使用requests库用cookie登录简书账号

Python网络爬虫与信息提取 

 

•  使用python的requests库，就是跳过浏览器直接用脚本去访问服务器；

• 首先我们要知道服务器的url，然后先用浏览器模拟访问该url，获取浏览器的信息（user-agent）和cookie进行重置request_header

  "cookie": "read_mode=day; default_font=font2; locale=zh-CN; __yadk_uid=tBJkWigvhZok7EuAKfwbks5CEThAs7SQ; Hm_lvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1564490433,1564582799,1564584053; remember_user_token=W1sxODk0NTA5MF0sIiQyYSQxMSQ0cC5hNkFBWlZXdC5wTExLSm1xVWhlIiwiMTU2NDU4NDE1MC43ODU1MyJd--492bdf762eff89f4862fd1253125371c872f6f1c; _m7e_session_core=e791d2ac5b26540689c22156723f10a6; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2218945090%22%2C%22%24device_id%22%3A%2216c42e580991c4-076c7180f30ebe-c343162-2073600-16c42e5809a632%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%7D%2C%22first_id%22%3A%2216c42e580991c4-076c7180f30ebe-c343162-2073600-16c42e5809a632%22%7D; Hm_lpvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1564585064",
  "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"

   

• 若是需要上传参数（写博文，评论，更改或获取具体信息），则需要使用post请求并在请求后面添加具体的参数

    data = {
        'content': "Just Try 一下！" + str(x),
        'parent_id': 'null'
    }
    r = requests.post(url_writer, headers=header_writer, data=data)

 

 

 一.登陆简书

import requests
from bs4 import BeautifulSoup

url = "https://www.jianshu.com/"

headers1 = {
    # 记得每个参数之后要带“，”
    # 不能带这些参数
    # ":authority": "www.jianshu.com",
    # ':method': 'GET',
    # ":path": "/subscriptions",
    # ":scheme": "https",
    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
    "accept-encoding": "gzip, deflate, br",
    "accept-language": "zh-CN,zh;q=0.9",
    "cache-control": "max-age=0",
    "cookie": "read_mode=day; default_font=font2; locale=zh-CN; __yadk_uid=tBJkWigvhZok7EuAKfwbks5CEThAs7SQ; Hm_lvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1564490433,1564582799,1564584053; remember_user_token=W1sxODk0NTA5MF0sIiQyYSQxMSQ0cC5hNkFBWlZXdC5wTExLSm1xVWhlIiwiMTU2NDU4NDE1MC43ODU1MyJd--492bdf762eff89f4862fd1253125371c872f6f1c; _m7e_session_core=e791d2ac5b26540689c22156723f10a6; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2218945090%22%2C%22%24device_id%22%3A%2216c42e580991c4-076c7180f30ebe-c343162-2073600-16c42e5809a632%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%7D%2C%22first_id%22%3A%2216c42e580991c4-076c7180f30ebe-c343162-2073600-16c42e5809a632%22%7D; Hm_lpvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1564585064"
    ,
    'if-none-match': 'W/"49471185b1d3265f2d523c590b251605"',
    "referer": "https://www.jianshu.com/notifications",
    "upgrade-insecure-requests": "1",
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36"
}

# requests库获取html请求
r = requests.get(url, headers=headers1)

# beautifulSoup库解析html文件
connect = BeautifulSoup(r.text, "html.parser")
# print(connect.text)

# 打印html页面
print(r.text)
print(r.status_code)

首先自己在网页登录简书的账号，然后找到链接并复制request header用来当作我们请求头，前面部分的要去掉，估计requests请求的时候自带一部分的内容

 

二.在文章里面评论 

首先找到发送评论的url，以及参数名（可以在Chrome的开发者模式network获取，或者使用fiddle）

import requests
from bs4 import BeautifulSoup
import time


# 简书写文章
url_writer = "https://www.jianshu.com/notes/47346873/comments"

header_writer = {
    # :authority: www.jianshu.com
    # :method: POST
    # :path: /notes/47346873/comments
    # :scheme: https
    # accept: application/json
    # accept-encoding: gzip, deflate, br
    # accept-language: zh-CN,zh;q=0.9
    # content-length: 34
    # content-type: application/json;charset=UTF-8
    'cookie':  'read_mode=day; default_font=font2; locale=zh-CN; __yadk_uid=tBJkWigvhZok7EuAKfwbks5CEThAs7SQ; _m7e_session_core=29d8488b1360c5c5c82504b394f435e0; Hm_lvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1564490433,1564582799,1564584053,1564673087; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%2218945090%22%2C%22%24device_id%22%3A%2216c42e580991c4-076c7180f30ebe-c343162-2073600-16c42e5809a632%22%2C%22props%22%3A%7B%22%24latest_traffic_source_type%22%3A%22%E7%9B%B4%E6%8E%A5%E6%B5%81%E9%87%8F%22%2C%22%24latest_referrer%22%3A%22%22%2C%22%24latest_referrer_host%22%3A%22%22%2C%22%24latest_search_keyword%22%3A%22%E6%9C%AA%E5%8F%96%E5%88%B0%E5%80%BC_%E7%9B%B4%E6%8E%A5%E6%89%93%E5%BC%80%22%7D%2C%22first_id%22%3A%2216c42e580991c4-076c7180f30ebe-c343162-2073600-16c42e5809a632%22%7D; Hm_lpvt_0c0e9d9b1e7d617b3e6842e85b9fb068=1564673722',
    'origin ':  'https://www.jianshu.com ',

    'referer': 'https://www.jianshu.com/p/5d4091cfdbc9',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36',
    'x-csrf-token': '0vcu/8mVFisy9QHdnNK/I3nsyesq7Rzaf7mSj7kj49XuQUUKyZbvEGVw3XVkbbU2kub8c34EJBTO1/a3daSPwQ=='
}


# requests库获取html请求
x = 5
while x:
    data = {
        'content': "Just Try 一下！" + str(x),
        'parent_id': 'null'
    }
    r = requests.post(url_writer, headers=header_writer, data=data)
    x = x-1
    print(data['content'])
    time.sleep(2)

# beautifulSoup库解析html文件
connect = BeautifulSoup(r.text, "html.parser")
# print(connect.text)

# 打印html页面
print(r.text)
print(r.status_code)