我必须将一些数据导出到Excel,但我希望它根据类别(用户名,时间,正文,标签,链接)将列表导出到列中
我在这里错过了什么因为我连续得到了所有东西。
lists =[]
lists2=[]
lists3=[]
lists4=[]
lists5=[]
for i in range(0,33):
link = (df.link.iloc[i])
source1 = urllib.request.urlopen(link).read()
soup1 = bs.BeautifulSoup(source1,'lxml')
for username in soup1.find_all('div', class_="user-name"):
lists.append([username.get_text().strip()])
for time in soup1.find_all('div',class_="thread-ago"):
lists2.append([time.get_text().strip()])
for body in soup1.find_all('div',class_="thread-body"):
lists3.append([body.get_text().strip()])
for tags in soup1.find_all('div', class_="data-tag"):
lists4.append([tags.get_text().strip()])
for inlink in soup1.find_all('a',class_="thread-detail"):
lists5.append([inlink.get('href')])
rows = zip(lists,lists2,lists3, lists4,lists5)
example = open('generalinfo.csv','w')
for column in rows:
wr = csv.writer(example,quoting = csv.QUOTE_ALL,delimiter = ",")
wr.writerows(column)
example.close()
答案 0 :(得分:0)
试试这个
lists =[]
lists2=[]
lists3=[]
lists4=[]
lists5=[]
for i in range(0,33):
link = (df.link.iloc[i])
source1 = urllib.request.urlopen(link).read()
soup1 = bs.BeautifulSoup(source1,'lxml')
for username in soup1.find_all('div', class_="user-name"):
lists.append([username.get_text().strip()])
for time in soup1.find_all('div',class_="thread-ago"):
lists2.append([time.get_text().strip()])
for body in soup1.find_all('div',class_="thread-body"):
lists3.append([body.get_text().strip()])
for tags in soup1.find_all('div', class_="data-tag"):
lists4.append([tags.get_text().strip()])
for inlink in soup1.find_all('a',class_="thread-detail"):
lists5.append([inlink.get('href')])
rows = zip(lists,lists2,lists3, lists4,lists5)
with open('generalinfo.csv','w') as csvfile:
wr = csv.writer(csvfile,quoting = csv.QUOTE_ALL,delimiter = ",")
for row in rows:
wr.writerows([row])