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 BulidLinkB():
import time, MyDef, os
start_time = time.time() # 初始时间戳
refer_dict = ReadMD5SamplingCSV()
MD5_refer_dict, MD5_list = ReadMD5CSV()
yun_link_dict = ReadMobile()
output_list = []
# ========================主目录========================
for key in refer_dict:
if key in yun_link_dict:
folder_name = MyDef.HexShift(key)
yun_link = yun_link_dict[key]
sample_list = refer_dict[key].split("|")
print(sample_list)
# ========================次级目录========================
for sample in sample_list: # 文件MD5
file_path = MD5_refer_dict[sample]
file_name = os.path.split(file_path)[1]
file_folder_name = MyDef.HexShift(sample)
file_link = yun_link + '#path=%252F' + folder_name + '%252F' + folder_name + file_folder_name
print(file_name)
print(file_link)
path_list = [file_path, file_link]
output_list.append(path_list)
path = '/Users/alicewish/Dropbox/漫画图源度盘地址表.csv'
MyDef.StoreCSV(output_list, path)
print(len(output_list))
print(MyDef.RunTime(start_time))
def UnDistribute():
import time, MyDef, os, shutil
start_time = time.time() # 初始时间戳
refer_dict = ReadMD5SamplingCSV()
MD5_refer_dict, MD5_list = ReadMD5CSV()
# ========================最外层目录========================
new_file_dir = '/Volumes/Mack/Distribute'
# ========================主目录========================
for key in refer_dict:
folder_name = MyDef.HexShift(key)
new_folder_path = os.path.join(new_file_dir, folder_name)
sample_list = refer_dict[key].split("|")
print(sample_list)
# ========================次级目录========================
for sample in sample_list: # 文件MD5
file_path = MD5_refer_dict[sample]
file_name = os.path.split(file_path)[1]
print("旧", file_path)
file_folder_name = MyDef.HexShift(sample)
new_file_folder_path = os.path.join(new_file_dir, folder_name,
folder_name + file_folder_name)
new_file_path = os.path.join(new_file_folder_path, file_name)
print("新", new_file_path)
try:
shutil.move(new_file_path, file_path) # 移动文件或目录都是使用这条命令
except:
pass
print(MyDef.RunTime(start_time))
def ChangeBack():
import os, MyDef
dropbox_path = '/Users/alicewish/Dropbox'
refer_file_name = '漫画图源MD5表.csv'
refer_file_path = os.path.join(dropbox_path, refer_file_name)
text_readline = MyDef.ReadCSV(refer_file_path, type=False)
for i in range(len(text_readline)):
if '@k_k@' in text_readline[i][1]:
print(text_readline[i][1])
text_readline[i][1] = text_readline[i][1].replace('@k_k@', '')
MyDef.StoreCSV(text_readline, refer_file_path)
def MD5Table(file_dir):
import time, os, MyDef
start_time = time.time() # 初始时间戳
dropbox_path = '/Users/alicewish/Dropbox'
refer_file_name = '漫画图源MD5表.csv'
refer_file_path = os.path.join(dropbox_path, refer_file_name) # 词典文件的地址
MD5_refer_dict = MyDef.ReadDictB(refer_file_path, True)
# print(MD5_refer_dict)
file_path_check_set = set()
major_key_list = []
output_list = []
# ================读取文件夹内容================
file_list = os.listdir(file_dir) # 获得目录中的内容
# print(file_list)
for file_MD5 in MD5_refer_dict:
file_path = MD5_refer_dict[file_MD5]
file_path_check_set.add(file_path)
for file_name in file_list:
file_path = os.path.join(file_dir, file_name)
if file_path in file_path_check_set:
pass
else:
# file_MD5 = MyDef.HashMD5File(file_path)
file_MD5 = MyDef.md5sum(file_path)
print(file_MD5, file_name)
MD5_refer_dict[file_MD5] = file_path
for file_MD5 in MD5_refer_dict:
file_path = MD5_refer_dict[file_MD5]
file_name = os.path.split(file_path)[1]
major_key = file_name + file_MD5
major_key_list.append(major_key)
major_key_list.sort()
for major_key in major_key_list:
file_MD5 = major_key[-32:]
info_list = [file_MD5, MD5_refer_dict[file_MD5]]
output_list.append(info_list)
head_info = ['MD5', '路径']
MyDef.StoreCSV(output_list, refer_file_path, head_info)
print(MyDef.RunTime(start_time))
def FileWithLink():
import time, os, MyDef
start_time = time.time() # 初始时间戳
# ========================输入区开始========================
output_readline = []
refer_file_path = '/Users/alicewish/Dropbox/漫画图源MD5表.csv'
MD5_dict = MyDef.ReadDictC(refer_file_path, True)
yun_link_file_path = '/Users/alicewish/Dropbox/漫画图源度盘地址表.csv'
yun_link_dict = MyDef.ReadDictB(yun_link_file_path)
file_path_list = []
for key in MD5_dict:
file_path = MD5_dict[key]
file_size = os.path.getsize(file_path)
readable_file_size = sizeof_fmt(file_size)
file_name = os.path.split(file_path)[1]
file_path_list.append(file_path)
if file_path in yun_link_dict:
yun_link = yun_link_dict[file_path]
output_line = "[" + file_name + "](" + yun_link + ") | " + readable_file_size
else:
output_line = "[" + file_name + "]() | " + readable_file_size
print(file_name)
# print(output_line)
output_readline.append(output_line)
output_readline.sort()
output_readline.insert(0, '--- | ---')
output_readline.insert(0, '文件名 | 大小')
for i in range(len(output_readline)):
line = output_readline[i]
if "]()" in line:
line = line[1:].replace("]()", "")
output_readline[i] = line
# ================写入剪贴板================
output_text = '\r\n'.join(output_readline)
MyDef.WriteClip(output_text)
print(MyDef.RunTime(start_time))
def ReadMD5CSV():
import os, MyDef
dropbox_path = '/Users/alicewish/Dropbox'
refer_file_name = '漫画图源MD5表.csv'
refer_file_path = os.path.join(dropbox_path, refer_file_name) # 词典文件的地址
MD5_refer_dict = MyDef.ReadDictB(refer_file_path, True)
MD5_list = []
for file_MD5 in MD5_refer_dict:
MD5_list.append(file_MD5)
return (MD5_refer_dict, MD5_list)
def ReadMobile():
import time, requests, MyDef
start_time = time.time() # 初始时间戳
refer_dict = {}
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?uk=2007334207&third=0'
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":"', '')
refer_dict[
title] = 'https://pan.baidu.com/share/link?uk=2007334207&shareid=' + shareid
refer_dict = AddDict(refer_dict)
# ================运行时间计时================
print(MyDef.RunTime(start_time))
print(refer_dict)
print(len(refer_dict))
return refer_dict
def Sampling(number=30):
import time, MyDef, os
start_time = time.time() # 初始时间戳
MD5_refer_dict, MD5_list = ReadMD5CSV()
remain_sample = MD5_list
refer_dict = {}
while len(remain_sample) > 0:
random_sample, remain_sample = RandomSample(remain_sample, number)
random_sample_string = '|'.join(random_sample)
print(random_sample_string)
random_sample_string_MD5 = MyDef.HashMD5String(random_sample_string)
print('方案MD5', random_sample_string_MD5)
refer_dict[random_sample_string_MD5] = random_sample_string
dropbox_path = '/Users/alicewish/Dropbox'
refer_file_name = '漫画图源MD5随机分样表.csv'
refer_file_path = os.path.join(dropbox_path, refer_file_name)
MyDef.WriteDictB(refer_dict, refer_file_path)
print(MyDef.RunTime(start_time))
def MD5Table(file_dir):
import time, os, MyDef
start_time = time.time() # 初始时间戳
dropbox_path = '/Users/alicewish/Dropbox'
refer_file_name = '漫画图源MD5表.csv'
refer_file_path = os.path.join(dropbox_path, refer_file_name) # 词典文件的地址
MD5_refer_dict = MyDef.ReadDictB(refer_file_path, True)
# print(MD5_refer_dict)
file_path_check_set = set()
major_key_list = []
output_list = []
# ================读取文件夹内容================
file_list = os.listdir(file_dir) # 获得目录中的内容
# print(file_list)
for file_MD5 in MD5_refer_dict:
file_path = MD5_refer_dict[file_MD5]
file_path_check_set.add(file_path)
for file_name in file_list:
file_path = os.path.join(file_dir, file_name)
if file_path in file_path_check_set:
pass
else:
# file_MD5 = MyDef.HashMD5File(file_path)
file_MD5 = MyDef.md5sum(file_path)
print(file_MD5, file_name)
MD5_refer_dict[file_MD5] = file_path
for file_MD5 in MD5_refer_dict:
file_path = MD5_refer_dict[file_MD5]
file_name = os.path.split(file_path)[1]
major_key = file_name + file_MD5
major_key_list.append(major_key)
major_key_list.sort()
for major_key in major_key_list:
file_MD5 = major_key[-32:]
info_list = [file_MD5, MD5_refer_dict[file_MD5]]
output_list.append(info_list)
head_info = ['MD5', '路径']
MyDef.StoreCSV(output_list, refer_file_path, head_info)
print(MyDef.RunTime(start_time))
def Distribute():
import time, MyDef, os, shutil
start_time = time.time() # 初始时间戳
refer_dict = ReadMD5SamplingCSV()
MD5_refer_dict, MD5_list = ReadMD5CSV()
new_file_dir = '/Volumes/Mack/Distribute'
try:
os.mkdir(new_file_dir) # 创建目录
except:
pass
for key in refer_dict:
new_folder_path = os.path.join(new_file_dir, key)
try:
os.mkdir(new_folder_path) # 创建目录
except:
pass
sample_list = refer_dict[key].split("|")
print(sample_list)
for sample in sample_list:
file_path = MD5_refer_dict[sample]
file_name = os.path.split(file_path)[1]
print("旧", file_path)
new_file_path = os.path.join(new_folder_path, sample, file_name)
print("新", new_file_path)
new_file_folder_path = os.path.join(new_file_dir, key, sample)
try:
os.mkdir(new_file_folder_path) # 创建目录
except:
pass
try:
shutil.move(file_path, new_file_path) # 移动文件或目录都是使用这条命令
except:
pass
print(MyDef.RunTime(start_time))
magnet_list = tree.xpath('//a[@title="Download this torrent using magnet"]/@href')
count = len(title_list)
for i in range(count):
output_line_in_list = [title_list[i], magnet_list[i]]
output_line = ",".join(output_line_in_list)
output_readline.append(output_line)
this_week_readline.append(magnet_list[0])
# ================写入文本================
text = '\r\n'.join(output_readline)
print(text)
f = open(output_file_path, 'w')
try:
f.write(text)
finally:
f.close()
info = "\r\n".join(this_week_readline)
print(info)
print(len(this_week_readline))
# ================写入剪贴板================
import pyperclip
pyperclip.copy(info)
spam = pyperclip.paste()
print("耗时:",MyDef.RunTime(start_time))
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
import time, re, MyDef
start_time = time.time() # 初始时间戳
now = time.strftime("%Y%m%d", time.localtime()) # 当前日期戳
# ========================输入区开始========================
# ================读取剪贴板================
text_readline = MyDef.ReadClipL()
# ========================处理文本========================
output_readline = [] # 初始化信息列表
for i in range(len(text_readline)):
line = text_readline[i]
output_line = line
level = 1
if re.match(r'第\w部分', line):
level = 1
elif re.match(r'第[0-9]{1,}章', line):
level = 2
elif re.match(r'[0-9]{1,2}\.[0-9]{1,2}', line):
level = 3
else:
level = 3
output_line = (level - 1) * " " + "- " + line
output_readline.append(output_line)
# ================写入昵称列表================
text = '\r\n'.join(output_readline) # 写入文本
print(text)
def Processing():
import time, jieba, re, MyDef
start_time = time.time() # 初始时间戳
scenario_list_full = Training()
# ======================================处理区开始======================================
dict_file_path = '/Users/alicewish/我的坚果云/userdict.txt' # 自定义词典路径
cut_right_count = 0
cut_wrong_count = 0
# ========================输入区开始========================
input_file_path = "/Users/alicewish/Downloads/my.md"
# ================按行读取输入文本================
read_text = open(input_file_path, 'r').read() # 读取文本
text_readline = read_text.replace("\nclass",
"class").replace("...",
"…").splitlines()
# print(text_readline)
# ================按行读取文本:with open(更好)================
status_readline = [] # 状态列表
output_readline = [] # 输出列表
jieba.load_userdict(dict_file_path)
line_formmat_list_all = []
for a in range(len(text_readline)):
text_readline[a] = re.sub(r'<span.*</span>', '',
text_readline[a]) # 去除span
text_readline[a] = text_readline[a].replace('……', '…')
markdown_line = text_readline[a].replace("\*", "の").replace(
"\[", "[").replace("\]", "]")
print(markdown_line)
line_cut_list = markdown_line.split("*")
print(line_cut_list)
plain_line = markdown_line.replace("*", "").replace("の", "*") # 调整*
print(plain_line)
line_formmat_list = []
for j in range(len(plain_line)):
line_formmat_list.append(0)
# print(line_formmat_list)
line_mark_count_list = []
for k in range(len(plain_line) + 1):
line_mark_count_list.append(0)
point = 0
for char in markdown_line:
if char == '*':
line_mark_count_list[point] = line_mark_count_list[point] + 1
else:
point = point + 1
print(line_mark_count_list)
pin = 0
before = 0
for seg in line_cut_list:
if seg == '':
pass
else:
last_pin = pin
pin += len(seg)
# print(line_mark_count_list[last_pin])
# print(line_mark_count_list[pin])
if last_pin > 0:
before = line_formmat_list[last_pin - 1]
for l in range(last_pin, pin):
if before == 0:
line_formmat_list[
l] = before + line_mark_count_list[last_pin]
elif before == 1 and line_mark_count_list[last_pin] == 1:
line_formmat_list[
l] = before - line_mark_count_list[last_pin]
elif before == 1 and line_mark_count_list[last_pin] == 2:
line_formmat_list[
l] = before + line_mark_count_list[last_pin]
elif before == 2 and line_mark_count_list[last_pin] == 1:
line_formmat_list[
l] = before + line_mark_count_list[last_pin]
elif before == 2 and line_mark_count_list[last_pin] == 2:
line_formmat_list[
l] = before - line_mark_count_list[last_pin]
elif before == 3:
line_formmat_list[
l] = before - line_mark_count_list[last_pin]
# print(line_formmat_list[last_pin - 1])
print(line_formmat_list)
line_formmat_list_all.append(line_formmat_list)
print(plain_line)
print(len(plain_line))
need_cut = True # 需要切吗?
if len(plain_line) == 0:
pass
elif len(plain_line) == 2 and re.match(r'[0-9][0-9]', plain_line):
# 页码
need_cut = False
elif a < 8:
# 首部
need_cut = False
elif len(plain_line) > 2:
if plain_line[0] == '*' or plain_line[0] == '[':
# 注释
need_cut = False
if plain_line == "":
status = 0 # 空行
elif not need_cut:
status = -1 # 不需要切
else:
status = 1 # 待分词
status_readline.append(status)
if status == 1:
# ================结巴分词================
string_list = []
seg_list = jieba.cut(plain_line) # 默认是精确模式
for word in seg_list:
string_list.append(word)
print(string_list)
start_status = False
for i in range(len(scenario_list_full)):
scenario_line_full = scenario_list_full[i]
if scenario_line_full[0:2] == str(len(plain_line)).zfill(2):
if start_status:
end_i = i
else:
start_i = i
start_status = True
end_i = i
# ================进行切分================
current_i = start_i
cut_right = False
while current_i <= end_i and not cut_right:
current_cut = scenario_list_full[current_i]
current_cut_list = current_cut[7:].split("-") # 列表存储的切分方案
# ================进行分词判断================
line_can_cut_list = []
for i in range(len(plain_line)):
line_can_cut_list.append(0)
j = 0
for string in string_list:
j = j + len(string)
# print(j)
line_can_cut_list[j - 1] = 1
# ================对标点和语气词进行纠正================
for i in range(len(plain_line)):
if plain_line[i] in ',.?!，。…？！”·-》>:】【]、':
# 这些之前不可切
line_can_cut_list[i - 1] = 0
elif plain_line[i] in '“《<【[':
# 这些之后不可切
line_can_cut_list[i] = 0
elif plain_line[
i] in '上中下内出完的地得了吗吧着个就前世里嘛图们来呗' and line_can_cut_list[
i - 1] == 1 and line_can_cut_list[i] == 1:
# 这些之前不可切
line_can_cut_list[i - 1] = 0
elif plain_line[i] in '太每帮跟另' and line_can_cut_list[
i - 1] == 1 and line_can_cut_list[i] == 1:
# 这些之后不可切
line_can_cut_list[i] = 0
print(line_can_cut_list)
print(current_cut_list)
# ================判断方案正确与否================
sum = 0
cut_right = True
for i in range(len(current_cut_list)): # 切分
last_sum = sum
sum = sum + int(current_cut_list[i])
print(line_can_cut_list[sum - 1])
print(plain_line[last_sum:sum])
if line_can_cut_list[sum - 1] == 0:
cut_right = False
print(cut_right)
if not cut_right:
current_i += 1
if cut_right: # 切对了
cut_right_count += 1
sum = 0
for i in range(len(current_cut_list)):
last_sum = sum
sum = sum + int(current_cut_list[i])
output_line = plain_line[last_sum:sum]
output_line_format_list = line_formmat_list_all[a][
last_sum:sum]
output_line_mark_count_list = []
format_list_for_use = [0] + output_line_format_list + [
0
] # 11
for b in range(len(format_list_for_use) - 1):
output_line_mark_count = abs(format_list_for_use[b +
1] -
format_list_for_use[b])
output_line_mark_count_list.append(
output_line_mark_count)
print(output_line_mark_count_list) # 10
output_markdown_line = ''
for c in range(len(output_line_mark_count_list) - 1):
for d in range(output_line_mark_count_list[c]):
output_markdown_line += '*'
output_markdown_line += output_line[c]
for d in range(output_line_mark_count_list[-1]):
output_markdown_line += '*'
output_readline.append(output_markdown_line)
print("格式", output_line_format_list)
else: # 切错了
output_readline.append(text_readline[a])
cut_wrong_count += 1
elif status == 0: # 不需要切
output_readline.append('\n|\n')
else: # 不需要切
output_readline.append(text_readline[a].replace("\[", "[").replace(
"\]", "]"))
print('切对', cut_right_count)
print('待切', cut_wrong_count)
# ================写入剪贴板================
text = '\r\n'.join(output_readline)
MyDef.WriteClip(text)
print(MyDef.RunTime(start_time))
all_count = len(output_readline) - 1
print(all_count)
text = '\r\n'.join(output_readline)
# print(text)
output_file_name = '0 Day Week文件地址-墨问非名制作-' + now_date + '(' + str(
all_count) + ').csv'
output_file_path = os.path.join(dropbox_path, output_file_name)
f = open(output_file_path, 'w')
try:
f.write(text)
finally:
f.close()
# ================写入剪贴板================
markdown_text = '\r\n'.join(markdown_readline)
MyDef.WriteClip(markdown_text)
# ================运行时间计时================
run_time = time.time() - start_time
if run_time < 60: # 秒(两位小数)
print("耗时:{:.2f}秒".format(run_time))
elif run_time < 3600: # 分+秒(取整)
print("耗时:{:.0f}分{:.0f}秒".format(run_time // 60, run_time % 60))
else: # 时分秒取整
print("耗时:{:.0f}时{:.0f}分{:.0f}秒".format(run_time // 3600,
run_time % 3600 // 60,
run_time % 60))
def ComixIssue(search_comic_name="Transformers"):
from lxml import html
import requests, time, re
# ========================输入区开始========================
save_comic_name = search_comic_name.replace(":", "").replace(
"/", "").replace("&", "").replace(" ", " ")
key_title = search_comic_name.replace(" ", "-")
print(key_title)
url_prefix = 'https://www.comixology.com/search?search='
comic_url = url_prefix + search_comic_name # 完整的查询网址
# ========================执行区开始========================
page = requests.get(comic_url) # 获取网页信息
tree = html.fromstring(page.text) # 构筑查询用树
# ====================找到系列====================
all_url = tree.xpath('//a[@class="content-details"]/@href')
print(len(all_url))
issues_url = [] # 每期网址
check_set = set() # 重复检查
info_dict = {}
alter_info_dict = {}
major_key_list = []
for i in range(len(all_url)):
entry_start_time = time.time()
print(i)
print(all_url[i])
if re.match(r'.*/digital-comic/[^?]*',
all_url[i]) and key_title in all_url[i]:
matches = re.match(r'.*/digital-comic/[^?]*', all_url[i])
short_link = matches.group(0)
if short_link not in check_set: # 尚未读取过
check_set.add(short_link)
print("获取中……")
issues_url.append(short_link)
# ========================执行区开始========================
page = requests.get(short_link) # 获取网页信息
tree = html.fromstring(page.text) # 构筑查询用树
# ====================关键词列表====================
key_word_list = [
"Written by", "Art by", "Pencils", "Inks", "Colored by",
"Cover by", "Genres", "Digital Release Date",
"Print Release Date", "Page Count", "Age Rating",
"Sold by", "About Book"
]
# ====================标题====================
title = tree.xpath('//h1[@class="title"]/text()')[0]
# ====================简介====================
raw_description = tree.xpath(
'//section[@class="item-description"]/text()') # 列表
description = "".join(raw_description)
formatted_description = description.strip("\n\t").replace(
"\r\n", "|")
formatted_description = formatted_description.replace(
"\r", "|").replace("\n", "|")
# ====================创作信息====================
credit_list = []
raw_credits = tree.xpath(
'//div[@class="credits"]//*/text()') # 列表
for i in range(len(raw_credits)):
credit_line = raw_credits[i].strip("\t\n")
if credit_line != "" and credit_line != "HIDE...":
credit_list.append(credit_line)
credit = "\n".join(credit_list)
# ====================评价数====================
rating_count = ""
try:
review_count = tree.xpath(
'//div[@itemprop="reviewCount"]/text()')[0]
rating_count = review_count.replace(
"Average Rating (", "").replace("):", "")
except:
pass
# ====================价格====================
price = ""
try:
price = tree.xpath('//h5[@class="item-price"]/text()')[0]
except:
pass
# ====================封面====================
cover_image_url = ""
try:
cover_image_url = tree.xpath(
'//img[@class="cover"]/@src')[0]
except:
pass
# ====================编剧====================
writer = ""
item = "Written by"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
writer = temp_store
# ====================画师====================
artist = ""
item = "Art by"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
artist = temp_store
# ====================铅稿====================
penciller = ""
item = "Pencils"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
penciller = temp_store
# ====================墨线====================
inker = ""
item = "Inks"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
inker = temp_store
# ====================上色====================
colorist = ""
item = "Colored by"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
colorist = temp_store
# ====================填字====================
letterer = ""
item = "Lettered by"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
letterer = temp_store
# ====================封面====================
cover_artist = ""
item = "Cover by"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
cover_artist = temp_store
# ====================类型====================
genres = ""
item = "Genres"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
genres = temp_store
# ====================故事线====================
story_arc = ""
item = "Story Arc"
if item in credit_list:
item_index = credit_list.index(item)
temp_store = credit_list[item_index + 1]
while credit_list[item_index + 2] not in key_word_list:
item_index += 1
temp_store = temp_store + "|" + credit_list[item_index
+ 1]
story_arc = temp_store
# ====================数字出版日期====================
digital_release_date = ""
item = "Digital Release Date"
if item in credit_list:
time_string = credit_list[credit_list.index(item) + 1]
time_convert = time.strptime(time_string, "%B %d %Y")
digital_release_date = time.strftime(
"%Y-%m-%d", time_convert)
# ====================实体出版日期====================
print_release_date = ""
item = "Print Release Date"
if item in credit_list:
time_string = credit_list[credit_list.index(item) + 1]
time_convert = time.strptime(time_string, "%B %d %Y")
print_release_date = time.strftime("%Y-%m-%d",
time_convert)
# ====================页数====================
page_count = ""
item = "Page Count"
if item in credit_list:
page_count = (credit_list[credit_list.index(item) +
1]).replace(" Pages", "")
# ====================年龄评级====================
age_rating = ""
item = "Age Rating"
if item in credit_list:
age_rating = (credit_list[credit_list.index(item) +
1]).replace(" Only", "")
# ====================出版公司====================
publisher = ""
item = "Sold by"
if item in credit_list:
publisher = credit_list[credit_list.index(item) + 1]
# ====================输出区开始====================
line_info = [
title, digital_release_date, print_release_date, price,
page_count, age_rating, rating_count, publisher, genres,
story_arc, writer, artist, penciller, inker, colorist,
letterer, cover_artist, short_link, cover_image_url,
formatted_description
]
this_line = "\t".join(line_info) # 行信息合并
print(this_line)
major_key = digital_release_date + title # "日期+标题"作为主键
major_key_list.append(major_key)
info_dict[major_key] = line_info
major_key_list.sort() # 主键表排序
text_list = []
for key in major_key_list:
text_list.append(info_dict[key])
# ================写入TXT================
txt_file_path = '/Users/alicewish/Dropbox/Comixology刊物' + save_comic_name + '.csv' # TXT文件名
head_info = [
"标题", "数字出版日期", "实体出版日期", "价格", "页数", "分级", "评价数", "出版商",
"类型", "故事线", "编剧", "画师", "铅笔稿", "墨线", "上色师", "填字员", "封面画师",
"短链", "封面图地址", "简介"
]
MyDef.StoreCSV(text_list, txt_file_path, head_info)
# ====================次级输出区开始====================
alter_line_info = ["### " + title, formatted_description]
alter_line = "\r\n".join(alter_line_info) # 行信息合并
print(alter_line)
alter_info_dict[major_key] = alter_line
major_key_list.sort() # 主键表排序
alter_text_list = []
for key in major_key_list:
alter_text_list.append(alter_info_dict[key])
alter_text = "\r\n".join(alter_text_list)
# ================写入TXT================
alter_txt_file_path = '/Users/alicewish/我的坚果云/Comixology简介' + save_comic_name + '.txt' # TXT文件名
f = open(alter_txt_file_path, 'w')
try:
f.write(alter_text)
finally:
f.close()
entry_run_time = time.time() - entry_start_time
print("耗时:{:.2f}秒".format(entry_run_time))
# ========================输出区开始========================
print("总共" + str(len(issues_url)) + "期")
def ReadMD5SamplingCSV():
import os, MyDef
dropbox_path = '/Users/alicewish/Dropbox'
refer_file_name = '漫画图源MD5随机分样表.csv'
refer_file_path = os.path.join(dropbox_path, refer_file_name)
return MyDef.ReadDictB(refer_file_path)
output_readline.append(output_line)
this_week_readline.append(magnet_list[0])
this_week_readline.append(magnet_list[1])
# ================写入文本================
text = '\r\n'.join(output_readline)
print(text)
f = open(output_file_path, 'w')
try:
f.write(text)
finally:
f.close()
info = "\r\n".join(this_week_readline)
print(info)
print(len(this_week_readline))
MyDef.Clipboard(info)
# ================运行时间计时================
run_time = time.time() - start_time
if run_time < 60: # 两位小数的秒
print("耗时:{:.2f}秒".format(run_time))
elif run_time < 3600: # 分秒取整
print("耗时:{:.0f}分{:.0f}秒".format(run_time // 60, run_time % 60))
else: # 时分秒取整
print("耗时:{:.0f}时{:.0f}分{:.0f}秒".format(run_time // 3600,
run_time % 3600 // 60,
run_time % 60))