def dowaloadTxt():
# csv_file = csv.reader(open(txt_list, 'r'))
# txts = []
# for i in csv_file:
# temp = []
# temp.append(i[0])
# temp.append(i[1])
# temp.append(i[2])
# txts.append(temp)
test = 'https://www.jjxs.la/txt/31534.htm'
bs = SpiderHtml(test).getBeautifulSoup(baseurl)
download_link = bs.find('ul', class_='downlistbox').find('a')['href']
print(download_link)
bs = SpiderHtml(baseurl + download_link).getBeautifulSoup(baseurl)
trs = bs.find_all('td')[0].find_all('tr')
for i in trs:
a_s = i.find_all('a')
for j in a_s:
if j.text == 'TXT电子书下载地址【无需解压缩】':
print(j['href'])
folder= '穿越小说'
if not (os.path.exists(folder)):
os.makedirs(folder)
DownloadBinaryFile(baseurl + j['href'],folder+'/小说1.txt').load()
pass
def getTxtListInfo(cate, link, num):
print('-----开始获取' + cate + str(num) + '下的小说-----')
url = baseurl + link + 'index_' + str(num) + '.html'
print(url)
bs = SpiderHtml(url=url).getBeautifulSoup(baseurl)
info_list = bs.find('div', id='catalog').find_all('div', class_='listbg')
f = open(txt_list, 'a+', newline='')
csv_write = csv.writer(f)
try:
for i in info_list:
temp = []
temp.append(i.a['href']) # 链接
temp.append(i.a['title']) # 小说名
date = ''
try:
date = i.find('span', class_='newDate').text
except Exception as e:
date = i.find('span', class_='oldDate').text
temp.append(date)
csv_write.writerow(temp)
except Exception as e:
print(e)
return 0
def runInfo():
print()
# 需要加referer
soup = SpiderHtml('http://www.mmjpg.com/mm/1316').getBeautifulSoup(base)
content = soup.find('div', id='content').a.img['src']
print(content)
DownloadUtils.DownloadBinaryFileWithReferer(content, '1.jpg', base).load()
def getInfoNum(url, name):
print()
soup = SpiderHtml(url).getBeautifulSoup(base)
page = 0
try:
page = soup.find('div', id='page').find_all('a')[-2].text
except Exception as e:
print()
print(name + " 共" + str(page) + '页 ' + '链接：' + url)
return int(page)
def getListNum(url, name):
page = 1
try:
soup = SpiderHtml(url).getBeautifulSoup(base)
page = soup.find('div', class_='page').find_all('a')[-1]['href']
page = page.split('/')[-1]
except Exception as e:
print()
print(name + " 共 " + str(page) + "页")
return int(page)
def runList():
print()
soup = SpiderHtml('http://www.mmjpg.com/tag/xinggan').getBeautifulSoup(
base)
li_s = soup.find(class_='pic').find('ul').find_all('li')
print(len(li_s))
for i in li_s:
# 获取名字，链接
print('链接是：' + i.a['href']) # link
print('名字是：' + i.find_all('span')[0].text) # name
print('发布时间：' + i.find_all('span')[1].text) # time
def runTags():
soup = SpiderHtml(url=url).getBeautifulSoup(base)
tags = soup.find(id='morelist').find_all('li')
print(len(tags))
with open(tag_csv_name, "a+", encoding="utf-8") as f:
writer = csv.writer(f)
for i in tags:
print(i)
list = []
list.append(i.a['href']) # link
list.append(i.a.img['src']) # img
list.append(i.a.img['data-img']) # img
list.append(i.find('i').text) # num
list.append(i.a.text) # name
writer.writerow(list)