使用 BeautifulSoup 从 python 导出到 .csv
Exporting to .csv from python with BeautifulSoup
我对此很陌生,似乎无法正确导出它。
# select document
with open('scrape1.html') as html_file:
soup = BeautifulSoup(html_file, 'lxml')
# create/name csv
with open('speechengine_report.csv', 'w') as csv_file:
writer = csv.writer(csv_file)
writer.writerow(['computer', 'usagedata'])
# tell bs4 to only look at x tags with a class of y
for licensedata in soup.find_all('div', class_='licensedata'):
# scrape pc id
computer = licensedata.p.b.text
print(computer)
# scrape usage stats for each id
for usagedata in licensedata.find_all('td'):
# minutes = usagedata.table.tbody
print(usagedata.text)
# blank line
print()
# writer.writerow([computer, usagedata])
csv_file.close()
您要将数据写入 csv 文件的其余代码应位于 with 块中。此外,您不需要 csv_file.close() 因为 with 可以为您处理。试试下面的代码。阅读 file handling in python
with open('scrape1.html') as html_file:
soup = BeautifulSoup(html_file, 'lxml')
# create/name csv
with open('speechengine_report.csv', 'w') as csv_file:
writer = csv.writer(csv_file)
writer.writerow(['computer', 'usagedata'])
# tell bs4 to only look at x tags with a class of y
for licensedata in soup.find_all('div', class_='licensedata'):
# scrape pc id
computer = licensedata.p.b.text
print(computer)
# scrape usage stats for each id
for usagedata in licensedata.find_all('td'):
# minutes = usagedata.table.tbody
print(usagedata.text)
# blank line
print()
# writer.writerow([computer, usagedata])
我对此很陌生,似乎无法正确导出它。
# select document
with open('scrape1.html') as html_file:
soup = BeautifulSoup(html_file, 'lxml')
# create/name csv
with open('speechengine_report.csv', 'w') as csv_file:
writer = csv.writer(csv_file)
writer.writerow(['computer', 'usagedata'])
# tell bs4 to only look at x tags with a class of y
for licensedata in soup.find_all('div', class_='licensedata'):
# scrape pc id
computer = licensedata.p.b.text
print(computer)
# scrape usage stats for each id
for usagedata in licensedata.find_all('td'):
# minutes = usagedata.table.tbody
print(usagedata.text)
# blank line
print()
# writer.writerow([computer, usagedata])
csv_file.close()
您要将数据写入 csv 文件的其余代码应位于 with 块中。此外,您不需要 csv_file.close() 因为 with 可以为您处理。试试下面的代码。阅读 file handling in python
with open('scrape1.html') as html_file:
soup = BeautifulSoup(html_file, 'lxml')
# create/name csv
with open('speechengine_report.csv', 'w') as csv_file:
writer = csv.writer(csv_file)
writer.writerow(['computer', 'usagedata'])
# tell bs4 to only look at x tags with a class of y
for licensedata in soup.find_all('div', class_='licensedata'):
# scrape pc id
computer = licensedata.p.b.text
print(computer)
# scrape usage stats for each id
for usagedata in licensedata.find_all('td'):
# minutes = usagedata.table.tbody
print(usagedata.text)
# blank line
print()
# writer.writerow([computer, usagedata])