爬取吞噬星空小说
import requests
import re
url = "https://www.777zw.net/2/2142/751765.html"
with open('tunshixingkong.txt', 'a', encoding='utf8') as f:
for i in range(5000):
try:
r = requests.get(url)
r.encoding = 'gbk'
url = re.findall('下一章', r.text)[0]
url = url.split(';')[-1]
url = re.findall(' title = re.findall('(.*?)
', r.text)[0]
content = re.findall('id="content">(.*?)
","\n")
f.write(title+'\n'+content+'\n'*2)
print(f'第{i+1}章')
except:
print('defeat!')
print(url)