l_1_0_O的博客

import requests# 下载视频def download(url): with requests.get(url, stream=True) as r: print('开始下载。。。') with open('v.mp4', 'wb')as f: for i in r.iter_content(chunk_size=...

from selenium import webdriverfrom fake_useragent import UserAgentimport timeimport requestsimport hashlibimport pymysqlimport randomimport jsonclass CookiesPool: def __init__(self): ...

from selenium import webdriverimport timedef login(): driver = webdriver.Chrome() try: driver.maximize_window() driver.get('http://www.weibo.com/login.php') time.sl...

import requestsfrom lxml import etreefrom queue import Queueimport threadingimport jsonclass thread_crawl(threading.Thread): ''' 抓取线程类 ''' def __init__(self, threadID): ...

此文以B站模拟登录，滑动验证码的测试。import randomimport timeimport requestsfrom selenium.webdriver import ActionChainsfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.webdriver.supp...

本文获取西刺网免费代理IP，与mysql数据交互。实现代理IP池from selenium import webdriverfrom bs4 import BeautifulSoupfrom fake_useragent import UserAgentimport timeimport requestsimport hashlibimport pymysqlimport rand...

黑白图片文字获取，字体必须工整 from PIL import Image import pytesseract image = Image.open('./images/tesseracttest.jpg') # image.show() text = pytesseract.image_to_string(image) print(text)...

from scrapy import signalsimport randomfrom selenium import webdriverfrom scrapy.http import HtmlResponsefrom fake_useragent import UserAgentimport base64from bilibili.proxyIPPool import ProxyIp...