Python爬虫期末试题（编程题答案）

Posted 2023-03-22

参考技术A from seleniumimport webdriver

import time

from selenium.webdriverimport ActionChains

driver = webdriver.Chrome()

driver.get("https://accounts.douban.com/passport/login")

# 点击密码登录

driver.find_element_by_class_name('account-tab-account').click()

# 定位账户 # 输入内容

driver.find_element_by_id('username').send_keys('2331566038')

driver.find_element_by_id('password').send_keys('*********')

# 点击登录

driver.find_element_by_link_text('登录豆瓣').click()

# 进入内嵌滑动验证页面

iframe = driver.find_element_by_id('tcaptcha_iframe')

driver.switch_to_frame(iframe)

element = driver.find_element_by_xpath('//*[@id="tcaptcha_drag_thumb"]')

ActionChains(driver).click_and_hold(on_element=element).perform()

ActionChains(driver).move_to_element_with_offset(to_element=element,xoffset=180,yoffset=0).perform()

driver.save_screenshot('豆瓣.png')

time.sleep(5)

driver.quit()

import urllib.request

import urllib.parse

url ="http://www.baidu.com/s"

word = "wd":"浙江大学"

word = urllib.parse.urlencode(word)

new_url = url +"?" + word

header =

"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/89.0.4389.114 Safari/537.36"



resquest = urllib.request.Request(new_url,headers = header,)

response = urllib.request.urlopen(resquest)

html = response.read().decode('utf-8')

print(html)