菜鸟中的菜菜鸟,学习得多实践
把学到的,输出自己的想法到代码上练习。
多实践才能多理解啊。
// A code block
spider for novel
// An highlighted block
import re, requests
from lxml.html import fromstring,tostring
import time
url = 'https://xxx.xxx.com/'
headers = {
"user_agent":"Mozilla/5.0",
}
a = []
with open("url.txt",'r') as f:
for line in f.readlines():
a.append(f"http:{line}")
for i in a:
res = requests.get(url=i,headers=headers,)
html = res.content
html = fromstring(html)
data = html.xpath("//div[@class='read-content j_readContent']")[0]
text_url = data.xpath('string(.)')
with open("url_new_http.txt",'a',encoding='utf-8') as fd:
fd.writelines(text_url)
time.sleep(3)