Preface
The content of the official account needs to be crawled for a single page of the actor's work and its year
Code
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
import time
browser = webdriver.Chrome()
url = "https://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gb18030&word=%B9%FE%CA%BF%C6%E6&fr=ala&ala=1&alatpl=adress&pos=0&hs=2&xthttps=000000"
headers = { # 模拟浏览器身份头向对方发送消息
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36',
}
browser.get("https://movie.douban.com/celebrity/1050210/movies?sortby=vote&format=pic")
info_list = browser.find_elements_by_xpath("//div[@id='content']//h6/a")
year_list = browser.find_elements_by_xpath("//div[@id='content']//h6/span[1]")
for (info,year) in zip(info_list,year_list):
print(info.text,year.text)
Get
it, get the poster down
url_list = browser.find_elements_by_xpath("//a[@class='nbg']/img")
for i,url in enumerate(url_list):
imgurl = str(url.get_attribute("src")).replace("webp","jpg")
print(imgurl)
img = requests.get(imgurl).content
with open("D:/base/%s.jpg"%i,"wb") as fp:
fp.write(img)
print("正在下载海报%s"%i)
Then you can copy it to the official account article