def duowanfunc():
girlurl=rq_girl.get()
r=requests.get(girlurl)
soup=BeautifulSoup(r.text,"html.parser")
# girlpage=soup.find('td',id=re.compile('postmessage.*'),attrs={'class':'t_f'})
girlpage=soup.find('div',attrs={'class':'t_fsz'})
if not girlpage:
return
IDkeys=['ID','id']
# 提取妹纸id
p=re.compile('(?:id|ID)[\s|:|：|;|；]*(\S+)\s*')
girlpagetext=girlpage.text
nickname=p.findall(girlpagetext)
# 判断是否存在id关键字
if len(nickname)<1:
return False
# 判断有没有照片
pics=girlpage.find_all('img',zoomfile=True)
if len(pics)<1:
return False
# nickname=nickname[0]
# 保存图片url
if len(pics)>5:
pics=pics[:5]
piclist=[utils.quote_url(pic.attrs['zoomfile']) for pic in pics]
return {'nickname':nickname,'picurls':piclist}
def duowanlol1():
pre_url=r"http://bbs.duowan.com/"
url="http://bbs.duowan.com/forum.php?mod=forumdisplay&fid=1343&orderby=dateline&typeid=7092&filter=author&orderby=dateline&typeid=7092&page=%s"
i=0
while True:
time.sleep(1)
# 计数循环
i+=1
if i==1000:
return
purl=url % i
r=requests.get(purl)
p=re.compile('求封面</a>\]</em> <span id="thread_\d+?"><a href="(.+?)"')
# urls=[pre_url+x for x in p.findall(r.text)]
urls=p.findall(r.text)
if urls is None:
return
for x in urls:
tmp=pre_url+utils.quote_url(x)
rq.put(tmp)
print(tmp)
print('=========duowan1-',i,' =========')
def qqlol():
pre_url=r"http://bbs.lol.qq.com/"
url="http://bbs.lol.qq.com/forum.php?mod=forumdisplay&fid=205&typeid=966&typeid=966&filter=typeid&page=%d"
i=0
while True:
time.sleep(1)
# 计数循环
i+=1
if i==1000:
return
purl=url % i
r=requests.get(purl)
p=re.compile('我要曝照</a>\]</em> <a href="(.+?)"')
# urls=[pre_url+x for x in p.findall(r.text)]
urls=p.findall(r.text)
if urls is None:
return
for x in urls:
tmp=pre_url+utils.quote_url(x)
rq.put(tmp)
print(tmp)
print('=========qqlol-',i,' =========')
def duowanlol1():
pre_url = r"http://bbs.duowan.com/"
url = "http://bbs.duowan.com/forum.php?mod=forumdisplay&fid=1343&orderby=dateline&typeid=7092&filter=author&orderby=dateline&typeid=7092&page=%s"
i = 0
while True:
time.sleep(1)
# 计数循环
i += 1
if i == 1000:
return
purl = url % i
r = requests.get(purl)
p = re.compile('求封面</a>\]</em> <span id="thread_\d+?"><a href="(.+?)"')
# urls=[pre_url+x for x in p.findall(r.text)]
urls = p.findall(r.text)
if urls is None:
return
for x in urls:
tmp = pre_url + utils.quote_url(x)
rq.put(tmp)
print(tmp)
print('=========duowan1-', i, ' =========')
def qqlol():
pre_url = r"http://bbs.lol.qq.com/"
url = "http://bbs.lol.qq.com/forum.php?mod=forumdisplay&fid=205&typeid=966&typeid=966&filter=typeid&page=%d"
i = 0
while True:
time.sleep(1)
# 计数循环
i += 1
if i == 1000:
return
purl = url % i
r = requests.get(purl)
p = re.compile('我要曝照</a>\]</em> <a href="(.+?)"')
# urls=[pre_url+x for x in p.findall(r.text)]
urls = p.findall(r.text)
if urls is None:
return
for x in urls:
tmp = pre_url + utils.quote_url(x)
rq.put(tmp)
print(tmp)
print('=========qqlol-', i, ' =========')