import requests

r = requests.get('https://api.github.com/user', auth=('haiyu19931121@163.com', 'Shy18137803170'))
print(r.status_code)  # 状态码200
print(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512
for chunk in r.iter_content(chunk_size=512):
    print(chunk)

from bs4 import BeautifulSoup

html_doc = """
<html>
<head>
<title>The Dormouse's story</title>
</head>
<body>
<p class="title"><b>The Dormouse's story</b></p>

<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""
# 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lxml
soup = BeautifulSoup(html_doc, 'lxml')
print(soup.prettify())

<html>
 <head>
  <title>
   The Dormouse's story
  </title>
 </head>
 <body>
  <p class="title">
   <b>
    The Dormouse's story
   </b>
  </p>
  <p class="story">
   Once upon a time there were three little sisters; and their names were
   <a class="sister" href="http://example.com/elsie" id="link1">
    Elsie
   </a>
   ,
   <a class="sister" href="http://example.com/lacie" id="link2">
    Lacie
   </a>
   and
   <a class="sister" href="http://example.com/tillie" id="link3">
    Tillie
   </a>
   ;
and they lived at the bottom of a well.
  </p>
  <p class="story">
   ...
  </p>
 </body>
</html>

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"])
# [<b>The Dormouse's story</b>,
#  <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
#  <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
#  <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]

# 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")
# [<title>The Dormouse's story</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)
# [<title name="good">The Dormouse's story</title>]
 

# 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text
a = 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 os
import requests
from 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1
    limit -= 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 os
import threading
import requests
from 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 webdriver
from selenium.webdriver.common.keys import Keys
import 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()