爬虫入门（一）

1.jupyter的快捷键

插入cell: a(向上) b(向下)
删除: x
执行 ： shift+enter
tab：补全
cell模式切换：y，m
shift+tab：打开帮助文档

2.requests

requests模块编写代码的流程
1指定url
2发起请求
3获取相应对象中的数据
4数据解析
5持久化存储

## 爬取搜狗首页
#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 f:
    f.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'
# 封装参数
wd = input('enter a word:')
parma = {
    'query':wd
}
response = requests.get(url=url,params=parma)

page_text = response.content

filename = wd + '.html'

with open(filename,'wb') as f:
    f.write(page_text)
    print('over')

# #爬取百度翻译结果
import requests
url = 'https://fanyi.baidu.com/sug'
wd = input('enter a word')
data = {
    'kw':wd
}

reponse = requests.post(url=url,data=data)

print(reponse.json())
# text:字符串
# content: 二进制
# json（）：对象

# 爬取豆瓣电影分类排行榜 https://movie.douban.com/中的电影详情数据
import requests
url = 'https://movie.douban.com/j/chart/top_list'
parma = {
    "type": "11",
    "interval_id": "100:90",
    "action": "",
    "start": "0",
    "limit": "20",
}
movie_data = requests.get(url=url,params=parma).json()
print(movie_data)

#需求：爬取国家药品监督管理总局中基于中华人民共和国化妆品生产许可证相关数据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 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'
}
id_list = []
for page in range(1,2):
    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_data = requests.post(url=detail_url,data=detail_data,headers=headers).json()
    print(detail_data)

# 方式一
import requests 
url = 'https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1551194867510&di=bbf61d08b5497fa04a519267c3efb3ee&imgtype=0&src=http%3A%2F%2Fimg4.duitang.com%2Fuploads%2Fitem%2F201402%2F09%2F20140209170955_AiTUh.thumb.700_0.jpeg'
img_data = requests.get(url=url,headers=headers).content
with open('./bingzhang.jpg','wb') as f:
    f.write(img_data)

# 方式二
import urllib
url = 'https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1551194867510&di=bbf61d08b5497fa04a519267c3efb3ee&imgtype=0&src=http%3A%2F%2Fimg4.duitang.com%2Fuploads%2Fitem%2F201402%2F09%2F20140209170955_AiTUh.thumb.700_0.jpeg'
urllib.request.urlretrieve(url=url,filename='./liweier.jpg')

3.使用正则解析数据

简单使用

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)  # M是一行一行


#匹配全部行
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)  # S全部

　　案例

import re
import os
import requests
import urllib

url = 'https://www.qiushibaike.com/pic/page/%s/?s=5170618'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 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)
    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(imgName,"下载成功")
print("over!!!")

4.bs4接续数据

先安装：　

pip install bs4
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着属性进行源码中的相关标签的定位  find（‘name’，class_="xxx"） findall() select()

　　3.将定位到的标签之间存在的文本或者属性值获取 string text get_text() a['href']

案例：

import requests
from bs4 import BeautifulSoup

url = 'http://www.shicimingju.com/book/sanguoyanyi.html'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 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('sangou.txt','w',encoding='utf-8')

for a in a_list:
    title = a.string
    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 + '
' + content)
    print(title,"x下载成功")
print("over!")
fp.close()