python 采集斗图啦(多线程)
import concurrent import requests; from concurrent.futures import ThreadPoolExecutor import os; import parsel; def send_request(url): header = { "user-agent":'Mozilla/5.0 (Macintos
Python
python 采集斗图啦xpath
import requests; import re; import os; import parsel; # 1.请求网页 header = { "user-agent":'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrom
python 采集唯美girl
import requests; import re; import os; # 1.请求网页 header = { "user-agent":'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100
py 采集流程整理
过程 获取列表链接 打开链接获取详情 处理数据 保存数据 对数据进行处理 处理杂质 可视化数据 import urllib import pandas as pd import requests from lxml import etree import os import csv import time import pymysql # 全局取消证书验证
py request 基础
import requests #常用的形式 # requests.get() # requests.post() # requests.put() # requests.request('post') # 参数 # url='xxx', # params={'name':11,'pwd':1212}, # cookies = {}, # headers =
py 登录github时token以及cookie的应用
import requests from bs4 import BeautifulSoup ## 获取token r1 = requests.get('https://github.com/login') s1 = BeautifulSoup(r1.text,'html.parser') token = s1.find(name='input',attrs
py 爬取汽车之家新闻案例
import requests from bs4 import BeautifulSoup response = requests.get("https://www.autohome.com.cn/news/") # 1. content /text 的区别 # print(response.content) # content 拿到的字节 response
python 案例
itchat 查看手机微信中用户比例 import itchat import pandas as pd # Python抓取微信好友数量、性别、城市分布，以及将py文件打包成exe. #https://zhuanlan.zhihu.com/p/73295760 # 先登录 itchat.auto_login(hotReload=True) # 获取好友列表
python request模块
sign token获取不到可测试手机端 百度翻译(案例) import requests header = { 'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.38
python 通用爬虫(百度贴吧)
import requests class TiebaSpider(): def __init__(self,tieba_name): self.tieba_name = tieba_name print(self.tieba_name) self.url_temp = "https://tieba.baidu.com/f?kw="+tieba_name+"