对 Python Beautifulsoup 中提取的 table 数据的结果进行分组以提高可读性
Grouping results from Python Beautifulsoup extracted table data for more readability
以下代码片段有效，但为了便于阅读，我需要帮助将结果格式化为屏幕。
from urllib.request import Request, urlopen,urljoin
from bs4 import BeautifulSoup
import re, random, ctypes
import requests
from time import sleep
url = 'https://bscscan.com/tokentxns'
user_agent_list = [
"header = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:86.0Gecko/20100101 Firefox/86.0'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.1 Safari/605.1.15'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36'}"
]
header = random.choice(user_agent_list)
req = requests.get(url,header, timeout=10)
soup = BeautifulSoup(req.content, 'html.parser')
rows = soup.findAll('table')[0].findAll('tr')
for row in rows[1:]:
tds = row.find_all('td')
txnhash = tds[1].text[0:]
value = tds[7].text[0:]
token = tds[8].text[0:]
link = urljoin(url, tds[8].find('a')['href'])
print(str(link)[26:] +"\t" + str(token) + "\t\t" + str(value))
当前输出：
0x154a9f9cbd3449ad22fdae23044319d6ef2a1fab CryptoBlades... (SKILL) 0
0x46d502fac9aea7c5bc7b13c8ec9d02378c33d36f WolfSafePoor... (WSPP) 532,654,321,110
0xb510e39a6cc3ebe999ff957ae7b5813d3326af88 GoldenBresco (GoBo) 0.1
0xbb4cdb9cbd36b01bd1cbaebf2de08d9173bc095c Wrapped BNB (WBNB) 0.193446389516094066
0xb510e39a6cc3ebe999ff957ae7b5813d3326af88 GoldenBresco (GoBo) 0.003
需要改进：# 分成 3 列
0x154a9f9cbd3449ad22fdae23044319d6ef2a1fab CryptoBlades... (SKILL) 2.746949883778173559
CryptoBlades... (SKILL) 0.971749999999999991
CryptoBlades... (SKILL) 0
0xbb4cdb9cbd36b01bd1cbaebf2de08d9173bc095c Wrapped BNB (WBNB) 0.1
Wrapped BNB (WBNB) 0.193446389516094066
Wrapped BNB (WBNB) 0.3
尝试：
import requests
from bs4 import BeautifulSoup
from itertools import groupby
url = "https://bscscan.com/tokentxns"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
data = []
for tr in soup.select("tr:has(td)"):
tds = [td.get_text(strip=True) for td in tr.select("td")]
_, txn_hash, tm, age, from_, _, to_, value, token = tds
data.append((txn_hash, token, value))
data = sorted(data)
for _, g in groupby(data, lambda k: k[0]):
g = list(map(list, g))
for subl in g[1:]:
subl[0] = ""
for subl in g:
print("{:<67} {:<27} {:<20}".format(*subl))
print()
打印：
0x0883f7ada1e30d266366577dbc46cd86a8deb737d669758a443ef03859ea551a FEGtoken (FEG) 1,946,201,644.40754275
Wrapped BNB (WBNB) 0.025356409113673479
0x41a7e28aa1f88522ba477718f9ea93d927bd8c456cd77c75691d961ac01da626 KOMOCOIN (KMC) 1,500
KOMOCOIN (KMC) 750
0x54bf03ddb42a151920fc2352a8419ed24720422b79c4956c74ab1d51aead142e BABY CAKE (BABYCA...) 140.806276687606518422
BABY CAKE (BABYCA...) 165.654443161890021673
BABY CAKE (BABYCA...) 2,164,578.319665288243959287
BABY CAKE (BABYCA...) 238.930554998160499529
BABY CAKE (BABYCA...) 42.164215587910676387
BABY CAKE (BABYCA...) 462,482.805614060076081865
BABY CAKE (BABYCA...) 797.902234563103604395
BABY CAKE (BABYCA...) 938.708511250710122817
BABY CAKE PR...(BBCAKE...) 190,322,532.495690243057683413
BABY CAKE PR...(BBCAKE...) 2,526,729.458161278746350005
BABY CAKE PR...(BBCAKE...) 251,979.604709746169304594
BABY CAKE PR...(BBCAKE...) 252,609.914806456810514054
BABY CAKE PR...(BBCAKE...) 36,251,910.951560046296701602
BABYCAKE_Div...(BABYCA...) 238.930554998160499529
Pancake LPs (Cake-L...) 0.222139817418176568
Pancake LPs (Cake-L...) 13.786493105169560097
Pancake LPs (Cake-L...) 486.96534350290155168
Pancake LPs (Cake-L...) 5.76850094907955108
PancakeSwap ...(Cake) 0.001286990618481616
PancakeSwap ...(Cake) 0.112893929385320841
PancakeSwap ...(Cake) 1.497338191475435628
PancakeSwap ...(Cake) 61.821404790611192339
PancakeSwap ...(Cake) 61.821404790611192339
Wrapped BNB (WBNB) 0.000146050638113703
Wrapped BNB (WBNB) 0.000146050638113703
Wrapped BNB (WBNB) 0.00146079350317574
Wrapped BNB (WBNB) 0.109629866733835175
Wrapped BNB (WBNB) 0.610745057130530703
Wrapped BNB (WBNB) 2.850122532653068215
0x6cc6153aa387de6a56c905f7d424ec38f047fefdcc2b7d766c53db7807b6f562 CryptoBlades...(SKILL) 0.005999999999999999
CryptoBlades...(SKILL) 0.06
0x776a1edc9446cc3e160cb08a69e2824dab0e6df7b6c79f252a1c9a0de4733bd4 Arena Token (ARENA) 0.000802589119468346
Arena Token (ARENA) 0.037402597402597402
Arena Token (ARENA) 0.374025974025974025
0x7ca15e96d56d686d79a93271e192021fefed01187dce424bec835f1a6a47b937 CryptoBlades...(SKILL) 0.971749999999999991
0x7f6bada297def57a2d1823000d464923187bea376c5747ba6ebe0b63b1ae1850 CryptoBlades...(SKILL) 0
0x8ddaceff011648b2f13128c8ce4ff5654171878200e12f2ce8f9cf3ec4ab97a3 CryptoBlades...(SKILL) 0.051999999999999999
CryptoBlades...(SKILL) 0.52
0x91d299dc263ac4e30027c5e54e5a5fd4fd2fb814db7c0fc00643764f8710e47b CryptoBlades...(SKILL) 0
0xa097fad173e3d6551e2a837048f40348ffcafc710ca13410de1fb532f2833ba7 Niubi Token (NIU) 2,152.08364390963091904
Wrapped BNB (WBNB) 0.05
0xf2c10ec09049cd810c3aac459b85b9bbbcbb53f3b78341d24af1cab585d6e1ba Foxy Equilib...(Foxy) 0.9
Foxy Equilib...(Foxy) 0.9
Foxy Equilib...(Foxy) 7.2
0xf5b44e82e4e4509d59b51491ce1bfa44888fae2c11a65bd5021d2aed9c75afd4 CryptoBlades...(SKILL) 0.055005280975673767
Wrapped BNB (WBNB) 0.022533425242910644
编辑：打印令牌 URL 而不是名称：
import requests
from bs4 import BeautifulSoup
from itertools import groupby
url = "https://bscscan.com/tokentxns"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
data = []
for tr in soup.select("tr:has(td)"):
tds = [td.get_text(strip=True) for td in tr.select("td")]
_, txn_hash, tm, age, from_, _, to_, value, token = tds
a = "https://bscscan.com" + tr.select("a")[-1]["href"]
data.append((txn_hash, a, value))
data = sorted(data)
for _, g in groupby(data, lambda k: k[0]):
g = list(map(list, g))
for subl in g[1:]:
subl[0] = ""
for subl in g:
print("{:<67} {:<27} {:<20}".format(*subl))
print()
我没有收到您关于 pastebin 的回复，所以这是我给出的简单样式化数据框的方法。我在评论中说过，您似乎真的只想按第一列排序，然后不要在该列中重复项目。您可以这样做 sort_values()，并使用 duplicated() 将重复项替换为 ''。我借用了 Andrej 的（赞成的）更简洁的语法来填充列表列表。
您可以根据需要设置数据框的样式。例如，我隐藏了单元格之间的边框并将背景设置为白色。
import pandas as pd
from bs4 import BeautifulSoup
import requests, random
url = 'https://bscscan.com/tokentxns'
user_agent_list = [
"header = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:86.0Gecko/20100101 Firefox/86.0'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.1 Safari/605.1.15'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36'}"
]
header = random.choice(user_agent_list)
req = requests.get(url,header, timeout=10)
soup = BeautifulSoup(req.content, 'html.parser')
df_rows = []
for tr in soup.select("tr:has(td)"):
tds = [td.get_text(strip=True) for td in tr.select("td")]
_, txnhash, tm, age, from_, _, to_, value, token = tds
df_rows.append([txnhash, token, value])
df = pd.DataFrame(df_rows, columns = ['hash', 'token', 'value'])
df['value'] = pd.to_numeric(df['value'].apply(lambda x: x.replace(',','')))
df.sort_values(['hash', 'token'], inplace = True)
df.hash = [i[1] if not i[0] else '' for i in zip(df.duplicated(subset=['hash']), df.hash)]
#df.reset_index(drop = True, inplace = True)
df.style.format(formatter={('value'): "{:,.3f}"}).hide_index() \
.set_properties(**{'background-color': 'white', 'text-align': 'left'}, padding="10px", border='0px solid white') \
.set_table_styles([dict(selector='th', props=[('text-align', 'left')])])
以下代码片段有效，但为了便于阅读，我需要帮助将结果格式化为屏幕。
from urllib.request import Request, urlopen,urljoin
from bs4 import BeautifulSoup
import re, random, ctypes
import requests
from time import sleep
url = 'https://bscscan.com/tokentxns'
user_agent_list = [
"header = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:86.0Gecko/20100101 Firefox/86.0'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.1 Safari/605.1.15'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36'}"
]
header = random.choice(user_agent_list)
req = requests.get(url,header, timeout=10)
soup = BeautifulSoup(req.content, 'html.parser')
rows = soup.findAll('table')[0].findAll('tr')
for row in rows[1:]:
tds = row.find_all('td')
txnhash = tds[1].text[0:]
value = tds[7].text[0:]
token = tds[8].text[0:]
link = urljoin(url, tds[8].find('a')['href'])
print(str(link)[26:] +"\t" + str(token) + "\t\t" + str(value))
当前输出：
0x154a9f9cbd3449ad22fdae23044319d6ef2a1fab CryptoBlades... (SKILL) 0
0x46d502fac9aea7c5bc7b13c8ec9d02378c33d36f WolfSafePoor... (WSPP) 532,654,321,110
0xb510e39a6cc3ebe999ff957ae7b5813d3326af88 GoldenBresco (GoBo) 0.1
0xbb4cdb9cbd36b01bd1cbaebf2de08d9173bc095c Wrapped BNB (WBNB) 0.193446389516094066
0xb510e39a6cc3ebe999ff957ae7b5813d3326af88 GoldenBresco (GoBo) 0.003
需要改进：# 分成 3 列
0x154a9f9cbd3449ad22fdae23044319d6ef2a1fab CryptoBlades... (SKILL) 2.746949883778173559
CryptoBlades... (SKILL) 0.971749999999999991
CryptoBlades... (SKILL) 0
0xbb4cdb9cbd36b01bd1cbaebf2de08d9173bc095c Wrapped BNB (WBNB) 0.1
Wrapped BNB (WBNB) 0.193446389516094066
Wrapped BNB (WBNB) 0.3
尝试：
import requests
from bs4 import BeautifulSoup
from itertools import groupby
url = "https://bscscan.com/tokentxns"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
data = []
for tr in soup.select("tr:has(td)"):
tds = [td.get_text(strip=True) for td in tr.select("td")]
_, txn_hash, tm, age, from_, _, to_, value, token = tds
data.append((txn_hash, token, value))
data = sorted(data)
for _, g in groupby(data, lambda k: k[0]):
g = list(map(list, g))
for subl in g[1:]:
subl[0] = ""
for subl in g:
print("{:<67} {:<27} {:<20}".format(*subl))
print()
打印：
0x0883f7ada1e30d266366577dbc46cd86a8deb737d669758a443ef03859ea551a FEGtoken (FEG) 1,946,201,644.40754275
Wrapped BNB (WBNB) 0.025356409113673479
0x41a7e28aa1f88522ba477718f9ea93d927bd8c456cd77c75691d961ac01da626 KOMOCOIN (KMC) 1,500
KOMOCOIN (KMC) 750
0x54bf03ddb42a151920fc2352a8419ed24720422b79c4956c74ab1d51aead142e BABY CAKE (BABYCA...) 140.806276687606518422
BABY CAKE (BABYCA...) 165.654443161890021673
BABY CAKE (BABYCA...) 2,164,578.319665288243959287
BABY CAKE (BABYCA...) 238.930554998160499529
BABY CAKE (BABYCA...) 42.164215587910676387
BABY CAKE (BABYCA...) 462,482.805614060076081865
BABY CAKE (BABYCA...) 797.902234563103604395
BABY CAKE (BABYCA...) 938.708511250710122817
BABY CAKE PR...(BBCAKE...) 190,322,532.495690243057683413
BABY CAKE PR...(BBCAKE...) 2,526,729.458161278746350005
BABY CAKE PR...(BBCAKE...) 251,979.604709746169304594
BABY CAKE PR...(BBCAKE...) 252,609.914806456810514054
BABY CAKE PR...(BBCAKE...) 36,251,910.951560046296701602
BABYCAKE_Div...(BABYCA...) 238.930554998160499529
Pancake LPs (Cake-L...) 0.222139817418176568
Pancake LPs (Cake-L...) 13.786493105169560097
Pancake LPs (Cake-L...) 486.96534350290155168
Pancake LPs (Cake-L...) 5.76850094907955108
PancakeSwap ...(Cake) 0.001286990618481616
PancakeSwap ...(Cake) 0.112893929385320841
PancakeSwap ...(Cake) 1.497338191475435628
PancakeSwap ...(Cake) 61.821404790611192339
PancakeSwap ...(Cake) 61.821404790611192339
Wrapped BNB (WBNB) 0.000146050638113703
Wrapped BNB (WBNB) 0.000146050638113703
Wrapped BNB (WBNB) 0.00146079350317574
Wrapped BNB (WBNB) 0.109629866733835175
Wrapped BNB (WBNB) 0.610745057130530703
Wrapped BNB (WBNB) 2.850122532653068215
0x6cc6153aa387de6a56c905f7d424ec38f047fefdcc2b7d766c53db7807b6f562 CryptoBlades...(SKILL) 0.005999999999999999
CryptoBlades...(SKILL) 0.06
0x776a1edc9446cc3e160cb08a69e2824dab0e6df7b6c79f252a1c9a0de4733bd4 Arena Token (ARENA) 0.000802589119468346
Arena Token (ARENA) 0.037402597402597402
Arena Token (ARENA) 0.374025974025974025
0x7ca15e96d56d686d79a93271e192021fefed01187dce424bec835f1a6a47b937 CryptoBlades...(SKILL) 0.971749999999999991
0x7f6bada297def57a2d1823000d464923187bea376c5747ba6ebe0b63b1ae1850 CryptoBlades...(SKILL) 0
0x8ddaceff011648b2f13128c8ce4ff5654171878200e12f2ce8f9cf3ec4ab97a3 CryptoBlades...(SKILL) 0.051999999999999999
CryptoBlades...(SKILL) 0.52
0x91d299dc263ac4e30027c5e54e5a5fd4fd2fb814db7c0fc00643764f8710e47b CryptoBlades...(SKILL) 0
0xa097fad173e3d6551e2a837048f40348ffcafc710ca13410de1fb532f2833ba7 Niubi Token (NIU) 2,152.08364390963091904
Wrapped BNB (WBNB) 0.05
0xf2c10ec09049cd810c3aac459b85b9bbbcbb53f3b78341d24af1cab585d6e1ba Foxy Equilib...(Foxy) 0.9
Foxy Equilib...(Foxy) 0.9
Foxy Equilib...(Foxy) 7.2
0xf5b44e82e4e4509d59b51491ce1bfa44888fae2c11a65bd5021d2aed9c75afd4 CryptoBlades...(SKILL) 0.055005280975673767
Wrapped BNB (WBNB) 0.022533425242910644
编辑：打印令牌 URL 而不是名称：
import requests
from bs4 import BeautifulSoup
from itertools import groupby
url = "https://bscscan.com/tokentxns"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
data = []
for tr in soup.select("tr:has(td)"):
tds = [td.get_text(strip=True) for td in tr.select("td")]
_, txn_hash, tm, age, from_, _, to_, value, token = tds
a = "https://bscscan.com" + tr.select("a")[-1]["href"]
data.append((txn_hash, a, value))
data = sorted(data)
for _, g in groupby(data, lambda k: k[0]):
g = list(map(list, g))
for subl in g[1:]:
subl[0] = ""
for subl in g:
print("{:<67} {:<27} {:<20}".format(*subl))
print()
我没有收到您关于 pastebin 的回复，所以这是我给出的简单样式化数据框的方法。我在评论中说过，您似乎真的只想按第一列排序，然后不要在该列中重复项目。您可以这样做 sort_values()，并使用 duplicated() 将重复项替换为 ''。我借用了 Andrej 的（赞成的）更简洁的语法来填充列表列表。
您可以根据需要设置数据框的样式。例如，我隐藏了单元格之间的边框并将背景设置为白色。
import pandas as pd
from bs4 import BeautifulSoup
import requests, random
url = 'https://bscscan.com/tokentxns'
user_agent_list = [
"header = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:86.0Gecko/20100101 Firefox/86.0'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.1.1 Safari/605.1.15'}",
"header = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36'}",
"header = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36'}"
]
header = random.choice(user_agent_list)
req = requests.get(url,header, timeout=10)
soup = BeautifulSoup(req.content, 'html.parser')
df_rows = []
for tr in soup.select("tr:has(td)"):
tds = [td.get_text(strip=True) for td in tr.select("td")]
_, txnhash, tm, age, from_, _, to_, value, token = tds
df_rows.append([txnhash, token, value])
df = pd.DataFrame(df_rows, columns = ['hash', 'token', 'value'])
df['value'] = pd.to_numeric(df['value'].apply(lambda x: x.replace(',','')))
df.sort_values(['hash', 'token'], inplace = True)
df.hash = [i[1] if not i[0] else '' for i in zip(df.duplicated(subset=['hash']), df.hash)]
#df.reset_index(drop = True, inplace = True)
df.style.format(formatter={('value'): "{:,.3f}"}).hide_index() \
.set_properties(**{'background-color': 'white', 'text-align': 'left'}, padding="10px", border='0px solid white') \
.set_table_styles([dict(selector='th', props=[('text-align', 'left')])])