Python~Day4
爬取豆瓣top250电影：
import requests
import re
url = 'https://movie.douban.com/top250'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
}
index = 0
while index < 10:
number=25 * index
response = requests.get(url, headers=headers,params={"start":number})
movie_content_list = re.findall(
'<div class="item">.*?href="(.*?)">.*?src="(.*?)".*?<span class="title">(.*?)</span>.*?<p class="">(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*? <span>(.*?)人评价.*?<span class="inq">(.*?)</span>',response.text, re.S)
for movie_content in movie_content_list:
detail_url, movie_jpg, name,detail_info, point, num ,slogan = movie_content
data = f'电影名称:{name}, 详情页url:{detail_url}, 图片url:{movie_jpg}, 电影详情信息:{detail_info}, 评分: {point}, 评价人数: {num} 宣传标语：{slogan} \n'
print(data)
with open('douban.txt', 'a', encoding='utf-8') as f:
f.write(data)
index +=1
课堂笔记：
爬虫原理：
什么是爬虫？
爬虫指的是爬取数据
什么是互联网？
由一堆网络设备把一台一台的计算机互联到一起
互联网建立的目的？
数据的传递与数据的共享、
上网的全过程：
- 普通用户
打开浏览器 --> 往目标站点发送请求 --> 接受响应数据 --> 渲染到页面上
- 爬虫程序
模拟浏览器 --> 往目标站点发送数据 --> 接受响应数据 --> 提取有用的数据 -->
浏览器发送的是什么请求？
http协议的请求？
- 请求url
- 请求方式：
GET.POST
-请求头：
cookies
user-agent
host
爬虫的全过程：
1.发送请求（请求库）
- requests模块
- selenium模块
2.获取相应数据（服务器返回）
3.解析并提取数据（解析库）
- bs4(BeautifulSoup4)
- Xpath
4.保存数据（存储库）
- MongoDB
(1.3.4 需要手动写)
- 爬虫框架：
Scrapy（基于面向对象）
爬取梨视频：
1.分析网站的视频源地址
2.通过requests网视频源地址发送请求
3.获取视频的二进制流，并保存到本地
'''
'''
今日内容：
requests模块
'''
# 爬取梨视频
'''
使用Chrome浏览器
'''
'''
请求url:
https://www.pearvideo.com/
请求方式：
GET
请求头：
user-agent:Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36
'''
# import requests
# import re #正则模块
#
# # 对梨视频详情页发送请求，获取响应请求
# response = requests.get(url='https://www.pearvideo.com/')
# print(response.status_code)
# print(response.text)
#
# # refindall('正则匹配规则'，'解析文本'，'正则模式')
# # re.S:全局模式（对整个文本进行匹配）
# # .指的是当前位置
# # *指的是查找所以
# '''
# <a href="video_(.*?)" #提取后面数字
# '''
# res = re.findall('<a href="video_(.*?)"', response.text, re.S)
# print(res)
#
# for m_id in res:
# # 拼接详情页url
# detail_url = 'https://www.pearvideo.com/video_' + m_id
# print(detail_url)
import requests
import re #正则模块
import uuid
# 爬虫三部曲
# 1.发送请求
def get_page(url):
response = requests.get(url)
return response
# 2.解析数据
# 解析主页获取视频详情页ID
def parse_index(text):
res = re.findall('<a href="video_(.*?)"', text, re.S)
print(res)
detail_url_list = []
for m_id in res:
# 拼接详情页url
detail_url = 'https://www.pearvideo.com/video_' + m_id
# print(detail_url)
detail_url_list.append(detail_url)
return detail_url_list
# refindall('正则匹配规则'，'解析文本'，'正则模式')
# re.S:全局模式（对整个文本进行匹配）
# .指的是当前位置
# *指的是查找所以
'''
<a href="video_(.*?)" #提取后面数字
'''
def parse_detail(text):
'''
(.*?):提取括号的内容
.*?:直接匹配
<video webkit-playsinline="" playsinline="" x-webkit-airplay="" autoplay="autoplay" src="https://video.pearvideo.com/mp4/adshort/20190613/cont-1566066-14015478_adpkg-ad_hd.mp4" style="width: 100%; height: 100%;"></video>
正则：<video.*?src="(.*?)"
正则：srcUrl="(.*?)"
'''
movie_url = re.findall('srcUrl="(.*?)"',text,re.S)[0]
return movie_url
def save_movie(movie_url):
response = requests.get(movie_url)
with open(f'{uuid.uuid4()}.mp4','wb') as f:
f.write(response .content)
f.flush()
if __name__ == '__main__':
# 1.对主页发送请求
index_res = get_page(url='https://www.pearvideo.com/')
# 2.对主页额进行解析、获取详情页id
detail_url_list = parse_index(index_res.text)
# print(detail_url_list)
# 3.对每个详情页url发送请求
for detail_url in detail_url_list:
detail_res = get_page(url=detail_url)
# print(detail_res.text)
# 4. 解析详情页获取视频url
movie_url=parse_detail(detail_res.text)
print(movie_url)
# 5.保存视频
save_movie(movie_url)
import requests
import re # 正则模块
# uuid.uuid4() 可以根据时间戳生成一段世界上唯一的随机字符串
import uuid
# 导入线程池模块
from concurrent.futures import ThreadPoolExecutor
# 线程池限制50个线程
pool = ThreadPoolExecutor(50)
# 爬虫三部曲
# 1.发送请求
def get_page(url):
print(f'开始异步任务：{url}')
response = requests.get(url)
return response
# 2.解析数据
# 解析主页获取视频详情页ID
def parse_index(res):
response = res.result()
# 提取出主页所有ID
id_list = re.findall('<a href="video_(.*?)"',response.text, re.S)
# print(res)
for m_id in id_list:
# 拼接详情页url
detail_url = 'https://www.pearvideo.com/video_' + m_id
# print(detail_url)
#把详情页url提交给get_page函数
pool.submit(get_page,detail_url).add_done_callback(parse_detail)
# refindall('正则匹配规则'，'解析文本'，'正则模式')
# re.S:全局模式（对整个文本进行匹配）
# .指的是当前位置
# *指的是查找所以
'''
<a href="video_(.*?)" #提取后面数字
'''
# 解析详情页获取视频url
def parse_detail(res):
response = res.result()
movie_url = re.findall('srcUrl="(.*?)"', response.text, re.S)[0]
# 异步提交把视频url传给get_page函数，把返回的结果传给save_movie
pool.submit(get_page,movie_url).add_done_callback(save_movie)
# 3.保存数据
def save_movie(res):
movie_res = res.result()
# 把视频写到本地
with open(f'{uuid.uuid4()}.mp4', 'wb') as f:
f.write(movie_res.content)
print(f'视频下载结束：{movie_res.url}')
f.flush()
if __name__ == '__main__':
# 1.往get_page发送异步请求，把结果交给parse_index函数
url='https://www.pearvideo.com/'
pool.submit(get_page,url).add_done_callback(parse_index)
# requests详细使用
'''
访问知乎发现
请求url：https://www.zhihu.com/explore
请求方式：GET
请求头：
user-agent:Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36
'''
# # 访问知乎
# import requests
# response = requests.get(url='https://www.zhihu.com/explore')
# print(response.status_code) #400
# print(response.text) # 返回错误页面
#
# #携带请求头参数访问知乎
# # 携带请求头字典
# headers = {
# 'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36'
# }
#
# # 在get请求内，添加user-agent
# response = requests.get(url='https://www.zhihu.com/explore',headers=headers)
# print(response.status_code)
# with open('zhihu.html','w',encoding='utf-8') as f:
# f.write(response.text)
'''
params参数
访问百度搜索蔡徐坤url
'''
# import requests
# from urllib.parse import urlencode
# # url = 'https://www.baidu.com/s?wd=%E8%94%A1%E5%BE%90%E5%9D%A4'
# # url = 'https://www.baidu.com/s?' + urlencode({"wd":蔡徐坤})
# url = 'https://www.baidu.com/s?'
# headers = {
# 'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36'
# }
# #print(url)
#
# # 在get方法中添加params参数
# # response = requests.get(url,headers=headers,params={"wd":'安徽工程大学'})
# response = requests.get(url,headers=headers,params={"wd":"安徽工程大学","pn":'20'})
# # print(response.text)
# with open('ahpu.html','w',encoding='utf-8') as f:
# f.write(response.text)
'''
携带cookies
携带登录cookies破解GitHub登录验证
请求url: https://github.com/settings/emails
请求方式：
GET
请求头：
user-agent
Cookie:has_recent_activity=1; _ga=GA1.2.637317055.1560497549; tz=Asia%2FShanghai; _octo=GH1.1.1390785586.1560497554; _device_id=ca2487362e89d9b8b40e3c55105f19d8; user_session=aRhxdrD1JIMG-svN8QAwtIHs5_NSRZI0Ajtp10FnKOi-IUmv; __Host-user_session_same_site=aRhxdrD1JIMG-svN8QAwtIHs5_NSRZI0Ajtp10FnKOi-IUmv; logged_in=yes; dotcom_user=lyj68; _gh_sess=OW9aaXVQbG1wY3JMWFhWdlg0MlVMSm5nZjlCQ250QnVNWHhUYU9ybHloem45OG1leFArQXc0SUttcnE2M3lvT3gvckVZVThtVXRQTnZjbGFNenF0YUxjZHNwdUlIeHhuQ2V2Q2xEOTFqaDFpNnhDNEJwNzFOQXNvcUdSN1FrYVNGUXpNMUZFWVd2aE56OSthd2dkMmQwVEp3M0E1Q21YQ2hjelRGMndkQ1NpcWJidExMb0tEL0NuQU9ZNmtYNkRNSjBpaC80b0FVc05yVmlEbkV3VUhKL3IrN2dHak9RR1ZVVFNTZU1YU1RWUlVDMVdkYklWUjRYU3A0NExOb2NEMnI0YlJheHg5enBGdzdMQmtYZThnVkFHM2ltcjFPS3ovVEdLZnVyUzNkeUk9LS1oSFdnK1R3R0JkRmJ6VGZoRW5TNVBRPT0%3D--067d19150a40df9a4afc9a0cd26e87624f41d623
'''
# import requests
#
# # 请求url
# url = 'https://github.com/settings/emails'
#
# # 请求头
# headers = {
# 'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36',
# 'Cookie':'has_recent_activity=1; _ga=GA1.2.637317055.1560497549; tz=Asia%2FShanghai; _octo=GH1.1.1390785586.1560497554; _device_id=ca2487362e89d9b8b40e3c55105f19d8; user_session=aRhxdrD1JIMG-svN8QAwtIHs5_NSRZI0Ajtp10FnKOi-IUmv; __Host-user_session_same_site=aRhxdrD1JIMG-svN8QAwtIHs5_NSRZI0Ajtp10FnKOi-IUmv; logged_in=yes; dotcom_user=lyj68; _gh_sess=OW9aaXVQbG1wY3JMWFhWdlg0MlVMSm5nZjlCQ250QnVNWHhUYU9ybHloem45OG1leFArQXc0SUttcnE2M3lvT3gvckVZVThtVXRQTnZjbGFNenF0YUxjZHNwdUlIeHhuQ2V2Q2xEOTFqaDFpNnhDNEJwNzFOQXNvcUdSN1FrYVNGUXpNMUZFWVd2aE56OSthd2dkMmQwVEp3M0E1Q21YQ2hjelRGMndkQ1NpcWJidExMb0tEL0NuQU9ZNmtYNkRNSjBpaC80b0FVc05yVmlEbkV3VUhKL3IrN2dHak9RR1ZVVFNTZU1YU1RWUlVDMVdkYklWUjRYU3A0NExOb2NEMnI0YlJheHg5enBGdzdMQmtYZThnVkFHM2ltcjFPS3ovVEdLZnVyUzNkeUk9LS1oSFdnK1R3R0JkRmJ6VGZoRW5TNVBRPT0%3D--067d19150a40df9a4afc9a0cd26e87624f41d623'
# }
#
# github_res= requests.get(url,headers=headers)
import requests
url = 'https://github.com/settings/emails'
headers = {
'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.80 Safari/537.36'}
cookie = {
'Cookie':'has_recent_activity=1; _ga=GA1.2.637317055.1560497549; tz=Asia%2FShanghai; _octo=GH1.1.1390785586.1560497554; _device_id=ca2487362e89d9b8b40e3c55105f19d8; user_session=aRhxdrD1JIMG-svN8QAwtIHs5_NSRZI0Ajtp10FnKOi-IUmv; __Host-user_session_same_site=aRhxdrD1JIMG-svN8QAwtIHs5_NSRZI0Ajtp10FnKOi-IUmv; logged_in=yes; dotcom_user=lyj68; _gh_sess=OW9aaXVQbG1wY3JMWFhWdlg0MlVMSm5nZjlCQ250QnVNWHhUYU9ybHloem45OG1leFArQXc0SUttcnE2M3lvT3gvckVZVThtVXRQTnZjbGFNenF0YUxjZHNwdUlIeHhuQ2V2Q2xEOTFqaDFpNnhDNEJwNzFOQXNvcUdSN1FrYVNGUXpNMUZFWVd2aE56OSthd2dkMmQwVEp3M0E1Q21YQ2hjelRGMndkQ1NpcWJidExMb0tEL0NuQU9ZNmtYNkRNSjBpaC80b0FVc05yVmlEbkV3VUhKL3IrN2dHak9RR1ZVVFNTZU1YU1RWUlVDMVdkYklWUjRYU3A0NExOb2NEMnI0YlJheHg5enBGdzdMQmtYZThnVkFHM2ltcjFPS3ovVEdLZnVyUzNkeUk9LS1oSFdnK1R3R0JkRmJ6VGZoRW5TNVBRPT0%3D--067d19150a40df9a4afc9a0cd26e87624f41d623'
}
github_res = requests.get(url,headers=headers,cookies=cookie)
print("540335019" in github_res.text)
''''''
'''
主页:
https://movie.douban.com/top250
GET
User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36
re正则:
# 电影详情页url、图片链接、电影名称、电影评分、评价人数
<div class="item">.*?href="(.*?)">.*?src="(.*?)".*?<span class="title">(.*?)</span>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价
'''
import requests
import re
url = 'https://movie.douban.com/top250'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
}
# 1、往豆瓣TOP250发送请求获取响应数据
response = requests.get(url, headers=headers)
# print(response.text)
# 2、通过正则解析提取数据
# 电影详情页url、图片链接、电影名称、电影评分、评价人数
movie_content_list = re.findall(
# 正则规则
'<div class="item">.*?href="(.*?)">.*?src="(.*?)".*?<span class="title">(.*?)</span>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价',
# 解析文本
response.text,
# 匹配模式
re.S)
for movie_content in movie_content_list:
# 解压赋值每一部电影
detail_url, movie_jpg, name, point, num = movie_content
data = f'电影名称:{name}, 详情页url:{detail_url}, 图片url:{movie_jpg}, 评分: {point}, 评价人数: {num} \n'
print(data)
# 3、保存数据，把电影信息写入文件中
with open('douban.txt', 'a', encoding='utf-8') as f:
f.write(data)
浙公网安备 33010602011771号