Python学习笔记｜爬虫基础（二）Cookie 模拟登录、Post请求

AI摘要：本文介绍了使用Python进行爬虫的基础知识，包括Cookie模拟登录和使用POST请求获取金山翻译的方法。通过模拟登录，可以在爬取网页时绕过登录验证，获取到需要的数据。而使用POST请求可以向服务器发送数据，并获取服务器返回的结果。文章中给出了具体的代码示例，帮助读者理解和实践这些方法。

一、Cookie 模拟登录

import requests

headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36',
    'Cookie':''
}

url = ''

res = requests.get(url, headers = headers)

print(res.text)

二、使用post请求获取金山翻译

import requests
import json
import random
from fake_useragent import UserAgent

# 获取请求url
url = 'https://ifanyi.iciba.com/index.php?c=trans'

# 构造headers
headers = {
    'User-Agengt':UserAgent().random
}

#输入待译文本
word = input("请输入待译文本：")

# 构建data参数字典
post_data ={
    'from':'zh',
    'to':'en',
    'q': word
}

#发起请求
res = requests.post(url, headers = headers, data = post_data)

#获取请求内容
# print(res.text)

#将Json数据解析为字典
dic = json.loads(res.text)

#获取输出内容格式
# print(type(dic))

#打印译文
print(dic["out"])

请输入待译文本： 金山翻译

Jinshan translation

import requests
import json
# import random
# from fake_useragent import UserAgent

# 获取请求url
url = 'https://app.languagex.com/api/translator/translation/text'

# 构造headers
headers = {
    'User-Agengt':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36',
    
    'Cookie': 'Hm_lvt_d78dae91eafe9d7af5ea9e954247f348=1704525651; token=eyJhbGciOiJIUzI1NiJ9.eyJ1aWQiOjE1NzI5NjUwNjIzMDU0OTcwOTAsIm1pZCI6MTY4MjIzMDI2MTM5NzAwMSwidXNlcm5hbWUiOiJMWDYzMmM3OTdkYTdmNjBhYzJlMjM5YjMyOCIsImV4cCI6MTcwNTU5MjUzNH0.YktHsPJ7aXhERNmvLQ3w0SAwabweGsoqsQ1wFAbiFoQ; org=eyJhbGciOiJIUzI1NiJ9.eyJpZCI6MTcwMTg1MTc3NzAwNjg3MywibmFtZSI6IumrmOagoee_u-ivkemhueebriIsInR5cGUiOiJFTlRFUlBSSVNFIiwicm9sZUlkIjoyLCJ0ZWFtSWRMaXN0IjpbMTcwMTg1MTc3NzAwNjg3N119.nCdkNCDrkBxHCDJxvYGZo4nFOUgsGKwUPDq4KwaStTw; Hm_lpvt_d78dae91eafe9d7af5ea9e954247f348=1705333336'
}

#输入待译文本
# word = input("请输入待译文本：")

# 构建data参数字典
post_data ={
    "domain":"general",
     "engine":"chatgpt",
     "engineKey":"chatgpt",
     "sourceLang":"zh",
     "sourceText":"美国",
     "targetLang":"en",
     "terms":[]
}

#发起请求
res = requests.post(url, headers = headers, data = post_data)

#获取请求内容
# print(res.text)
print(res)

#将Json数据解析为字典
# dic = json.loads(res.text)

#获取输出内容格式
# print(type(dic))

#打印译文
# print(dic["out"])

<Response [415]>