[已解决]python爬虫，re模块获取网址

53清 · 发表于 2021-8-20 21:09:51

您需要登录才可以下载或查看，没有账号？立即注册

x

import requests
import parsel
import re
headers = {
"User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122 Safari / 537.40"
}#UA伪装
url = 'https://www.leshe.us/?ref=214'#乐摄网
response = requests.get(url=url,headers=headers)
selector = parsel.Selector(response.text)
lis = list(selector.css('.row.posts-wrapper div article'))
for li in lis:
urls2 = li.css('a::attr(href)').get()
response2 = requests.get(url=urls2,headers=headers)
text = response2.text
print(text)
print('--------------------------')
photo = re.findall('data-srcset="(.*?)" title',text)#这里有问题，photo获取不到想要的网址
print(photo)

复制代码

获取不到网址，photo返回的是空列表

最佳答案

suchocolate

2021-8-21 15:19:17

本帖最后由 suchocolate 于 2021-8-21 15:20 编辑

# _*_ coding: utf-8 _*_
# Developer: suchocolate
# Date: 2021-08-21 14:26
# File name: test.py
# Development tool: PyCharm
import requests
import re
import os
import time
def main():
"""
1）先从总页面获取各相册入口。
2）遍历各个相册获取图片链接。
3）遍历图片链接下载图片。
:return:
"""
pd = 'pics' # 图片存储路径
if not os.path.exists(pd):
os.mkdir(pd)
os.chdir(pd)
headers = {'user-agent': 'firefox'}
pl = [] # 存储相册url
print('获取相册url...')
for pn in range(5): # 想爬多少页的相册自己定，这里爬5页
try:
url = f'https://www.leshe.us/page/{pn}'
r = requests.get(url, headers=headers)
result = re.findall(r'<a target="_blank" href="(.*?\.html)"', r.text) # 获取当前页相册url
pl.extend(result)
time.sleep(0.3)
except Exception as e:
print(e)
# print(pl)
jl = [] # 存图片url
print('获取图片url...')
for pu in pl:
try:
r = requests.get(pu, headers=headers, timeout=5)
result = re.findall(r'data-srcset="(.*?)"', r.text) # 获取当前页面图片的url
jl.extend(result)
time.sleep(0.3)
except Exception as e:
print(e)
# print(jl)
n = 1 # 图片计数
print(f'共{len(jl)}张图片，开始下载!')
for j in jl:
r = requests.get(j, headers=headers)
jn = j.split('/')[-1] # 图片的名字由url最后的字段决定
with open(jn, 'wb') as f:
f.write(r.content)
print(f'已下载{jn}, 共下载{n}张图片。')
n += 1
if __name__ == '__main__':
main()

复制代码

wp231957 · 发表于 2021-8-21 12:22:56

这个网站有反扒不是常规静态网站

suchocolate · 发表于 2021-8-21 15:19:17

本帖最后由 suchocolate 于 2021-8-21 15:20 编辑

# _*_ coding: utf-8 _*_
# Developer: suchocolate
# Date: 2021-08-21 14:26
# File name: test.py
# Development tool: PyCharm
import requests
import re
import os
import time
def main():
"""
1）先从总页面获取各相册入口。
2）遍历各个相册获取图片链接。
3）遍历图片链接下载图片。
:return:
"""
pd = 'pics' # 图片存储路径
if not os.path.exists(pd):
os.mkdir(pd)
os.chdir(pd)
headers = {'user-agent': 'firefox'}
pl = [] # 存储相册url
print('获取相册url...')
for pn in range(5): # 想爬多少页的相册自己定，这里爬5页
try:
url = f'https://www.leshe.us/page/{pn}'
r = requests.get(url, headers=headers)
result = re.findall(r'<a target="_blank" href="(.*?\.html)"', r.text) # 获取当前页相册url
pl.extend(result)
time.sleep(0.3)
except Exception as e:
print(e)
# print(pl)
jl = [] # 存图片url
print('获取图片url...')
for pu in pl:
try:
r = requests.get(pu, headers=headers, timeout=5)
result = re.findall(r'data-srcset="(.*?)"', r.text) # 获取当前页面图片的url
jl.extend(result)
time.sleep(0.3)
except Exception as e:
print(e)
# print(jl)
n = 1 # 图片计数
print(f'共{len(jl)}张图片，开始下载!')
for j in jl:
r = requests.get(j, headers=headers)
jn = j.split('/')[-1] # 图片的名字由url最后的字段决定
with open(jn, 'wb') as f:
f.write(r.content)
print(f'已下载{jn}, 共下载{n}张图片。')
n += 1
if __name__ == '__main__':
main()

复制代码

账号		自动登录	找回密码
密码			立即注册