day9
昨日作业：
'''
主页:
图标地址、下载次数、大小、详情页地址
主页:
图标地址、下载次数、大小、详情页地址
详情页:
游戏名、好评率、评论数、小编点评、下载地址、简介、网友评论、1-5张截图链接地址、
https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=1&ctoken=FRsWKgWBqMBZLdxLaK4iem9B
游戏名、好评率、评论数、小编点评、下载地址、简介、网友评论、1-5张截图链接地址、
https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=1&ctoken=FRsWKgWBqMBZLdxLaK4iem9B
https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=2&ctoken=FRsWKgWBqMBZLdxLaK4iem9B
https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page=3&ctoken=FRsWKgWBqMBZLdxLaK4iem9B
32
'''
import requests
from bs4 import BeautifulSoup
from pymongo import MongoClient
'''
3、把豌豆荚爬取的数据插入mongoDB中
- 创建一个wandoujia库
- 把主页的数据存放一个名为index集合中
- 把详情页的数据存放一个名为detail集合中
'''
# 连接MongoDB客户端
client = MongoClient('localhost', 27017)
# 创建或选择wandoujia库，index集合
index_col = client['wandoujia']['index']
# 创建或选择wandoujia库，detail集合
detail_col = client['wandoujia']['detail']
'''
import requests
from bs4 import BeautifulSoup
from pymongo import MongoClient
'''
3、把豌豆荚爬取的数据插入mongoDB中
- 创建一个wandoujia库
- 把主页的数据存放一个名为index集合中
- 把详情页的数据存放一个名为detail集合中
'''
# 连接MongoDB客户端
client = MongoClient('localhost', 27017)
# 创建或选择wandoujia库，index集合
index_col = client['wandoujia']['index']
# 创建或选择wandoujia库，detail集合
detail_col = client['wandoujia']['detail']
# 1、发送请求
def get_page(url):
response = requests.get(url)
return response
def get_page(url):
response = requests.get(url)
return response
# 2、开始解析
# 解析详情页
def parse_detail(text):
soup = BeautifulSoup(text, 'lxml')
# print(soup)
# print(soup)
# app名称
try:
name = soup.find(name="span", attrs={"class": "title"}).text
except Exception:
# 若有异常，设置为None
name = None
# print(name)
try:
name = soup.find(name="span", attrs={"class": "title"}).text
except Exception:
# 若有异常，设置为None
name = None
# print(name)
# 好评率
try:
love = soup.find(name='span', attrs={"class": "love"}).text
try:
love = soup.find(name='span', attrs={"class": "love"}).text
except Exception:
love = None
# print(love)
love = None
# print(love)
# 评论数
try:
commit_num = soup.find(name='a', attrs={"class": "comment-open"}).text
except Exception:
commit_num = None
# print(commit_num)
try:
commit_num = soup.find(name='a', attrs={"class": "comment-open"}).text
except Exception:
commit_num = None
# print(commit_num)
# 小编点评
try:
commit_content = soup.find(name='div', attrs={"class": "con"}).text
except Exception:
commit_content = None
# print(commit_content)
try:
commit_content = soup.find(name='div', attrs={"class": "con"}).text
except Exception:
commit_content = None
# print(commit_content)
# app下载链接
try:
download_url = soup.find(name='a', attrs={"class": "normal-dl-btn"}).attrs['href']
except Exception:
# 若有异常，设置为None
download_url = None
download_url = soup.find(name='a', attrs={"class": "normal-dl-btn"}).attrs['href']
except Exception:
# 若有异常，设置为None
download_url = None
# print(download_url)
# print(
# f'''
# ============= tank ==============
# app名称:{name}
# 好评率: {love}
# 评论数: {commit_num}
# 小编点评: {commit_content}
# app下载链接: {download_url}
# ============= end ==============
# '''
# )
# f'''
# ============= tank ==============
# app名称:{name}
# 好评率: {love}
# 评论数: {commit_num}
# 小编点评: {commit_content}
# app下载链接: {download_url}
# ============= end ==============
# '''
# )
# 判断所有数据都存在，正常赋值
if name and love and commit_num and commit_content and download_url :
detail_data = {
'name': name,
'love': love,
'commit_num': commit_num,
'commit_content': commit_content,
'download_url': download_url
}
if name and love and commit_num and commit_content and download_url :
detail_data = {
'name': name,
'love': love,
'commit_num': commit_num,
'commit_content': commit_content,
'download_url': download_url
}
# 若love没有值，则设置为 没人点赞，很惨
if not love:
detail_data = {
'name': name,
'love': "没人点赞，很惨",
'commit_num': commit_num,
'commit_content': commit_content,
'download_url': download_url
}
# 若download_url没有值，则设置为 没有安装包
if not download_url:
detail_data = {
'name': name,
'love': love,
'commit_num': commit_num,
'commit_content': commit_content,
'download_url': '没有安装包'
}
if not love:
detail_data = {
'name': name,
'love': "没人点赞，很惨",
'commit_num': commit_num,
'commit_content': commit_content,
'download_url': download_url
}
# 若download_url没有值，则设置为 没有安装包
if not download_url:
detail_data = {
'name': name,
'love': love,
'commit_num': commit_num,
'commit_content': commit_content,
'download_url': '没有安装包'
}
# 插入详情页数据
detail_col.insert(detail_data)
print(f'{name}app数据插入成功!')
detail_col.insert(detail_data)
print(f'{name}app数据插入成功!')
# 解析主页
def parse_index(data):
soup = BeautifulSoup(data, 'lxml')
def parse_index(data):
soup = BeautifulSoup(data, 'lxml')
# 获取所有app的li标签
app_list = soup.find_all(name='li', attrs={"class": "card"})
for app in app_list:
# print(app)
# print('tank' * 1000)
# print('tank *' * 1000)
# print(app)
# 图标地址
# 获取第一个img标签中的data-original属性
img = app.find(name='img').attrs['data-original']
# print(img)
app_list = soup.find_all(name='li', attrs={"class": "card"})
for app in app_list:
# print(app)
# print('tank' * 1000)
# print('tank *' * 1000)
# print(app)
# 图标地址
# 获取第一个img标签中的data-original属性
img = app.find(name='img').attrs['data-original']
# print(img)
# 下载次数
# 获取class为install-count的span标签中的文本
down_num = app.find(name='span', attrs={"class": "install-count"}).text
# print(down_num)
# 获取class为install-count的span标签中的文本
down_num = app.find(name='span', attrs={"class": "install-count"}).text
# print(down_num)
import re
# 大小
# 根据文本正则获取到文本中包含 数字 + MB（\d+代表数字）的span标签中的文本
size = soup.find(name='span', text=re.compile("\d+MB")).text
# print(size)
# 大小
# 根据文本正则获取到文本中包含 数字 + MB（\d+代表数字）的span标签中的文本
size = soup.find(name='span', text=re.compile("\d+MB")).text
# print(size)
# 详情页地址
# 获取class为detail-check-btn的a标签中的href属性
# detail_url = soup.find(name='a', attrs={"class": "name"}).attrs['href']
# print(detail_url)
# 获取class为detail-check-btn的a标签中的href属性
# detail_url = soup.find(name='a', attrs={"class": "name"}).attrs['href']
# print(detail_url)
# 详情页地址
detail_url = app.find(name='a').attrs['href']
# print(detail_url)
detail_url = app.find(name='a').attrs['href']
# print(detail_url)
# 拼接数据
index_data = {
'img': img,
'down_num': down_num,
'size': size,
'detail_url': detail_url
}
index_data = {
'img': img,
'down_num': down_num,
'size': size,
'detail_url': detail_url
}
# 插入数据
index_col.insert(index_data)
print('主页数据插入成功!')
index_col.insert(index_data)
print('主页数据插入成功!')
# 3、往app详情页发送请求
response = get_page(detail_url)
response = get_page(detail_url)
# 4、解析app详情页
parse_detail(response.text)
parse_detail(response.text)
def main():
for line in range(1, 33):
url = f"https://www.wandoujia.com/wdjweb/api/category/more?catId=6001&subCatId=0&page={line}&ctoken=FRsWKgWBqMBZLdxLaK4iem9B"
# 1、往app接口发送请求
response = get_page(url)
# print(response.text)
print('*' * 1000)
# 反序列化为字典
data = response.json()
response = get_page(url)
# print(response.text)
print('*' * 1000)
# 反序列化为字典
data = response.json()
# 获取接口中app标签数据
app_li = data['data']['content']
# print(app_li)
app_li = data['data']['content']
# print(app_li)
# 2、解析app标签数据
parse_index(app_li)
parse_index(app_li)
# 执行完所有函数关闭mongoDB客户端
client.close()
client.close()
if __name__ == '__main__':
main()
main()
今日学习内容：
一 Scrapy爬虫框架
发送请求 ---> 获取响应数据 ---> 解析数据 ---> 保存数据
** Scarpy框架介绍 **
1、引擎(EGINE)
引擎负责控制系统所有组件之间的数据流，并在某些动作发生时触发事件。有关详细信息，请参见上面的数据流部分。
2、调度器(SCHEDULER)
用来接受引擎发过来的请求, 压入队列中, 并在引擎再次请求的时候返回. 可以想像成一个URL的优先级队列, 由它来决定下一个要抓取的网址是什么, 同时去除重复的网址
3、下载器(DOWLOADER)
用于下载网页内容, 并将网页内容返回给EGINE，下载器是建立在twisted这个高效的异步模型上的
4、爬虫(SPIDERS)
SPIDERS是开发人员自定义的类，用来解析responses，并且提取items，或者发送新的请求
5、项目管道(ITEM PIPLINES)
在items被提取后负责处理它们，主要包括清理、验证、持久化（比如存到数据库）等操作
下载器中间件(Downloader Middlewares)位于Scrapy引擎和下载器之间，主要用来处理从EGINE传到DOWLOADER的请求request，已经从DOWNLOADER传到EGINE的响应response，
你可用该中间件做以下几件事：
(1) process a request just before it is sent to the Downloader (i.e. right before Scrapy sends the request to the website);
(2) change received response before passing it to a spider;
(3) send a new Request instead of passing received response to a spider;
(4) pass response to a spider without fetching a web page;
(5) silently drop some requests.
6、爬虫中间件(Spider Middlewares)
位于EGINE和SPIDERS之间，主要工作是处理SPIDERS的输入（即responses）和输出（即requests）
** Scarpy安装 **
1、pip3 install wheel
2、pip3 install lxml
3、pip3 install pyopenssl
4、pip3 install pypiwin32
5、安装twisted框架
下载twisted
http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted
安装下载好的twisted
pip3 install 下载目录\Twisted-17.9.0-cp36-cp36m-win_amd64.whl
6、pip3 install scrapy
** Scarpy使用 **
1、进入终端cmd
- scrapy
C:\Users\administortra>scrapy
Scrapy 1.6.0 - no active project
2、创建scrapy项目
1.创建一个文件夹，专门用于存放scrapy项目
- D:\Scrapy_prject
2.cmd终端输入命令
scrapy startproject Spider_Project（ 项目名）
- 会在 D:\Scrapy_prject文件夹下会生成一个文件
Spider_Project : Scrapy项目文件
3.创建爬虫程序
cd Spider_Project # 切换到scrapy项目目录下
# 爬虫程序名称 目标网站域名
scrapy genspider baidu www.baidu.com # 创建爬虫程序
3、启动scrapy项目，执行爬虫程序
# 找到爬虫程序文件进行执行
scrapy runspider只能执行某个 爬虫程序.py
# 切换到爬虫程序执行文件目录下
- cd D:\Scrapy_prject\Spider_Project\Spider_Project\spiders
- scrapy runspider baidu.py
# 根据爬虫名称找到相应的爬虫程序执行
scrapy crawl 爬虫程序名称
# 切换到项目目录下
- cd D:\Scrapy_prject\Spider_Project
- scrapy crawl baidu
[console_scripts]
cftp = twisted.conch.scripts.cftp:run
ckeygen = twisted.conch.scripts.ckeygen:run
conch = twisted.conch.scripts.conch:run
mailmail = twisted.mail.scripts.mailmail:run
pyhtmlizer = twisted.scripts.htmlizer:run
tkconch = twisted.conch.scripts.tkconch:run
trial = twisted.scripts.trial:run
twist = twisted.application.twist._twist:Twist.main
twistd = twisted.scripts.twistd:run
ckeygen = twisted.conch.scripts.ckeygen:run
conch = twisted.conch.scripts.conch:run
mailmail = twisted.mail.scripts.mailmail:run
pyhtmlizer = twisted.scripts.htmlizer:run
tkconch = twisted.conch.scripts.tkconch:run
trial = twisted.scripts.trial:run
twist = twisted.application.twist._twist:Twist.main
twistd = twisted.scripts.twistd:run
