Python爬取网页信息的示例

def get_url1():
 urls=[]
 # A,'B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z'
 a=['A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']　　　　#自动生成A~Z的链接
 for i in a:
  urls.append("https://nameberry.com/search/baby_names_starting_with/%s" %i)
 dp=pd.DataFrame(urls)
 dp.to_csv("A~Z_Link1.csv",mode="a",encoding='utf_8_sig')　　　　#循环用于在每个字母链接下，调用爬取名字链接的页面的函数，即函数嵌套
 for j in urls:
  get_pages_Html(j)
 return urls

#获取页数
def get_pages_Html(url1):
 req = requests.get(url1)
 soup=BeautifulSoup(req.text)
#异常处理，为解决页面不存在多页的问题，使用re正则表达式获取页面数
 try:
  lastpage = soup.find(class_="last").find("a")['href']
  str1='{}'.format(lastpage)
  b=re.findall('\\d+', str1 )
  for page in b:
   num=page
 except:
  num=1
 get_pages(num,url1)
 return num

def get_pages(n,url):
 pages=[]
 for k in range(1,int(n)+1):
  pages.append("{}?page={}".format(url,k))
 dp=pd.DataFrame(pages)
 dp.to_csv("NUM_pages_1.csv",mode="a",encoding='utf_8_sig')
  #函数调用
 for l in pages:
  parse_HTML2(l)
 return pages


# 名字的链接，根据网页源码的标签，确定名字链接的位置
def parse_HTML2(url2):
 try:
  req = requests.get(url2)
  req.encoding = req.apparent_encoding
  soup = BeautifulSoup(req.text)
 except:
  dp=pd.DataFrame(url2)
  dp.to_csv("Error_pages_1.csv",mode="a",encoding='utf_8_sig')
 name_data_l=[]
 error=[]
 li_list = soup.find_all('li',class_="Listing-name pt-15 pb-15 bdb-gray-light w-100pct flex border-highlight")
 try:
  for li in li_list:
   nameList=li.find('a',class_='flex-1')['href']
   name_data_l.append('https://nameberry.com/'+nameList)
   time.sleep(1)
  cun(name_data_l,'Name_List_1')
 except:
  dp=pd.DataFrame(name_data_l)
  dp.to_csv("Error_Name_List_1.csv",mode="a",encoding='utf_8_sig')
  # cun(url2,'Error_link_Q')
 # dp=pd.DataFrame(name_data_l)
 # dp.to_csv("Name_List.csv",mode="a",encoding='utf_8_sig')
 # for i in name_data_l:
 #  parse_HTML3(i)
 return name_data_l

# 名字里的内容
def parse_HTML3(url3):
 count=0
 req = requests.get(url3)
 req.encoding = req.apparent_encoding
 soup = BeautifulSoup(req.text)
 error=[]
 try:
  Name=soup.find('h1',class_='first-header').find("a").get_text().replace(",","").replace("\n","")
 except:
  error.append(url3)
  cun(error,"Error_Link_Comment")
 li_list = soup.find_all('div',class_="comment")
 for li in li_list:
  Title=li.find("h4").get_text().replace(",","").replace("\n","")
  Time=li.find("p",class_='meta').get_text().replace(",","").replace("\n","")
  Comments=li.find("div",class_='comment-text').get_text().replace(",","").replace("\n","")
  dic2={
   "Name":Name,
   "Title":Title,
   "Time":Time,
   "Comments":Comments
  }
  time.sleep(1)
  count=count+1
  save_to_csv(dic2,"Name_data_comment")
  print(count)
 return 1