爬虫 request,正则,bs4

jupyter notebook
开启服务

• 爬虫: 经过编写程序,模拟浏览器上网,而后让其去互联网上爬取数据的过程.
• 爬虫的分类:
  • 通用爬虫:
  • 聚焦爬虫:
  • 增量式
• 反扒机制:

• 反反爬机制:
  -robots.txt 协议: 遵循或者不遵循.

• requests 模块代码编写的流程:
  • 指定url
  • 发起请求
  • 获取响应对象中的数据
  • 持久化存储

practice.py

import requests
#1
url = 'https://www.sogou.com'
#2.
response = requests.get(url=url)

#3
page_text =response.text

#4.
with open('./sougou.html','w',encoding='utf-8') as fp:
    fp.write(page_text)

需求: 爬取搜狗指定词条搜索后的页面数据

import requests
url = 'https://www.sogou.com/web'
# 封装函数
wd = input('enter a word:')
param = {
    'query': wd
}
response = requests.get(url=url, params=param)

page_text = response.content
fileName = wd + '.html'
with open(fileName, 'wb') as fp:
    fp.write(page_text)
    print('over')

爬取百度翻译结构

url = 'https://fanyi.baidu.com/sug'
wd = input('enter a word:')
data = {
    'kw': wd
}
response = requests.post(url=url,data=data)

print(response.json())

爬取豆瓣电影分类排行榜 https://move.douban.com/中的电影详情数据

url = 'https://movie.douban.com/j/chart/top_list'
params = {
    'type': '5',
    'interval_id': "100:90",
    'action': '',
    'start': '60',
    'limit': '100',
}

movie_data = requests.get(url=url,params=params).json()

print(movie_data)

需求: 爬取国家药品监督管理总局基于中华人民共和国化妆品生产学课程相关数据http://125.35.6.84:81/xk/

import requests
url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsList'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
id_list = []
for page in range(1,11):
    data = {
        "on": "true",
        "page": str(page),
        "pageSize": "15",
        "productName": "",
        "conditionType": "1",
        "applyname": "",
        "applysn": "",
    }
    json_data = requests.post(url=url,data=data,headers=headers).json()
    for dic in json_data['list']:
        id = dic['ID']
        id_list.append(id)
        
detail_url = 'http://125.35.6.84:81/xk/itownet/portalAction.do?method=getXkzsById'
for id in id_list:
    detail_data = {
        'id': id
    }
    detail_json = requests.post(url=detail_url,data=detail_data,headers=headers).json()
    print(detail_json)

爬取照片

url = 'https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1551785494&di=d9329f74ebdc5bd6158447daf4d5a783&imgtype=jpg&er=1&src=http%3A%2F%2Fimg.biaoche.org%2F%3Fimg%3D03.imgmini.eastday.com%2Fmobile%2F20180616%2F0e1faa7f78e9c172db3c73d0cc1be192_wmk.jpeg'
img_data =requests.get(url=url,headers=headers).content
with open('./xiaohua.jpg','wb') as fp:
    fp.write(img_data)
    
import urllib

url = 'https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1551191414490&di=8db3ee6e5b31215f03cf77e7deaa2077&imgtype=0&src=http%3A%2F%2F00imgmini.eastday.com%2Fmobile%2F20180918%2F20180918171154_1d58954e0491887b39e7122bdd1a9506_2.jpeg'
urllib.request.urlretrieve(url=url,filename='lulaoye.jpg')

正则

import re
string = '''fall in love with you
i love you very much
i love she
i love her
'''
re.findall('^i.*', string,re.M)
# re.M 匹配以后分多个
['i love you very much', 'i love she', 'i love her']


###########################################
# 匹配所有行
string1 = """细思极恐
你的队友在看书
你的敌人在磨刀
你的闺蜜在减肥
隔壁老王在练腰

"""
re.findall('.*',string1,re.S)
# re.s 匹配成一行
# ['细思极恐\n你的队友在看书\n你的敌人在磨刀\n你的闺蜜在减肥\n隔壁老王在练腰\n\n', '']

爬取糗事百科中全部的图片进行保存

import os
import re
import urllib
import requests


url = 'https://www.qiushibaike.com/pic/page/%d/?s=5170552'
# page = 1
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
if not os.path.exists('./qiutu'):
    os.mkdir('./qiutu')
    
start_page = int(input('enter a start pageNum:'))
end_page = int(input('enter a end pageNum:'))

for page in range(start_page,end_page+1):
    new_url = format(url%page)
#     print(new_url)
    page_text = requests.get(url=new_url,headers=headers).text
    img_url_list = re.findall('<div class="thumb">.*?<img src="(.*?)" alt=.*?</div>',page_text,re.S)
    for img_url in img_url_list:
        img_url = 'https:'+img_url
        imgName = img_url.split('/')[-1]
        imgPath = 'qiutu/'+imgName
        urllib.request.urlretrieve(url=img_url,filename=imgPath)
        print(imgPath,'下载成功!')
        
print('over!!!')

bs4的使用

• bs4解析: 1.pip install bs4
  2.pip install lxml
• 解析原理:
  • 1 将即将要进行解析的源码加载到bs对象
  • 2 调用bs对象中相关的方法或者属性进行源码中的相关标签的定位
  • 3 将定位到的标签纸巾存在的文本或者属性值获取

mport requests
from bs4 import BeautifulSoup

url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'
}
page_text = requests.get(url=url,headers=headers).text

soup = BeautifulSoup(page_text,'lxml')

a_list =soup.select('.book-mulu > ul > li > a')
fp = open('sanguo.txt','w',encoding='utf-8')
for a in a_list:
    title = a.string
    # string 是亲儿子 ,下面的文字
    detail_url = 'http://www.shicimingju.com' + a['href']
    detail_page_text = requests.get(url=detail_url,headers=headers).text
    
    soup = BeautifulSoup(detail_page_text,'lxml')
    content = soup.find('div',class_='chapter_content').text
    
    fp.write(title + '\n' + content)
    print(title,'下载完成')
print('over')
fp.close