def print_character_pinyin(self, characters):
pinyin = CHARACTER_PINYIN_MAPPING.get(characters, '')
pinyins = []
pinyin_nums = []
if not pinyin:
pinyin = Pinyin().get_pinyin(characters, ' ', tone_marks='marks')
pinyin_num = Pinyin().get_pinyin(characters,
' ',
tone_marks='numbers')
pinyins = pinyin.split(' ')
pinyin_nums = pinyin_num.split(' ')
else:
for p in pinyin.split(' '):
r = decode_pinyin(p)
pinyins.append(r)
print(f'''"{characters}": "{''.join(pinyin_nums)}",''')
return pinyins
def download(self):
global condition
condition = ""
# 定义爬取信息
pinyin = Pinyin().get_pinyin(self.keyword)
pinyinList = pinyin.split("-")
keywordPinyin = "".join(pinyinList)
URLToScrap = "https://818ps.com/muban/0-0-0-0-%s-null-52_24_0_0-0-0-0.html?route_id=&route=&after_route=" % str(
keywordPinyin)
URLData = urllib.request.urlopen(URLToScrap).read().decode(
"utf-8", "ignore")
imageExp = "/pic/(.*?).html"
imageURLList = re.compile(imageExp).findall(URLData)
imageURLList = list(set(imageURLList))
# 处理信息填写及错误
if len(imageURLList) == 0:
print("没有搜索到相关海报")
condition = "img:none"
elif self.count > len(imageURLList):
print("数量过多\n最多%s张" % len(imageURLList))
condition = "img:overflow"
elif not self.infoIsCorrect():
print('下载信息填写错误！')
condition = "info:error"
print(infoIsCorrect(printReason=True))
else:
# 网站请求错误处理
try:
# 重复下载需要的图片
imageCount = self.count
if self.count == 0: # 规则：如果数量为0，下载全部
imageCount = len(imageURLList)
for imgSerial in range(imageCount):
imgNumber = str(imageURLList[imgSerial])
detailImgURL = "https://818ps.com/detail/" + imgNumber + ".html"
detailData = urllib.request.urlopen(
detailImgURL).read().decode("utf-8", "ignore")
detailImageExp = 'https://img.tuguaishou.com/ips_templ_preview/(.*?)"'
detailImgURLArg = re.compile(detailImageExp).findall(
detailData)
for i in range(len(detailImgURLArg)):
finalImageURL = "https://img.tuguaishou.com/ips_templ_preview/" + str(
detailImgURLArg[i])
finalImgFileID = str(imgSerial) + '-' + str(imgNumber)
print("正在下载：编号为%s的图片..." % finalImgFileID)
# 保存图片
file = self.path + str(
self.keyword
) + "-" + finalImgFileID + "." + self.suffix
if self.isTest == False:
self.images.append(file)
urllib.request.urlretrieve(finalImageURL,
filename=file)
print("下载完成！目录：", file)
else:
print("测试完成！测试伪目录：", file)
# 错误处理
except urllib.error.URLError as e:
if hasattr(e, 'code'):
print(e.code)
if hasattr(e, "reason"):
print(e.reason)
