码迷,mamicode.com
首页 > 编程语言 > 详细

python3 访问百度返回压缩格式

时间:2018-06-03 17:28:06      阅读:261      评论:0      收藏:0      [点我收藏+]

标签:dup   file   main   find   3.1   like   2.0   else   name   

import urllib, urllib.request, urllib.parse
import random
import zlib
import re
import os, time

SavePath="Save"

def InitDev():
    AllHanzi = ""
    if not os.path.exists(SavePath):
        os.makedirs(SavePath)
    with open("all.txt", mode="r", encoding="utf-8") as f:
        AllHanzi=f.read()
    return AllHanzi

def SaveGif(zi):
    url = r"https://xxxxxxxxx.xxxxxxxxxx.com/s?{}"
    data={"wd": zi,
          "from": "xxxx"}
    datastr=urllib.parse.urlencode(data)
    url = url.format(datastr)

    USER_AGENTS = [
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
        "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
        "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
        "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
        "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/531.21.8 (KHTML, like Gecko) Version/4.0.4 Safari/531.21.10",
        "Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/533.17.8 (KHTML, like Gecko) Version/5.0.1 Safari/533.17.8",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533.19.4 (KHTML, like Gecko) Version/5.0.2 Safari/533.18.5",
        "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-GB; rv:1.9.1.17) Gecko/20110123 (like Firefox/3.x) SeaMonkey/2.0.12",
        "Mozilla/5.0 (Windows NT 5.2; rv:10.0.1) Gecko/20100101 Firefox/10.0.1 SeaMonkey/2.7.1",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_5_8; en-US) AppleWebKit/532.8 (KHTML, like Gecko) Chrome/4.0.302.2 Safari/532.8",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_4; en-US) AppleWebKit/534.3 (KHTML, like Gecko) Chrome/6.0.464.0 Safari/534.3",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_5; en-US) AppleWebKit/534.13 (KHTML, like Gecko) Chrome/9.0.597.15 Safari/534.13",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.186 Safari/535.1",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.54 Safari/535.2",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
        "Mozilla/5.0 (Macintosh; U; Mac OS X Mach-O; en-US; rv:2.0a) Gecko/20040614 Firefox/3.0.0 ",
        "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.0.3) Gecko/2008092414 Firefox/3.0.3",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.5; en-US; rv:1.9.1) Gecko/20090624 Firefox/3.5",
        "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6; en-US; rv:1.9.2.14) Gecko/20110218 AlexaToolbar/alxf-2.0 Firefox/3.6.14",
        "Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10.5; en-US; rv:1.9.2.15) Gecko/20110303 Firefox/3.6.15",
        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1"
    ]

    headerStr = {"User-Agent" : random.choice(USER_AGENTS),
                 "Host": "xxxxx.baidu.com",
                 "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
                 "Accept-Encoding": "gzip, deflate, br",
                 "Accept-Language": "zh-CN,zh;q=0.9",
                 #"Cookie": "PSTM=1527352228; BIDUPSID=50BA11B43CD76A00613EB02151D5E961; BAIDUID=EB49A1306B852804B150538899B2632A:FG=1; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=1453_21101; Hm_lvt_010e9ef9290225e88b64ebf20166c8c4=1527941967,1527994003; PSINO=1; Hm_lpvt_010e9ef9290225e88b64ebf20166c8c4=1528002586",
                 "Referer": "https://xxxxx.xxxxx.xxxx"}
    try:
        req=urllib.request.Request(url=url, headers=headerStr, method="GET")
        response=urllib.request.urlopen(req)
        html = response.read()

        decompressed_data = zlib.decompress(html, 16 + zlib.MAX_WBITS)
        text = decompressed_data.decode(‘utf8‘)

        list = re.findall(r"data-gif=\"(.*?)\"", text)
        print (list)

        destFile = "{}\\{}.gif".format(SavePath, zi)
        if (list.__len__() > 0):
            urllib.request.urlretrieve(list[0], destFile)
            SaveResult(zi, True)
        else:
            SaveResult(zi, False)
    except Exception as e:
        SaveResult(zi, False)
    time.sleep(1)

def SaveResult(str, success):
    fileStr = "error.log"
    if success:
        fileStr = "ok.log"
    with open(fileStr, "a+") as f:
        f.write(str)

def SaveAll():
    AllHanzi = InitDev()
    for x in range(len(AllHanzi)):
        print(AllHanzi[x], "\r\n")
        SaveGif(AllHanzi[x])


if __name__ == ‘__main__‘:
    SaveAll()

  

python3 访问百度返回压缩格式

标签:dup   file   main   find   3.1   like   2.0   else   name   

原文地址:https://www.cnblogs.com/onlyou13/p/9129556.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!