day02

1、爬取ajax请求的数据(循环)：

from urllib.request import Request,urlopen
base_url = "https://movie.douban.com/j/chart/top_list?type=24&interval_id=100%3A90&action=&start={0}&limit={1}"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36"
}
i = 0
while True:
    url = base_url.format(i*20,20)
    print(url)
    request = Request(url,headers=headers)
    response = urlopen(request)
    content = response.read().decode()
    if content == "[]" or content == None:    # 爬取的内容为空时，就停止
        break;
    print(content)
    print(i)
    i += 1

 

 2、忽略证书问题：

 

 3、proxy代理：

 　　1） 自己创建build_opener对象，调用open方法：

from urllib.request import Request,build_opener
from fake_useragent import UserAgent

url = "http://httpbin.org/get"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36"
}
request = Request(url,headers=headers)
# 之前都是通过urlopen，里面也是创建build_opener类，再调用open方法
# 现在自己创建build_opener，调用open方法
openr = build_opener()
response = openr.open(request)  # 去请求url
print(response.read().decode())

 　　2） 代理ip：防止自己的ip被封 ： 

from urllib.request import Request,build_opener,ProxyHandler
from fake_useragent import UserAgent
url = "http://httpbin.org/get"
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36"
}
request = Request(url,headers=headers)

# proxy = ProxyHandler({"http":"username:pwd@120.27.224.41:16818"})#独享ip,花钱买
proxy = ProxyHandler({"http":"163.125.249.117:8118"}) # 免费ip
openr = build_opener(proxy)
response = openr.open(request)  
print(response.read().decode())

 

4、cookies：

　　1）、使用自己登录的cookies：

from urllib.request import HTTPCookieProcessor,Request,build_opener
from fake_useragent import UserAgent
url = "https://www.sxt.cn/index/user.html"
headers = {
    "User-Agent":UserAgent().random,
    # 自己登录网站，拿网站返回的cookie ， cookie放到请求头中
    "Cookie":"UM_distinctid=1677e8c7912122-0191ed60274b72-5c10301c-e1000-1677e8c791420d; 53gid2=10689069155008; 53gid1=10689069155008; 53revisit=1544016395113; 53gid0=10689069155008; PHPSESSID=rgp2u6edmipoflg2i4ivqefp70; visitor_type=old; 53kf_72085067_from_host=www.sxt.cn;  53kf_72085067_land_page=https%253A%252F%252Fwww.sxt.cn%252Findex.html;  kf_72085067_land_page_ok=1; 53kf_72085067_keyword=https%3A%2F%2Fwww.sxt.cn%2Findex%2Flogin%2Flogin.html; CNZZDATA1261969808=954793838-1544013478-https%253A%252F%252Fwww.sxt.cn%252F%7C1544071377"
}
request = Request(url,headers=headers)
opener = build_opener()
response = opener.open(request)
print(response.read().decode())

　　2）、使用写代码登录的cookies:

from urllib.request import HTTPCookieProcessor,Request,build_opener
from fake_useragent import UserAgent
from urllib.parse import urlencode

login_url = "https://www.sxt.cn/index/login/login"
data = {
    "user": "17703181473",
    "password": "123456",
}
headers = {
    "User-Agent":UserAgent().random,
}
request = Request(login_url,headers=headers,data=urlencode(data).encode())
cookie = HTTPCookieProcessor()
opener = build_opener(cookie)          # 将返回的cookie放到opener中，下次再用这个opener请求url
response = opener.open(request)

user_url = "https://www.sxt.cn/index/user.html"
request = Request(user_url,headers=headers)
response = opener.open(request)
print(response.read().decode())

　　3）、使用cookiejar，将cookie写到文件中：

from urllib.request import HTTPCookieProcessor, Request, build_opener
from fake_useragent import UserAgent
from urllib.parse import urlencode
from http.cookiejar import MozillaCookieJar

headers = {
    "User-Agent": UserAgent().random,
}

# 获得cookie，存进文件中
def get_cookie():
    login_url = "https://www.sxt.cn/index/login/login"
    data = {
        "user": "17703181473",
        "password": "123456",
    }
    request = Request(login_url,
                  headers=headers,   data=urlencode(data).encode())
    cookiejar = MozillaCookieJar()
    cookie = HTTPCookieProcessor(cookiejar)
    opener = build_opener(cookie)
    response = opener.open(request)
    # cookiejar:将cookie存到文件中，discard:丢弃的cookie,expires:无效的cookie
    cookiejar.save("cookie.txt", ignore_discard=True, ignore_expires=True)

# 使用文件中cookie，进入用户界面
def use_cookie():
    user_url = "https://www.sxt.cn/index/user.html"
    request = Request(user_url, headers=headers)
    cookiejar = MozillaCookieJar()
    # 后面两个True需要加的
    cookiejar.load("cookie.txt",ignore_expires=True,ignore_discard=True)
    cookie = HTTPCookieProcessor(cookiejar)
    opener = build_opener(cookie)
    response = opener.open(request)
    print(response.read().decode())


if __name__ == "__main__":
    get_cookie()
    use_cookie()

 

 5、URLError-捕获异常：

from urllib.request import Request,urlopen,URLError
from fake_useragent import UserAgent
url = "https://www.sxt.cn/index/login/login.htmls"
headers = {
    "User-Agent":UserAgent().random
}
try:
    request = Request(url,headers=headers)
    response = urlopen(request)
    print(response.read().decode())
except URLError as e:
    # HTTP Error 404: Not Found
    # <urlopen error [Errno 11004] getaddrinfo failed>
    if e.args==():    # 不存在url    404
        print(e.code)
    else:             # 域名不存在   11004
        print(e.args[0].errno)
print("成功")

 

6、requests库：

1）、get请求：
import requests
url = "http://www.baidu.com/s"
params = {
    "wd":"尚学堂"
}
response = requests.get(url,params=params)
print(response.text)


2）、post请求 ：
import requests
url = "https://www.sxt.cn/index/login/login"
data = {
    "user": "17703181473",
    "password": "123456",
}
# data接受post数据
response = requests.post(url,data=data)
print(response.text)

3）、代理：
import requests
from fake_useragent import UserAgent
url = "http://httpbin.org/get"
headers = {
    "User-Agent":UserAgent().random
}
proxy = {
    # 书写格式
    "http":"http://124.235.135.210:80"
    # 独享代理
    # "http":"http://user:pwd@ip:port"
}
# data接受post数据
response = requests.get(url,headers=headers,proxies=proxy)
print(response.text)

4）、证书：
import requests
from fake_useragent import UserAgent
url = "https://www.12306.cn/index/"
headers = {
    "User-Agent":UserAgent().random
}
# 去掉红色的警告
requests.packages.urllib3.disable_warnings()
# verify= False 不需要证书
response = requests.get(url,headers=headers,verify=False)
response.encoding="utf-8"   # 设置编码
print(response.text)

5）、cookies：
import requests
from fake_useragent import UserAgent
session = requests.session()  # 发送请求用这个
headers = {
    "User-Agent":UserAgent().random
}
login_url = "https://www.sxt.cn/index/login/login"
data = {
    "user": "17703181473",
    "password": "123456",
}
response = session.post(login_url,headers=headers,data=data)
url = "https://www.sxt.cn/index/user.html"
response = session.get(url,headers=headers)    # session中有cookie
print(response.text)

 

7、re模块：

import re
str = "Iss study Python3.6 Everyday"
################## 1、match####################
result = re.match("I",str)
print(result.group())  # I
result = re.match("\w",str)
print(result.group())  # I
result = re.match(".",str)
print(result.group())  # I
result = re.match("\D",str)  # \D 非数字
print(result.group())  # I

result = re.match("i",str,re.I)  # re.I忽略大小写
print(result.group())  # I
result = re.match("\S",str,re.I)  # \S非空格
print(result.group())  # I

result = re.match("\Study",str,re.I)  # \S非空格
# print(result.group())  # None 匹配不到

###############2、search 搜索一个###############
str = "Iss study Python3.6 Everyday study"
result2= re.search("study",str)
print(result2.group()) # study
result2= re.search("st\w+",str)
print(result2.group()) # study
result2= re.search("P\w+.\d",str)
print(result2.group()) # Python3.6

###############3、finall 找所有内容################
str = "Iss study Python3.6 Everyday"
result3 = re.findall("y",str)
print(result3)           # [y,y,y,y] 找到所有的字符y
str2 = "<div class='info' id='info' ><a href='http://www.sxt.com'>尚学堂ewew</a></div>"
result3 = re.findall("<a href='http://www.sxt.com'>(.*)</a>",str2)
print(result3)           # [尚学堂ewew]
result3 = re.findall("<a href='http://www.sxt.com'>(.+)</a>",str2)
print(result3)           # [尚学堂ewew]
result3 = re.findall("<a href='http://www.sxt.com'>([\u4E00-\u9FA5]\w+)</a>",str2)
print(result3)            # [尚学堂ewew]
result3 = re.findall("<a href='(.+)'>",str2)
print(result3)           # ['http://www.sxt.com']

###############4、sub 替换 #########################
str3 = "<div><a href='http://www.sxt.com'>尚学堂ewew</a></div>"
result4 = re.sub('<div>(.*)</div>',r"<span>\1</span>",str3)     # 记得加r
print(result4)   # <span><a href='http://www.sxt.com'>尚学堂ewew</a></span>

 

 8、糗事百科案例：

import requests,re
from fake_useragent import UserAgent
url = "https://www.qiushibaike.com/text/page/1/"
response = requests.get(url)
# \s+ 是 空格
infos = re.findall('<div class="content">\s+<span>\s+(.*)\s+</span>',response.text)
for info in infos:
    info = info.replace("<br/>","")      # 去除<br/>
    print(info)
    with open("duanzi.txt","a+",encoding="utf-8") as f:
        f.write(info+"\n\n\n")

 

9、BeautifulSoup4：

　　

from bs4 import BeautifulSoup
from bs4.element import Comment
str = '''
<title>尚学堂</title>
<div class='info div1' float='left'>Welcome to SXT</div>
<div class='info' float='right'>
    <span>Good Good Study</span>
    <a href='www.bistx.cn'></a>
    <strong><!--没有用--></strong>
</div>
'''

soup = BeautifulSoup(str,"lxml")
################1、获得标签######################
print(soup.title)  # <title>尚学堂</title> 获得title标签
print(soup.div)    # <div class="info" float="left">Welcome to SXT</div> 默认获得第一个

################2、获得标签的属性#################
print(soup.div.attrs)  # {'class': ['info'], 'float': 'left'} 默认获得第一个div的属性
print(soup.div.get("class")) # ['info']
print(soup.div["class"])     # ['info']
print(soup.a["href"])     # www.bistx.cn


################3 、获得文本 string：NavigableString对象，text：字符串str ############
print(soup.div.string)        # Welcome to SXT
print(type(soup.div.string))  # <class 'bs4.element.NavigableString'>
print(soup.div.text)          #  Welcome to SXT
print(type(soup.div.text))    # <class 'str'>

print(soup.strong.string)                      # 没有用
print(type(soup.strong.string))                # <class 'bs4.element.Comment'>  注释是Comment对象
print(soup.strong.text,type(soup.strong.text)) # ""  <class 'str'>

if type(soup.strong.string) == Comment:    # 若是Comment对象(注释)
    print(soup.strong.string)           # 没有用
    print(soup.strong.prettify())       # <strong><!--没有用--></strong>
else:
    print(soup.strong.text)

################4 、find_all 和 find 获得标签对象、通过属性获得标签对象#############

print(soup.find_all("title"))  # [<title>尚学堂</title>]  获得所有的title标签
print(soup.find_all("div"))    # 获得两个div  <div class='info' ... </div> <div>....</div>
print(soup.find_all(float="left")) # [<div class="info div1" float="left">Welcome to SXT</div>]
# class 是关键字，所以加_
print(soup.find_all(class_="div1")) # [<div class="info div1" float="left">Welcome to SXT</div>]
print(soup.find_all("div",attrs={"float":"left"})) # [<div class="info div1" float="left">Welcome to SXT</div>]

################5、select 选择标签 ############

 

10、etree之xpath：

# 下载xpath谷歌插件：用于写xpath语句，不用每次运行代码测试
import requests
from lxml import etree

url = "https://www.qidian.com/rank/yuepiao?style=1"
response = requests.get(url)
e = etree.HTML(response.text)
bookNames = e.xpath("//h4/a/text()")
authors = e.xpath("//p[@class='author']/a[1]/text()")

# for num in range(len(bookNames)):
#     print(bookNames[num]+":"+authors[num])
# 这个方法也可以同时输出书名和作者
for name,author in zip(bookNames,authors):
    print(name+":"+author)

# 1、在scrapy中用到xpath：
 item_list= response.xpath("
//div[@id='content-list']/div[@class='item']")

# 2、beautifulsoup用到find和find_all: 
soup = BeautifulSoup(response1.text,"html.parser")
div = soup.find(name="div",attrs={"id":"auto-channel-lazyload-article"})
print(soup.find_all(class_="div1"))

# 3、re用到findall：
result3 = re.findall("<a href='http://www.sxt.com'>(.*)</a>",str2)
print(result3)            # [尚学堂ewew]

 

11、数据提取之pyquery：

pip3 install pyquery

from pyquery import PyQuery as pq
import requests
from fake_useragent import UserAgent
url="http://www.xicidaili.com/nn"
headers={
    "User-Agent":UserAgent().random
}
response = requests.get(url,headers=headers)
doc =  pq(response.text)
trs = doc("#ip_list tr")  #  找id为ip_list标签下的所有tr
for num in range(1,len(trs)):
    ip = trs.eq(num).find("td").eq(1).text() # 注意是eq，不是[num]
    port = trs.eq(num).find("td").eq(2).text()
    type = trs.eq(num).find("td").eq(5).text()
    print(ip+":"+port+":"+type)

 

12、数据提取之jsonpath：

　　1）、json的dumps和load函数：

import json
str = '{"name":"无名之辈"}'
################1、loads ： 将json字符串转换为#json对象#############
obj = json.loads(str)
print(obj,type(obj))    # {'name': '无名之辈'} <class 'dict'>

################2、dumps ： 将json对象转换为json字符串##############
result2 = json.dumps(obj,ensure_ascii=False)
print(result2,type(result2))  # {"name": "无名之辈"} <class 'str'>

##############3、dump 将json对象存进文件中，编码需要的##################
json.dump(obj,open("movie.txt","w",encoding="utf-8"),ensure_ascii=False)

##############3、dump 将文件中的json字符串转换为json对象，编码需要#########
str3 = json.load(open("movie.txt",encoding="utf-8"))
print(str3,type(str3))   # {'name': '无名之辈'} <class 'dict'>

 

 　　2）、JsonPath：

　　　　安装模块：pip3 install JsonPath

from jsonpath import jsonpath
import requests,json
# 拉勾网的所有市的信息
url="https://www.lagou.com/lbs/getAllCitySearchLabels.json"
response = requests.get(url)

names = jsonpath(json.loads(response.text),"$..name") # 必须加$
codes = jsonpath(json.loads(response.text),"$..code")

for code,name in zip(codes,names):
    print(code+":"+name)

补充：
response.text、response.content与response.json：
1、response.json：返回的是json格式数据；
2、返回的数据类型 ：
response.text ：返回的是一个 unicode 型的文本数据； 
response.content ：返回的是 bytes 型的二进制数据 ；
也就是说如果想取文本数据可以通过response.text 如果想取图片，文件，则可以通过 response.content；
3、数据编码 ：
response.content ：返回的是二进制响应内容 ；
response.text ： 则是默认”iso-8859-1”编码，服务器不指定的话是根据网页的响应来猜测编码。