求助
触发网页反爬了怎么解决，今天刚学习到实战那里，代码打好了执行以后就返回418的错误 {:10_284:}能上个代码、错误提示么。。。。。。你这一句话，也不知道啥意思一般加个headers，多几个参数，或者换手机端网页，能获取json就获取json更方便 本帖最后由 黄jz 于 2020-10-3 18:07 编辑
import urllib.request
from http.cookiejar import CookieJar
# 豆瓣的登录url
loginurl = 'https://accounts.douban.com/passport/login'
cookie = CookieJar()
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor)
data = {
"form_email":"your email",
"form_password":"your password",
"source":"index_nav"
}
data = {}
data['form_email'] = '
data['form_password'] =
data['source'] = 'index_nav'
response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
# 登录成功跳转至首页
if response.geturl() == "http://www.douban.com/":
print('登录成功！')
Traceback (most recent call last):
File "G:\新建文件夹 (4)\test2.py", line 20, in <module>
response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
File "E:\python\lib\urllib\request.py", line 531, in open
response = meth(req, response)
File "E:\python\lib\urllib\request.py", line 640, in http_response
response = self.parent.error(
File "E:\python\lib\urllib\request.py", line 569, in error
return self._call_chain(*args)
File "E:\python\lib\urllib\request.py", line 502, in _call_chain
result = func(*args)
File "E:\python\lib\urllib\request.py", line 649, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 418:
>>> 本帖最后由 黄jz 于 2020-10-3 18:07 编辑
疾风怪盗 发表于 2020-9-10 12:59
能上个代码、错误提示么。。。。。。你这一句话，也不知道啥意思
一般加个headers，多几个参数 ...
import urllib.request
from http.cookiejar import CookieJar
# 豆瓣的登录url
loginurl = 'https://accounts.douban.com/passport/login'
cookie = CookieJar()
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor)
data = {
"form_email":"your email",
"form_password":"your password",
"source":"index_nav"
}
data = {}
data['form_email'] = '
data['form_password'] =
data['source'] = 'index_nav'
response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
# 登录成功跳转至首页
if response.geturl() == "http://www.douban.com/":
print('登录成功！')
Traceback (most recent call last):
File "G:\新建文件夹 (4)\test2.py", line 20, in <module>
response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
File "E:\python\lib\urllib\request.py", line 531, in open
response = meth(req, response)
File "E:\python\lib\urllib\request.py", line 640, in http_response
response = self.parent.error(
File "E:\python\lib\urllib\request.py", line 569, in error
return self._call_chain(*args)
File "E:\python\lib\urllib\request.py", line 502, in _call_chain
result = func(*args)
File "E:\python\lib\urllib\request.py", line 649, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 418:
>>> 豆瓣418吧，改ua，默认ua会被反扒，要这样：
import requests
headers = {'user-agent': 'firefox'} # 其实写成什么都可以，只要不是默认的python-requests/urllib，这里随便写的firefox。
r = requests.get('https://www.douban.com', headers=headers)
print(r.text)
页:
[1]