def AddDict(refer_dict):
import requests, MyDef
for k in range(15):
header = {
'User-Agent':
'Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.8.1.14) Gecko/20080404 (FoxPlus) Firefox/2.0.0.14'
}
url = 'https://pan.baidu.com/wap/share/home?third=0&uk=2007334207&start=' + str(
20 * (k + 1))
page = requests.get(url=url, headers=header)
# print(page.encoding)
# print(page.headers)
# print(page.cookies)
# print(page.text)
html = page.content.decode("utf", "ignore")
# print(html)
shareid_list = MyDef.ReFind(html, r'"shareid":"[0-9]{1,20}')
print(shareid_list)
print(len(shareid_list))
title_list = MyDef.ReFind(html, r'"title":"[a-z]{64}')
print(title_list)
print(len(title_list))
for i in range(len(shareid_list)):
shareid = shareid_list[i].replace('"shareid":"', '')
title = title_list[i].replace('"title":"', '')
real_name = MyDef.HexShiftBack(title[:32])
refer_dict[
real_name] = 'https://pan.baidu.com/share/link?uk=2007334207&shareid=' + shareid
return refer_dict
def ReadChrome(input_file_path):
import time, re, MyDef
from lxml import html
start_time = time.time() # 初始时间戳
# ==============读取文本==============
input_file_path = '/Users/alicewish/Dropbox/百度云 网盘-我的分享.htm'
read_text = open(input_file_path, 'r').read() # 读取文本
tree = html.fromstring(read_text)
# ==============读取文件名==============
names = tree.xpath('//span[@node-type="name-text"]/@title') # 列表存储
all_name = '\r\n'.join(names)
print(len(names))
print(all_name)
# ==============读取下载地址==============
share_links = []
links = tree.xpath('//a[@target="_blank"]/@href') # 列表存储
for link in links:
# print(link)
if re.match(r'https://pan.baidu.com/s/[^<]*', link): # 判断是否度盘外链
share_links.append(link)
all_link = '\n'.join(share_links)
print(len(share_links))
print(all_link)
# ==============读取分享时间和浏览、保存、下载次数==============
raw_share_time = tree.xpath(
'//div[@style="width: 20%"]/text()') # 列表存储分享时间
all_number = tree.xpath('//div[@style="width: 9%"]/text()') # 列表存储各类次数
share_time = []
view_number = []
save_number = []
download_number = []
for i in range(len(names)):
share_time.append(raw_share_time[i + 1].strip(" \n\t\r"))
view_number.append(all_number[3 * i +
3].strip(" \n\t\r").strip("次")) # 浏览次数
save_number.append(all_number[3 * i +
4].strip(" \n\t\r").strip("次")) # 保存次数
download_number.append(
all_number[3 * i + 5].strip(" \n\t\r").strip("次")) # 下载次数
# ==============合并信息==============
info_list = []
refer_dict = {}
if len(names) == len(share_links):
for i in range(len(names)):
info_line_in_list = [
names[i], share_links[i], share_time[i], view_number[i],
save_number[i], download_number[i]
]
info_line = "\t".join(info_line_in_list)
info_list.append(info_line)
if len(names[i]) == 64:
real_name = MyDef.HexShiftBack(names[i][:32]) # 重要
refer_dict[real_name] = share_links[i]
else:
print("错误", len(names), len(share_links))
all_info = '\n'.join(info_list)
print(all_info)
print(MyDef.RunTime(start_time))
return refer_dict