lsy/practice_code
0
0
Fork 0
Code Pull Requests Actions Packages Projects Releases Wiki Activity

更新wz

Browse Source
This commit is contained in:
lsy2246 2024-03-27 18:37:21 +08:00
parent dd7b4df73a
commit 04d9de88e8
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
python/spider/blog/wz.py
View File

@ -2,24 +2,29 @@ import requests
from threading import Thread from threading import Thread
from lxml import etree from lxml import etree
import re import re
import os
def get_html(url): def get_html(url):
if not os.path.exists("wz"):
os.mkdir("wz")
resp = requests.get(url) resp = requests.get(url)
resp.close() resp.close()
html = etree.HTML(resp.text) html = etree.HTML(resp.text)
title = html.xpath('/html/body/div[2]/div/main/div[1]/div/h1/text()') title = html.xpath('/html/body/div[2]/div/main/div[1]/div/h1/text()')
content = html.xpath('/html/body/div[2]/div/main/article/div') content = html.xpath('/html/body/div[2]/div/main/article/div')
title = ''.join(list(title[0])) title = ''.join(list(title[0]))
file = open(f"wz\\{title}.txt", "a+") file = open(f"wz\\{title}.txt", "a+", errors='ignore')
file.write(f"URL : {url}\n") URL = (f"URL : {url}\n")
file.write(URL)
print(f"正在抓取{title}")
## 获取内容 ## 获取内容
for i in content: for i in content:
text = i.xpath('.//text()') text = i.xpath('.//text()')
for word in text: for word in text:
word_encode = word.encode('utf-8')
file.write(word) file.write(word)
file.close() file.close()
print(f"{title}抓取成功")
for index in range(1, 4): for index in range(1, 4):