requests

requests

requests模块在处理爬虫更加高效，快捷。

基于request发起get请求

• 需求：爬取搜狗首页的数据

import requests
# 1.指定url
url =  'https://www.sogou.com/'
#2发起get请求:get方法会返回请求成功的响应对象
response = requests.get(url=url)
#获取响应的数据：text可以获取响应对象中字符串形式的页面数据
page_data = response.text
#print(page_data)
# 4进行持久化存储
with open('./sougou.html','w',encoding='utf-8')as fp:
    fp.write(page_data)

response对象中其他重要属性

import requests
#指定url
url = 'https://www.sogou.com/'
#2发起get请求:get方法会返回请求成功的响应对象
response = requests.get(url=url)
#获取响应的数据：text可以获取响应对象中字符串形式的页面数据
# page_data = response.content # content 获取的是二进制数据
# print(page_data)

#返回响应状态码
print(response.status_code)

# 获取响应头信息
print(response.headers)

# 获取请求指定的url
print(response.url)

request模块如何处理带参数的get请求

• 方式一
需求：指定一个词条，获取搜狗搜索结果所对应的页面数据

import requests
url = 'https://www.sogou.com/web?query=周杰伦&ie=utf8' # 不需要编码中文
response = requests.get(url=url)
page_data = response.text
# print(page_data)
with open('./zhou.html','w',encoding='utf-8')as fp:
    fp.write(page_data)

• 方式二

import requests

url = 'https://www.sogou.com/web'
# 将参数封装到字典中
params =  {
    'query':'周杰伦',
    'ie':'utf-8'
}
response = requests.get(url=url,params=params)

response.status_code

print(response.text)

自定义请求头信息

import requests
url = 'https://www.sogou.com/web'
# 将参数封装到字典中
params =  {
    'query':'周杰伦',
    'ie':'utf-8'
}
# 自定义请求头信息
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'

}
response=requests.get(url=url,params=params,headers=headers)
print(response.status_code)

基于request发起post请求

- 登录豆瓣 获取登陆成功之后的页面数据

import requests
# url = 'https://accounts.douban.com/login'
url = "https://www.douban.com/accounts/login"
# 封装post请求的数据
data ={
    "sourse":"movie",
    "redir":"https://movie.douban.com/",
    "form_email":"15027900535",
    "form_password":"bobo@15027900535",
    "login":"登录"
}
# 自定义请求头信息
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'

}
#发起post请求
response=requests.post(url=url,data=data,headers=headers)
# 获取页面数据
page_text = response.text
# print(page_text)
# 持久化存储
with open('./douban.html','w',encoding='utf-8')as fp:
    fp.write(page_text)

基于ajax的get请求

• 需求：抓取豆瓣电影上电影详情的数据

import requests
url = 'https://movie.douban.com/j/chart/top_list?'

# 封装ajax数据
params={
    "type":"24",
    "interval_id":"100:90",
    "action":"",
    "start":"0", # 从哪里开始
    "limit":"10"  # 获取多少条数据
}
# 自定义请求头信息
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    
}
#发起post请求
response=requests.get(url=url,params=params,headers=headers)

# 获取页面数据
page_text = response.text
print(page_text)
with open('./douban1.html','w',encoding='GBK')as fp:  # 写入文件会出现乱码，而且是纯文本
    fp.write(page_text)
print('ok')

基于ajax的post请求

• 需求：爬取肯德基

import requests
url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'
data = {
    "cname":'',
    'pid':'',
    'keyword':'上海',
    'pageIndex':'1',
    'pageSize':'10'
}
response = requests.post(url=url,data=data)
print(response.text)

综合项目实战

- 需求：爬取搜狗知乎某一词条对应一定页码范围表示的页面数据

import requests
import os
# 创建一个文件夹
if not os.path.exists('./pages'):
    os.mkdir('./pages')
word = input('enter a key-word:')
start_num = int(input('enter start num:').strip())
end_num = int(input('enter end num:').strip())

url = 'http://zhihu.sogou.com/zhihu?'
# 自定义请求头信息
headers={
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
    
}
for page in range(start_num,end_num+1):
    params={
        'query':word,
        'ie':'utf-8',
        'page':page
    }
    response= requests.get(url=url,params=params,headers=headers)
    page_text = response.text
    file_name = word+str(page)+'.html'
    file_path='pages/'+file_name
    with open(file_path,'w',encoding='utf-8')as fp:
        fp.write(page_text)
        print('第%d页写入成功'%page)