爬虫之requests库

Why requests

python的标准库urllib2提供了大部分需要的HTTP功能，但是API太逆天了，一个简单的功能就需要一大堆代码。

Requests 使用的是 urllib3，因此继承了它的所有特性。Requests 支持 HTTP 连接保持和连接池，支持使用 cookie 保持会话，支持文件上传，支持自动确定响应内容的编码，支持国际化的 URL 和 POST 数据自动编码。现代、国际化、人性化。。

官方文档：http://docs.python-requests.org/en/master/

中文文档：http://docs.python-requests.org/zh_CN/latest/user/quickstart.html

安装：

pip install requests

或者下载源码后安装

$ git clone git://github.com/kennethreitz/requests.git
$ cd requests
$ python setup.py install

也可以通过IDE安装比如pycharm(File-settings-Projecr Interpreter 点击右边的加号"+"然后搜索requests点击Install Package安装)

爬取校花网视频：

import requests
import re
import os
import hashlib
import time

DOWLOAD_PATH = r‘D:\Downloads‘

def get_page(url):
    try:
        response = requests.get(url, )
        if response.status_code == 200:
            return response.text
    except Exception:
        pass

def parse_index(index_contents):
    detail_urls = re.findall(‘class="items".*?href="(.*?)"‘, index_contents, re.S)
    for detail_url in detail_urls:
        if not detail_url.startswith(‘http‘):
            detail_url = ‘http://www.xiaohuar.com‘ + detail_url
        yield detail_url

def parse_detail(detail_contents):
    movie_urls = re.findall(‘id="media".*?src="(.*?)"‘, detail_contents, re.S)
    if movie_urls:
        movie_url = movie_urls[0]
        if movie_url.endswith(‘mp4‘):
            yield movie_url

def download(movie_url):
    print(movie_url)
    try:
        response = requests.get(movie_url,
                                )
        if response.status_code == 200:
            data = response.content
            m = hashlib.md5()
            m.update(str(time.time()).encode(‘utf-8‘))
            m.update(movie_url.encode(‘utf-8‘))
            filepath = os.path.join(DOWLOAD_PATH, ‘%s.mp4‘ % m.hexdigest())
            with open(filepath, ‘wb‘) as f:
                f.write(data)
                f.flush()
                print(‘下载成功‘, movie_url)
    except Exception:
        pass

def main():
    raw_url = ‘http://www.xiaohuar.com/list-3-{page_num}.html‘
    for i in range(5):
        index_url = raw_url.format(page_num=i)
        index_contents = get_page(index_url)
        detail_urls = parse_index(index_contents)

        for detail_url in detail_urls:
            detail_contents = get_page(detail_url)
            movie_urls = parse_detail(detail_contents)

            for movie_url in movie_urls:
                download(movie_url)

if __name__ == ‘__main__‘:
    main()

注：D盘要创建一个Downloads文件夹

线程池版

import requests
import re
import os
import hashlib
import time
from concurrent.futures import ThreadPoolExecutor

pool = ThreadPoolExecutor(50)
DOWLOAD_PATH = r‘D:\Downloads‘

def get_page(url):
    try:
        response = requests.get(url, )
        if response.status_code == 200:
            return response.text
    except Exception:
        pass

def parse_index(index_contents):
    index_contents = index_contents.result()
    detail_urls = re.findall(‘class="items".*?href="(.*?)"‘, index_contents, re.S)
    for detail_url in detail_urls:
        if not detail_url.startswith(‘http‘):
            detail_url = ‘http://www.xiaohuar.com‘ + detail_url
        pool.submit(get_page, detail_url).add_done_callback(parse_detail)

def parse_detail(detail_contents):
    detail_contents = detail_contents.result()
    movie_urls = re.findall(‘id="media".*?src="(.*?)"‘, detail_contents, re.S)
    if movie_urls:
        movie_url = movie_urls[0]
        if movie_url.endswith(‘mp4‘):
            pool.submit(download, movie_url)

def download(movie_url):
    try:
        response = requests.get(movie_url,
                                )
        if response.status_code == 200:
            data = response.content
            m = hashlib.md5()
            m.update(str(time.time()).encode(‘utf-8‘))
            m.update(movie_url.encode(‘utf-8‘))
            filepath = os.path.join(DOWLOAD_PATH, ‘%s.mp4‘ % m.hexdigest())
            with open(filepath, ‘wb‘) as f:
                f.write(data)
                f.flush()
                print(‘下载成功‘, movie_url)
    except Exception:
        pass

def main():
    raw_url = ‘http://www.xiaohuar.com/list-3-{page_num}.html‘
    for i in range(5):
        index_url = raw_url.format(page_num=i)
        pool.submit(get_page, index_url).add_done_callback(parse_index)

if __name__ == ‘__main__‘:
    main()

参考博客：

http://www.zhidaow.com/post/python-requests-install-and-brief-introduction

http://blog.csdn.net/shanzhizi/article/details/50903748

原文地址：https://www.cnblogs.com/0bug/p/8252929.html