爬虫小练习：网页源代码隐藏数据（非ajax和js加载）之空气质量网

注：一层一层剥开它的心，切记一次性访问目标网页

from selenium import webdriver
import requests
import time

option = webdriver.ChromeOptions()
option.add_argument("disable-infobars")
option.add_argument("--headless")

driver = webdriver.Chrome(chrome_options = option)
driver.get("https://www.aqistudy.cn/historydata/")
driver.maximize_window()
time.sleep(2)

driver.find_element_by_xpath('//div[@class="bottom"]//a[@href="monthdata.php?city=深圳"]').click()
time.sleep(3)
content = driver.page_source
# print(content)

# response = requests.get("https://www.aqistudy.cn/historydata/monthdata.php?city=%E4%B8%8A%E6%B5%B7")
# content = response.content.decode("utf-8")

with open("test.txt","w",encoding='utf-8') as f:
	f.write(content)

# print(content)