# get请求
# 获取豆瓣电影的第一页的数据 并且保存起来
import urllib.request
url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=0&limit=20'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}
# (1) 请求对象的定制
request = urllib.request.Request(url=url,headers=headers)
# (2)获取响应的数据
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
# (3) 数据下载到本地
# open方法默认情况下使用的是gbk的编码 如果我们要想保存汉字 那么需要在open方法中指定编码格式为utf-8
# encoding = 'utf-8'
# fp = open('douban.json','w',encoding='utf-8')
# fp.write(content)
# 这里需要记得关闭文件,with方法就是自动关闭
with open('douban1.json','w',encoding='utf-8') as fp:
fp.write(content)
注意:
1. 数据换行:ctrl + alt + L
2. open方法默认情况下使用的是gbk的编码 如果我们要想保存汉字 那么需要在open方法中指定编码格式为utf-8、 encoding = 'utf-8'
思路:
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=0&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=20&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=40&limit=20
# https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&
# start=60&limit=20
# page 1 2 3 4
# start 0 20 40 60
# start (page - 1)*20
# 下载豆瓣电影前10页的数据
# (1) 请求对象的定制
# (2) 获取响应的数据
# (3) 下载数据
import urllib.parse
import urllib.request
def create_request(page):
base_url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&'
# 拼接数据
data = {
'start':(page - 1) * 20,
'limit':20
}
data = urllib.parse.urlencode(data)
url = base_url + data
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}
request = urllib.request.Request(url=url,headers=headers)
return request
def get_content(request):
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
return content
def down_load(page,content):
with open('douban_' + str(page) + '.json','w',encoding='utf-8')as fp:
fp.write(content)
# 程序的入口
if __name__ == '__main__':
# 这里将字符串转换为整型
start_page = int(input('请输入起始的页码'))
end_page = int(input('请输入结束的页面'))
for page in range(start_page,end_page+1):
# 每一页都有自己的请求对象的定制
request = create_request(page)
# 获取响应的数据
content = get_content(request)
# 下载
down_load(page,content)
思路:
注意:
1. Ajax - 懒加载
2. 如果跟 + 连接,前后数据必须一样(需要加强制类型转化)
# 1页
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
# post
# cname: 北京
# pid:
# pageIndex: 1
# pageSize: 10
# 2页
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
# post
# cname: 北京
# pid:
# pageIndex: 2
# pageSize: 10
import urllib.request
import urllib.parse
def create_request(page):
base_url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname'
data = {
'cname': '北京',
'pid':'',
'pageIndex': page,
'pageSize': '10'
}
data = urllib.parse.urlencode(data).encode('utf-8')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}
request = urllib.request.Request(url=base_url,headers=headers,data=data)
return request
def get_content(request):
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
return content
def down_load(page,content):
with open('kfc_' + str(page) + '.json','w',encoding='utf-8')as fp:
fp.write(content)
if __name__ == '__main__':
start_page = int(input('请输入起始页码'))
end_page = int(input('请输入结束页码'))
for page in range(start_page,end_page+1):
# 请求对象的定制
request = create_request(page)
# 获取网页源码
content = get_content(request)
# 下载
down_load(page,content)
思路:
注意:
1. post 请求,必须要编码
各位路过的朋友,如果觉得可以学到些什么的话,点个赞再走吧,欢迎各位路过的大佬评论,指正错误,也欢迎有问题的小伙伴评论留言.