com/book/13417/#main"</span><br><span class="linenum hljs-number" style="font-size: inherit; line-height: inherit; margin: 0px; padding: 0px; color: rgb(174, 135, 250); padding-right: 20px; word-spacing: 0px; word-wrap: inherit !important; word-break: inherit !important;">11 r = requests.get(url)
12 html = r.text
13
14 #获取书名
15 title_bf = BeautifulSoup(html)
16 title = title_bf.find_all(property = 'og:title')
17 print(title)
18 #data = re.search( '?)" property=', title, re.M|re.I)
19 searchObj = re.search( '?)" property=' , str(title), re.M|re.I)
20 if searchObj:
21 print ("searchObj.group(1) : ", searchObj.group(1))
22 ShuMing = searchObj.group(1)
23 else:
24 print ("Nothing found!!")
25
26 #获取小说目录
27
28 div_bf = BeautifulSoup(html)
29 div = div_bf.findall('div',class="listmain")
30 #print(div[zxsq-anti-bbcode-0])
31 a_bf = BeautifulSoup(str(div[0]))
32 a = a_bf.find_all('a')
33 for each in a:
34 print(each.string, server + each.get('href'))
35
36 #创建文件目录
37 path = "J:/python/Python/我的Python学习/爬虫及文件写入/" + ShuMing
38 if not os.path.exists(path):
39 os.mkdir(path)
40 #获取正文内容
41 if name == "main":
42 r = requests.get(server + each.get('href'))
43 html = r.text
44 bf = BeautifulSoup(html)
45 tetx_content = bf.findall('div', class = 'showtxt')
46 print(tetx_content[0].text.replace('\xa0'*8,'\n'))
47 #tetx_content = bf.replace(u'\xa0', u' ')
48
49 #写入文件
50 with open(path + "/" + each.string + '.txt', 'w') as f:
51 #f.file.write(tetx_content[zxsq-anti-bbcode-0].content.replace(u'\xa0,u'))
52 f.write(tetx_content[0].text.replace(u'\xa0', u' '))
1from bs4 import BeautifulSoup
2import requests,os,re
3
4
5
6
7#获取小说章节与链接
8if name == "main":
9 server = "https://www.abcxs.com"</span><br><span class="linenum hljs-number" style="font-size: inherit; line-height: inherit; margin: 0px; padding: 0px; color: rgb(174, 135, 250); padding-right: 20px; word-spacing: 0px; word-wrap: inherit !important; word-break: inherit !important;">10 url = "https://www.abcxs.com/book/13417/#main"</span><br><span class="linenum hljs-number" style="font-size: inherit; line-height: inherit; margin: 0px; padding: 0px; color: rgb(174, 135, 250); padding-right: 20px; word-spacing: 0px; word-wrap: inherit !important; word-break: inherit !important;">11 r = requests.get(url)
12 html = r.text
13
14 #获取书名
15 title_bf = BeautifulSoup(html)
16 title = title_bf.find_all(property = 'og:title')
17 print(title)
18 #data = re.search( '?)" property=', title, re.M|re.I)
19 searchObj = re.search( '?)" property=' , str(title), re.M|re.I)
20 if searchObj:
21 print ("searchObj.group(1) : ", searchObj.group(1))
22 ShuMing = searchObj.group(1)
23 else:
24 print ("Nothing found!!")
25
26 #获取小说目录
27
28 div_bf = BeautifulSoup(html)
29 div = div_bf.findall('div',class="listmain")
30 #print(div[zxsq-anti-bbcode-0])
31 a_bf = BeautifulSoup(str(div[0]))
32 a = a_bf.find_all('a')
33 for each in a:
34 print(each.string, server + each.get('href'))
35
36 #创建文件目录
37 path = "J:/python/Python/我的Python学习/爬虫及文件写入/" + ShuMing
38 if not os.path.exists(path):
39 os.mkdir(path)
40 #获取正文内容
41 if name == "main":
42 r = requests.get(server + each.get('href'))
43 html = r.text
44 bf = BeautifulSoup(html)
45 tetx_content = bf.findall('div', class = 'showtxt')
46 print(tetx_content[0].text.replace('\xa0'*8,'\n'))
47 #tetx_content = bf.replace(u'\xa0', u' ')
48
49 #写入文件
50 with open(path + "/" + each.string + '.txt', 'w') as f:
51 #f.file.write(tetx_content[zxsq-anti-bbcode-0].content.replace(u'\xa0,u'))
52 f.write(tetx_content[0].text.replace(u'\xa0', u' '))
| 欢迎光临 精易论坛 (https://125.confly.eu.org/) | Powered by Discuz! X3.4 |