爬虫-requests用法

中文文档 API： http://requests.kennethreitz.org/zh_CN/latest/

安装

pip install requests

获取网页

# coding=utf-8
import requests

response = requests.get('http://www.baidu.com')

# 第一种方式 获取响应内容
# 查看网页编码方式
print(response.encoding)
# 修改编码方式
response.encoding = 'utf-8'
# 获取响应内容
print(response.text)

# 第二种方式 获取二进制响应内容

# 获取二进制响应内容
print(response.content)
# 解码 decode('解码方式') 默认时utf-8的方式
print(response.content.decode())# coding=utf-8
import requests

response = requests.get('http://www.baidu.com')

# 第一种方式 获取响应内容
# 查看网页编码方式
print(response.encoding)
# 修改编码方式
response.encoding = 'utf-8'
# 获取响应内容
print(response.text)

# 第二种方式 获取二进制响应内容

# 获取二进制响应内容
print(response.content)
# 解码 decode('解码方式') 默认时utf-8的方式
print(response.content.decode())

保存图片

import requests

response = requests.get('http://requests.kennethreitz.org/zh_CN/latest/_static/requests-sidebar.png')
# 保存图片
with open('a.png','wb') as f:
    f.write(response.content)

获取状态码以及判断请求是否成功

import requests
r = requests.get('http://www.baidu.com')
# 获取状态码
print(r.status_code)  # 获取到200不一定成功 可能获取的时跳转之后的页码
# 断言 判断请求是否成功
assert r.status_code==200  # 如果成功 没有任何反应 失败会报错

# 获取响应header
print(r.headers)
# 获取请求header
print(r.request.headers)

# 获取请求url
print(r.request.url)
# 获取响应的url
print(r.url)

带header头伪装浏览器爬取内容

import requests
# 模拟header头
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'}
# 获取网页
r = requests.get('http://www.baidu.com',headers=headers)
# 获取响应内容
print(r.text)

爬取贴吧内容

import requests

class WebSpider():
    def __init__(self, name):
        self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'}
        self.url_temp = "http://tieba.baidu.com/f?kw="+ name +"&ie=utf-8&pn={}"
        self.name = name

    # 构建地址列表
    def get_url_list(self):
        return [self.url_temp.format(i*50) for i in range(1000)]

    # 获取贴吧内容
    def parse_url(self, url):  #爬取数据
        print(url)
        r = requests.get(url, headers=self.headers)
        return r.content.decode()

    def run(self):
        # 获取地址列表
        urls = self.get_url_list()
        # 遍历 爬取数据
        for url in urls:
            html_str = self.parse_url(url)
            # 保存
            page_num = urls.index(url)+1  # 获取也码数
            file_name =  self.name + "第{}页.html".format(page_num)
            with open(file_name, "w", encoding="utf-8") as f:
                f.write(html_str)
if __name__ == '__main__':
    r = WebSpider(input("请输入贴吧名字："))
    r.run()

使用代理

import requests

headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36"}
# 使用代理池 {协议：网址1和端口1, 协议：网址2和端口2}
proxies =  {
    "http":"http://39.137.69.8:80",
    "http":"http://111.29.3.184:80"
}
r = requests.get("http://www.baidu.com", headers=headers, proxies=proxies)
print(r.status_code)  # 查看是否成功

POST请求

# coding=utf-8
import requests
import sys

class BiyingFanyi(object):
    def __init__(self, trans_str):
        self.trans_str = trans_str
        self.headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36"}
        self.url = "https://cn.bing.com/ttranslatev3?isVertical=1&&IG=1A4E692C98A4412BA37107204839D81C&IID=translator.5032.4"

    def parse_url(self, url, data):
        response = requests.post(url, data=data, headers=self.headers)
        data = list(eval(response.content.decode()))  # [{},{}] 把类似列表的字符串转化为列表
        return data

    def run(self):
        # 获取翻译的语言类型
        #     请求地址
        lang_data = {"text":self.trans_str,
                     "fromLang": "auto - detect",
                     "to": "en"
                     }
        #     请求数据
        lang= self.parse_url(self.url, lang_data)
        #     获取lang
        fromLang = lang[0]["detectedLanguage"]["language"]
        # post请求数据
        trans_data = {"text":self.trans_str,"fromLang": "zh-Hans","to": "en"} if fromLang == 'zh-Hans' else \
                        {"text": self.trans_str, "fromLang": "en", "to": "zh-Hans"}  # 三元运算符

        # 获取相应内容
        trans_str = self.parse_url(self.url, trans_data)
        trans = trans_str[0]["translations"][0]["text"]
        print(trans)

if __name__ == '__main__':
    trans_str = sys.argv[1]  # 启动该文件时加参数
    fanyi = BiyingFanyi(trans_str)
    fanyi.run()

这样再终端调用的时候直接输入要翻译的数据

这种方法有点长 可以给文件起别名

找到.bashrc文件 vi ~/.bashrc在最下面添加

启动下bashrc文件

使用别名运行

使用cookie得三种方式

1，登录账号保存到session里

# coding=utf-8
import requests

# 实例化一个session对象
session = requests.session()
# 请求网址
post_url = "http://www.renren.com/PLogin.do"
# 人人网账号和密码
post_data = {"email":"18656******", "password":"qw******"}
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36"}
# 使用session发送post请求,cookie保存在其中
session.post(post_url, data=post_data, headers=headers)
# 在使用session进行请求登陆后才能访问的地址
r = session.get("http://www.renren.com/972533172/newsfeed/photo", headers=headers)
# 保存页面
with open('renren1.html', "w", encoding="utf-8") as f:
    f.write(r.content.decode())

2.Cookie放入请求头

# coding=utf-8
import requests

headers = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36",
    "Cookie":"anonymid=jso2jqr9-ua7yx8; _r01_=1; XNESSESSIONID=196ea2cc9d76; depovince=GW; jebecookies=d90c5751-c3f3-486e-a72c-745450b49686|||||; ick_login=5826e3f3-931a-4fef-ba96-44bbf4002755; _de=1F357FAF1F9FBA7F803C7095955979B8; p=4dc77dc5f602d42c37e075914279d3bc2; first_login_flag=1; ln_uact=18656711411; ln_hurl=http://head.xiaonei.com/photos/0/0/men_main.gif; t=e0a9e51796415e5018a3adee3ea84a0b2; societyguester=e0a9e51796415e5018a3adee3ea84a0b2; id=972533172; xnsid=e7f4f06; ver=7.0; loginfrom=null; jebe_key=9d0aeb38-53ed-4f12-9bb6-c37611fbe84b%7C44bfbc433568681820735e4eb5dfc039%7C1571714808839%7C1%7C1571714811980; wpsid=15257123636357; wp_fold=0"
}
r = requests.get("http://www.renren.com/972533172/newsfeed/photo", headers=headers)
with open("renren2.html", "w", encoding="utf-8") as f:
    f.write(r.content.decode())

3.设置cookies字典

# coding=utf-8
import requests

headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.80 Safari/537.36"}
cookie = "anonymid=jso2jqr9-ua7yx8; _r01_=1; XNESSESSIONID=196ea2cc9d76; depovince=GW; jebecookies=d90c5751-c3f3-486e-a72c-745450b49686|||||; ick_login=5826e3f3-931a-4fef-ba96-44bbf4002755; _de=1F357FAF1F9FBA7F803C7095955979B8; p=4dc77dc5f602d42c37e075914279d3bc2; first_login_flag=1; ln_uact=18656711411; ln_hurl=http://head.xiaonei.com/photos/0/0/men_main.gif; t=e0a9e51796415e5018a3adee3ea84a0b2; societyguester=e0a9e51796415e5018a3adee3ea84a0b2; id=972533172; xnsid=e7f4f06; ver=7.0; loginfrom=null; jebe_key=9d0aeb38-53ed-4f12-9bb6-c37611fbe84b%7C44bfbc433568681820735e4eb5dfc039%7C1571714808839%7C1%7C1571714811980; wpsid=15257123636357; wp_fold=0"
Cookies = {i.split('=')[0]:i.split('=')[1] for i in cookie.split("; ")}  # 字典推导式
r = requests.get("http://www.renren.com/972533172/newsfeed/photo", headers=headers, cookies=Cookies)
with open("renren3.html", "w", encoding="utf-8") as f:
    f.write(r.content.decode())

抓包 寻找登录的url地址

勾选perserve log按钮 防止页面跳转找不到url地址

寻找参数时，需要多点几次，看参数变化不

定位js

1.选择会触发js事件得按钮，点击Event listeners,同时formwork listeners打勾，找到js的位置

点击js

想看得js效果可以在console里直接复制进去

断点调试，点击js对应得行号

再点击次登录按钮进入调试状态

2.查找请求的地址

复制请求地址或关键字点search

搜索复制的地址或关键字

requests其它小技巧

把响应数据里的cookie对象转换成字典

把字典转换成响应数据里的cookie对象

requests.utils.cookiejar_from_dict({'BDORZ': ''}

url解码

requests.utils.unquote("http://tieba.baidu.com/f?kw=%E6%9D%A8%E6%B4%8B")

url编码

requests.utils.quote('http://tieba.baidu.com/f?kw=杨洋')

请求SSL证书验证

response = requests.get("https://www.12306.cn/mormhweb/ ", verify=False)

添加超时参数

response = requests.get(url,timeout=10)

配合状态码判断是否请求成功

assert response.status_code == 200