python爬虫学习

Posted 2020-08-28

基于python2.7

get与post：

url = "http://zzk.cnblogs.com"
urllib.urlopen(url)----->get方法

name = urllib.urlencode({"k":"b"})
urllib.urlopen(url+name)----->pst方法

开发者工具中form表单的method选项为post，那么必须使用post方法。

urllib：

import urllib
import re

reponse = urllib.urlopen("https://www.baidu.com")         #打开指定的网页，返回网页所有信息
reponse_code = reponse.getcode()                          #获取状态码
reponse_body = reponse.read()                             #获取网页内容
#直接保存网页地址的内容到指定的文件
save = urllib.urlretrieve("https://www.baidu.com", filename="/home/guido/python/baidu.html")
images = re.findall(r"src=‘(.*?\\.jpg)‘", reponse_body)    #利用正则表达式匹配数据
urllib.urlretrieve(images[0], filename="/home/guido/python/baidu_images.html")

拼接链接格式

import urllib
parament = urllib.urlencode({"t":"b", "w":"ios"})
url = ("http://zzk.cnblogs.com/s?"+parament)
print(url)

执行结果：
http://zzk.cnblogs.com/s?t=b&w=ios

　　

urllib2：

import urllib2
url = "http://www.phpno.com"
#伪造浏览器请求头
send_headers = {
        "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
        "Accept-Encoding":"gzip, deflate, sdch",
        "Accept-Language":"zh-CN,zh;q=0.8",
        "Cache-Control":"max-age=0",
        "Connection":"keep-alive",
        "Cookie":"ASPSESSIONIDCCTRDBQT=OJNFDDEANPLCEFLECFILODNN; Hm_lvt_39dcd5bd05965dcfa70b1d2457c6dcae=1484820976,1484821014,1484821053; Hm_lpvt_39dcd5bd05965dcfa70b1d2457c6dcae=1484821053",
        "Host":"www.nm3dp.com",
        "Referer":"https://www.baidu.com/link?url=Q_AEn1rb05AX6miw616Tx5bIWILq5K_FpUQl_eyJ7TS&wd=&eqid=cb712bbf00052caf00000003588091e9",
        "Upgrade-Insecure-Requests":"1",
        "User-Agent":"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36"
}
req = urllib2.Request(url, headers=send_headers)     #合并浏览器向服务器发送的内容
r = urllib2.urlopen(req)
print(r.read())