import requests

r = requests.get('https://api.github.com/user', auth=('haiyu19931121@163.com', 'Shy18137803170'))print(r.status_code)  # 状态码200print(r.json())  # 返回json格式print(r.text)  # 返回文本print(r.headers)  # 头信息print(r.encoding)  # 编码方式，一般utf-8# 当写入文件比较大时，避免内存耗尽，可以一次写指定的字节数或者一行。# 一次读一行，chunk_size=512为默认值for chunk in r.iter_lines():print(chunk)# 一次读取一块，大小为512for chunk in r.iter_content(chunk_size=512):print(chunk)

from bs4 import BeautifulSoup

html_doc = """
The Dormouse's story
Once upon a time there were three little sisters; and their names wereElsie,Lacie andTillie;and they lived at the bottom of a well.
...
"""# 就注意一点，第二个参数指定解析器，必须填上，不然会有警告。推荐使用lxmlsoup = BeautifulSoup(html_doc, 'lxml')

soup.a
soup.find('p')

# soup.body是一个Tag对象。是body标签中所有html代码print(soup.body)

# 获取body里所有文本，不含标签print(soup.body.text)# 等同于下面的写法soup.body.get_text()# 还可以这样写,strings是所有文本的生成器for string in soup.body.strings:print(string, end='')

# 获得该标签里的文本。print(soup.title.string)

# Tag对象的get方法可以根据属性的名称获得属性的值，此句表示得到第一个p标签里class属性的值print(soup.p.get('class'))# 和下面的写法等同print(soup.p['class'])

# 查看a标签的所有属性，以字典形式给出print(soup.a.attrs)

# 标签的名称soup.title.name

soup.find_all('a', id='link1')
soup('a', id='link1')

# 传入字符串soup.find_all('p')# 传入正则表达式import re# 必须以b开头for tag in soup.find_all(re.compile("^b")):print(tag.name)# body# b# 含有t就行for tag in soup.find_all(re.compile("t")):print(tag.name)# html# title# 传入列表表示，一次查找多个标签soup.find_all(["a", "b"])# [The Dormouse's story,#  Elsie,#  Lacie,#  Tillie]

# title不是html的直接子节点，但是会检索其下所有子孙节点soup.html.find_all("title")# []# 参数设置为False，只会找直接子节点soup.html.find_all("title", recursive=False)# []# title就是head的直接子节点，所以这个参数此时无影响a = soup.head.find_all("title", recursive=False)# []

# 查看所有id为link1的p标签soup.find_all('a', id='link1')

soup.find_all('p', class_='story')
soup.find_all('p', 'story')
soup.find_all('p', attrs={"class": "story"})

a = soup.find_all(text='Elsie')# 或者，4.4以上版本请使用texta = soup.find_all(string='Elsie')

# 所有div标签soup.select('div')# 所有id为username的元素soup.select('.username')# 所有class为story的元素soup.select('#story')# 所有div元素之内的span元素，中间可以有其他元素soup.select('div span')# 所有div元素之内的span元素，中间没有其他元素soup.select('div > span')# 所有具有一个id属性的input标签，id的值无所谓soup.select('input[id]')# 所有具有一个id属性且值为user的input标签soup.select('input[id="user"]')# 搜索多个，class为link1或者link2的元素都符合soup.select("#link1, #link2")

import osimport requestsfrom bs4 import BeautifulSoup# exist_ok=True，若文件夹已经存在也不会报错os.makedirs('xkcd')
url = 'https://xkcd.com/'headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '  'Chrome/57.0.2987.98 Safari/537.36'}def save_img(img_url, limit=1):
    r = requests.get(img_url, headers=headers)
    soup = BeautifulSoup(r.text, 'lxml')try:
        img = 'https:' + soup.find('div', id='comic').img.get('src')except AttributeError:print('Image Not Found')else:print('Downloading', img)
        response = requests.get(img, headers=headers)with open(os.path.join('xkcd', os.path.basename(img)), 'wb') as f:for chunk in response.iter_content(chunk_size=1024*1024):
                f.write(chunk)# 每次下载一张图片，就减1limit -= 1# 找到上一张图片的网址if limit > 0:try:
            prev = 'https://xkcd.com' + soup.find('a', rel='prev').get('href')except AttributeError:print('Link Not Exist')else:
            save_img(prev, limit)if __name__ == '__main__':
    save_img(url, limit=20)print('Done!')

import osimport threadingimport requestsfrom bs4 import BeautifulSoup

os.makedirs('xkcd')

headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '  'Chrome/57.0.2987.98 Safari/537.36'}def download_imgs(start, end):for url_num in range(start, end):
        img_url = 'https://xkcd.com/' + str(url_num)
        r = requests.get(img_url, headers=headers)
        soup = BeautifulSoup(r.text, 'lxml')try:
            img = 'https:' + soup.find('div', id='comic').img.get('src')except AttributeError:print('Image Not Found')else:print('Downloading', img)
            response = requests.get(img, headers=headers)with open(os.path.join('xkcd', os.path.basename(img)), 'wb') as f:for chunk in response.iter_content(chunk_size=1024 * 1024):
                    f.write(chunk)if __name__ == '__main__':# 下载从1到30，每个线程下载10个threads = []for i in range(1, 30, 10):
        thread_obj = threading.Thread(target=download_imgs, args=(i, i + 10))
        threads.append(thread_obj)
        thread_obj.start()# 阻塞，等待线程执行结束都会等待for thread in threads:
        thread.join()# 所有线程下载完毕，才打印print('Done!')

from selenium import webdriverfrom selenium.webdriver.common.keys import Keysimport time

browser = webdriver.Chrome()# Chrome打开百度首页browser.get('https://www.baidu.com/')# 找到输入区域input_area = browser.find_element_by_id('kw')# 区域内填写内容input_area.send_keys('The Zen of Python')# 找到"百度一下"search = browser.find_element_by_id('su')# 点击search.click()# 或者按下回车# input_area.send_keys('The Zen of Python', Keys.ENTER)time.sleep(3)
browser.get('https://www.zhihu.com/')
time.sleep(2)# 返回到百度搜索browser.back()
time.sleep(2)# 退出浏览器browser.quit()

browser.back()  # 返回按钮browser.forward() # 前进按钮browser.refresh()  # 刷新按钮browser.close()  # 关闭当前窗口browser.quit()  # 退出浏览器

browser = webdriver.Chrome()
browser.get('https://passport.csdn.net/account/login')
browser.find_element_by_id('username').send_keys('haiyu19931121@163.com')
browser.find_element_by_id('password').send_keys('**********')
browser.find_element_by_class_name('logging').click()