為了研究chrome 插件的代碼肮柜，可以下載chrome插件crx文件(zip)并解壓為源碼格式即可查看源代碼:
# -*- coding: UTF-8 -*-
import requests, json,time
# baseUrl = "https://ext.chrome.#/provider/extlist/?category=全部&count=20&sortType=download&token=" # 50 頁(yè)
baseUrl = "https://ext.chrome.#/provider/extlist/?category=全部&count=100&sortType=download&token="
class UrlManager():
def getPage(self,page):
currentPage = baseUrl + str(page)
print("currentPage is " + currentPage)
headers = {'User-Agent': 'Baidu Spidder', 'Referer': 'http://www.baidu.com'}
response = requests.get(currentPage, headers=headers, verify=False) # 忽略https
# jstr = '{"name":"xiaoming","age":"22"}'
# jstr = "{'name':'xiaoming','age':'22'}" // 錯(cuò)誤效诅，按照上面的寫(xiě)法
# jdata = json.dumps(jstr) # 把python字典轉(zhuǎn)為json字符串
jsonObject = json.loads(response.content) # 把json字符串轉(zhuǎn)為python字典
_list = jsonObject["list"]
for o in _list:
name = o["name"]
crxUrl = o["filename"]
version = o["version"]
descpic = o["descpic"] # 圖片
self.download(name,crxUrl)
def download(self,name,url):
time.sleep(3) # 3s
print("正在下載 == 》 "+ name)
prefix = name + "_"
headers = {'User-Agent': 'Baidu Spidder','Referer':'http://www.baidu.com'}
response = requests.get(url,headers=headers)
filename = url.split("/")[-1]
dest = "F:/" + prefix + filename
with open(dest,"wb") as fout:
fout.write(response.content)
print("《===="+name+" 下載完成====》")
class Demo():
# 初始各個(gè)對(duì)象
def __init__(self):
self.urlManager = UrlManager()
def craw(self):
print(" begin")
for u in range(1,2):
self.urlManager.getPage(u)
if __name__ == "__main__":
obj_spider = Demo()
obj_spider.craw()
